From a984374fddd308f1458151534f4d5aceddf5336b Mon Sep 17 00:00:00 2001 From: Thomas Schaffter Date: Thu, 9 Nov 2023 00:00:25 +0000 Subject: [PATCH 1/4] Experimenting --- .../notebook/challenge_headlines.json | 3203 +---------------- .../challenge_headline_llm.py | 9 +- 2 files changed, 77 insertions(+), 3135 deletions(-) diff --git a/apps/openchallenges/notebook/challenge_headlines.json b/apps/openchallenges/notebook/challenge_headlines.json index b953035c13..1d696a4b09 100644 --- a/apps/openchallenges/notebook/challenge_headlines.json +++ b/apps/openchallenges/notebook/challenge_headlines.json @@ -3,3249 +3,188 @@ "id": 1, "slug": "network-topology-and-parameter-inference", "name": "Network Topology and Parameter Inference", - "headline": "", - "headline_alternatives": [ - "1. Optimize methods to estimate biology model parameters", - "2. Develop optimization for accurate biology model predictions ", - "3. Apply optimization to estimate parameters in Systems Biology", - "4. Select experiments to optimize Systems Biology model accuracy", - "5. Perturbation prediction through optimization of Systems Biology models" - ] + "headline": "Optimize methods to estimate biology model parameters for Network Topology a...", + "headline_alternatives": [] }, { "id": 2, "slug": "breast-cancer-prognosis", "name": "Breast Cancer Prognosis", - "headline": "", - "headline_alternatives": [ - "1. Predict breast cancer survival from clinical and genomic data", - "2. Assess models for breast cancer prognosis using clinical and molecular data ", - "3. Evaluate computational models for breast cancer survival prediction", - "4. Benchmark algorithms to predict breast cancer prognosis ", - "5. Assess accuracy of models predicting breast cancer patient survival" - ] + "headline": "Predict breast cancer survival from clinical and genomic data for Breast Can...", + "headline_alternatives": [] }, { "id": 3, "slug": "phil-bowen-als-prediction-prize4life", "name": "Phil Bowen ALS Prediction Prize4Life", - "headline": "", - "headline_alternatives": [ - "1. Seeking treatment to halt ALS's fatal loss of motor function ", - "2. Stopping ALS from rapidly killing nerve cells controlling muscles", - "3. Finding a cure for ALS, which currently has no treatment options", - "4. Developing new ways to prolong life for ALS patients ", - "5. Discovering risk factors and treatment for ALS, a fatal disease" - ] + "headline": "Seeking treatment to halt ALS's fatal loss of motor function for Phil Bowen ...", + "headline_alternatives": [] }, { "id": 4, "slug": "drug-sensitivity-and-drug-synergy-prediction", "name": "Drug Sensitivity and Drug Synergy Prediction", - "headline": "", - "headline_alternatives": [] + "headline": "Revolutionizing Cancer Therapeutics: Predicting Drug Sensitivity in Human Ce...", + "headline_alternatives": [ + "1. Seeking computational methods to predict chemotherapeutic response from cancer cell line data (98 characters)", + "2. Develop models predicting drug response in cancer using cell line genomic profiles (93 characters) ", + "3. Improve cancer treatment by modeling drug sensitivity from cell line data (84 characters)", + "4. Identify chemotherapeutic response using computational analysis of cell lines (95 characters)", + "5. Create new ways to predict best cancer drugs from cell line experiments (97 characters)" + ] }, { "id": 5, "slug": "niehs-ncats-unc-toxicogenetics", "name": "NIEHS-NCATS-UNC Toxicogenetics", - "headline": "", - "headline_alternatives": [ - "1. Predicting cytotoxicity from genomic and chemical data", - "2. Modeling cytotoxicity responses to chemicals ", - "3. Forecasting cytotoxic effects of compounds", - "4. Estimating cytotoxicity in cell lines via models", - "5. Cytotoxicity challenge: predict toxicity from data" - ] + "headline": "Predicting cytotoxicity from genomic and chemical data for NIEHS-NCATS-UNC T...", + "headline_alternatives": [] }, { "id": 6, "slug": "whole-cell-parameter-estimation", "name": "Whole-Cell Parameter Estimation", - "headline": "", - "headline_alternatives": [ - "1. Seeking innovative parameter estimation methods for large models", - "2. Comparing optimization approaches for parameterizing complex simulations ", - "3. Collaborate to find best methods for estimating large model parameters", - "4. Developing new techniques to select informative experiments ", - "5. Form teams to find optimal approaches to parameterize big models" - ] + "headline": "Seeking innovative parameter estimation methods for large models for Whole-C...", + "headline_alternatives": [] }, { "id": 7, "slug": "hpn-dream-breast-cancer-network-inference", "name": "HPN-DREAM Breast Cancer Network Inference", - "headline": "", - "headline_alternatives": [ - "1. Inferring causal signaling networks in breast cancer", - "2. Advancing network inference in breast cancer cells ", - "3. Predicting phospho-dynamics from cancer cell line data", - "4. Breast cancer challenge - infer networks from perturbations", - "5. Using perturbations to infer breast cancer networks" - ] + "headline": "Inferring causal signaling networks in breast cancer for HPN-DREAM Breast Ca...", + "headline_alternatives": [] }, { "id": 8, "slug": "rheumatoid-arthritis-responder", "name": "Rheumatoid Arthritis Responder", - "headline": "", + "headline": "Unlocking Anti-TNF Response Predictors: A Crowdsourced Breakthrough in RA Th...", "headline_alternatives": [] }, { "id": 9, "slug": "icgc-tcga-dream-mutation-calling", "name": "ICGC-TCGA DREAM Mutation Calling", - "headline": "", + "headline": "Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection for ICGC-...", "headline_alternatives": [ - "1. Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection", - "2. Open Challenge Aims to Advance Cancer Genomics Analysis Methods ", - "3. International Effort to Boost Cancer Mutation Identification in Genomes", - "4. Challenge Pursues Innovation in Detecting Cancer Mutations in DNA", - "5. Scientists Initiate Contest to Improve Identification of Cancer Mutations" + "1. Global contest to advance cancer mutation detection in genome sequences. (100 characters)", + "2. International competition to improve identification of cancer mutations from DNA data. (99 characters) ", + "3. Worldwide effort to enhance techniques for finding cancer mutations in genomes. (97 characters)", + "4. Open challenge to progress methods for detecting genomic changes linked to cancer. (95 characters)", + "5. Crowdsourced contest pushing innovation in cancer genomics analysis methods. (99 characters)" ] }, { "id": 10, "slug": "acute-myeloid-leukemia-outcome-prediction", "name": "Acute Myeloid Leukemia Outcome Prediction", - "headline": "", + "headline": "Uncover drivers of AML using clinical and proteomic data for Acute Myeloid L...", "headline_alternatives": [ - "1. Uncover drivers of AML using clinical and proteomic data", - "2. Predict AML outcomes with clinical and proteomic datasets ", - "3. Tailor AML therapies using challenge insights on drivers", - "4. Accelerate leukemia drug development with challenge insights", - "5. Interpret rich AML dataset to uncover disease drivers" + "1. Uncover drivers of AML using clinical, genomic, and proteomic data for 271 AML patients. (99 characters)", + "2. Interpret rich AML dataset to predict outcomes and tailor therapies for leukemia patients. (91 characters)", + "3. Leverage clinical, mutation, and protein data to understand AML biology and improve patient care. (99 characters) ", + "4. Analyze proteomic profiles of 271 AML patients to uncover disease drivers and inform treatment. (99 characters)", + "5. Harness multi-omics AML data to accelerate leukemia drug development and precision medicine. (97 characters)" ] }, { "id": 11, "slug": "broad-dream-gene-essentiality-prediction", "name": "Broad-DREAM Gene Essentiality Prediction", - "headline": "", + "headline": "Crowdsourcing Models to Predict Cancer Cell Gene Dependencies for Broad-DREA...", "headline_alternatives": [ - "1. Crowdsourcing Models to Predict Cancer Cell Gene Dependencies", - "2. Competition to Develop Models Predicting Essential Cancer Genes ", - "3. Contest to Find Biomarkers Predicting Key Cancer Genes", - "4. Crowdsourced Models to Infer Cancer Cell Gene Importance ", - "5. Competition to Develop Cancer Gene Dependency Predictors" + "1. Crowdsourcing models to predict essential cancer genes from cell features (82 characters)", + "2. Inferring cancer cell gene dependencies from genomic biomarkers (76 characters)", + "3. Modeling cancer cell viability using gene expression and mutations (71 characters) ", + "4. Predicting essential genes in cancer cells via crowdsourcing (69 characters)", + "5. Crowd-based models to find key cancer genes and biomarkers (69 characters)" ] }, { "id": 12, "slug": "alzheimers-disease-big-data", "name": "Alzheimer's Disease Big Data", - "headline": "", - "headline_alternatives": [ - "1. Seeking Accurate Predictive Biomarkers for Alzheimer's Diagnosis", - "2. Leveraging Data to Improve Alzheimer's Disease Diagnosis and Treatment ", - "3. Applying Open Science to Identify Alzheimer's Biomarkers", - "4. First in Series to Use Big Data for Alzheimer's Biomarker Discovery", - "5. Alzheimer's Data Challenge Seeks Improved Diagnostic Biomarkers" - ] + "headline": "Seeking Accurate Predictive Biomarkers for Alzheimer's Diagnosis for Alzheim...", + "headline_alternatives": [] }, { "id": 13, "slug": "olfaction-prediction", "name": "Olfaction Prediction", - "headline": "", + "headline": "Predicting smell from molecule features for Olfaction Prediction", "headline_alternatives": [ - "1. Predicting smell from molecule features", - "2. Linking molecules to odor perception", - "3. Accelerating fragrance design through smell prediction ", - "4. Modeling how molecules become smell sensations", - "5. Connecting chemical features to odor predictions" + "1. Predicting odor from molecular features to understand smell perception (82 characters)", + "2. Linking molecular properties to odor for fragrance design breakthroughs (91 characters)", + "3. Modeling how molecules' features relate to smell to advance fragrance creation (99 characters) ", + "4. Connecting chemical qualities to odor perception, accelerating fragrance development (93 characters)", + "5. Understanding smell from molecules, enabling faster fragrance ingredient discovery (97 characters)" ] }, { "id": 14, "slug": "prostate-cancer", "name": "Prostate Cancer", - "headline": "", - "headline_alternatives": [ - "1. Predict survival of docetaxel treatment in mCRPC patients", - "2. Establish benchmarks for mCRPC prognosis modeling ", - "3. Improve predictions for docetaxel toxicity and survival ", - "4. Enhance understanding of mCRPC progression via modeling", - "5. Benchmark prognostic models for mCRPC with docetaxel" - ] + "headline": "Predict survival of docetaxel treatment in mCRPC patients for Prostate Cancer", + "headline_alternatives": [] }, { "id": 15, "slug": "als-stratification-prize4life", "name": "ALS Stratification Prize4Life", - "headline": "", + "headline": "Advancing ALS Treatment: Predicting Disease Progression and Survival with Data.", "headline_alternatives": [] }, { "id": 16, "slug": "astrazeneca-sanger-drug-combination-prediction", "name": "AstraZeneca-Sanger Drug Combination Prediction", - "headline": "", - "headline_alternatives": [ - "1. Predict effective drug combinations using genomic data", - "2. Explore traits underlying synergistic drug combinations ", - "3. Accelerate understanding of drug synergy with genomic data", - "4. Model synergistic drug behavior using pre-treatment data", - "5. Predict drug combination efficacy from genomic profiles" - ] + "headline": "Predict effective drug combinations using genomic data for AstraZeneca-Sange...", + "headline_alternatives": [] }, { "id": 17, "slug": "smc-dna-meta", "name": "SMC-DNA Meta", - "headline": "", + "headline": "Seeking Most Accurate Somatic Mutation Detection Pipeline for SMC-DNA Meta", "headline_alternatives": [ - "1. Seeking Most Accurate Somatic Mutation Detection Pipeline", - "2. Establishing State-of-the-Art for Cancer Mutation Detection ", - "3. Identifying Best Meta-Pipeline for Detecting Somatic Mutations", - "4. Challenge to Find Top Cancer Mutation Detection Algorithm", - "5. Competition to Determine Ideal Somatic Mutation Calling Process" + "1. Seeking most accurate pipeline for detecting cancer mutations from callers", + "2. Establishing state-of-the-art in somatic mutation detection from predictors ", + "3. Identifying best meta-pipeline for somatic mutation calls from variants", + "4. Understanding complementarity of algorithms for cancer mutation detection", + "5. Highlighting advantages and deficiencies of somatic mutation callers" ] }, { "id": 18, "slug": "smc-het", "name": "SMC-Het", - "headline": "", + "headline": "Crowdsourcing Challenge to Improve Tumor Subclonal Reconstruction for SMC-Het", "headline_alternatives": [ - "1. Crowdsourcing Challenge to Improve Tumor Subclonal Reconstruction", - "2. Open Challenge to Advance Tumor Heterogeneity Quantification ", - "3. International Effort to Progress Tumor Subclonal Profiling", - "4. Crowdsourcing Tumor Heterogeneity and Subclonal Genotyping", - "5. Advancing Subclonal Reconstruction of Tumor Heterogeneity" + "1. Crowdsourcing challenge to improve subclonal reconstruction from tumor sequencing data. (99 characters)", + "2. Open challenge to advance quantification and genotyping of tumor subclones. (87 characters)", + "3. International effort to enhance tumor heterogeneity profiling from sequencing. (97 characters)", + "4. Collaborative challenge to progress tumor subclonal reconstruction methods. (97 characters) ", + "5. Crowdsourcing tumor heterogeneity profiling through subclonal reconstruction. (99 characters)" ] }, { "id": 19, "slug": "respiratory-viral", "name": "Respiratory Viral", - "headline": "", + "headline": "Unraveling Viral Susceptibility: Early Predictors of Respiratory Infection a...", "headline_alternatives": [] }, { "id": 20, "slug": "disease-module-identification", "name": "Disease Module Identification", - "headline": "", - "headline_alternatives": [ - "1. Crowdsourcing challenge to find disease modules in genomic networks", - "2. Open effort to assess module ID methods on disease networks ", - "3. Discover novel modules in genomic networks related to disease", - "4. Leverage crowd wisdom to identify disease modules in networks", - "5. Assess module identification methods on genomic networks for disease" - ] - }, - { - "id": 21, - "slug": "encode", - "name": "ENCODE", - "headline": "", - "headline_alternatives": [ - "1. Predict transcription factor binding sites from limited data", - "2. Computationally expand knowledge of transcription factor binding", - "3. Improve prediction of in vivo transcription factor binding sites ", - "4. Model transcription factor binding across cell types and conditions", - "5. Complement experimental binding data with computational prediction" - ] - }, - { - "id": 22, - "slug": "idea", - "name": "Idea", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 23, - "slug": "smc-rna", - "name": "SMC-RNA", - "headline": "", - "headline_alternatives": [ - "1. Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection from RNA Data", - "2. Open Challenge Aims to Advance Identification of Cancer Mutations with RNA Sequencing ", - "3. International Effort to Boost Detection of Cancer Mutations from RNA Sequencing Data", - "4. Dream Challenge Focuses on Improving Identification of Cancer Mutations in RNA Sequencing", - "5. ICGC and TCGA Launch Crowdsourcing Effort to Improve RNA Methods for Finding Cancer Mutations" - ] - }, - { - "id": 24, - "slug": "digital-mammography", - "name": "Digital Mammography", - "headline": "", - "headline_alternatives": [ - "1. Improve mammography prediction to detect breast cancer early", - "2. Enhance tools for decreasing recall rate in mammography screening ", - "3. Establish new methods to shift screening towards more benefit, less harm", - "4. Develop models using mammography images to predict breast cancer", - "5. Create tools to help reduce unnecessary mammography recalls" - ] - }, - { - "id": 25, - "slug": "multiple-myeloma", - "name": "Multiple Myeloma", - "headline": "", - "headline_alternatives": [ - "1. Develop precise risk model for myeloma patients", - "2. Improve patient stratification for myeloma treatment ", - "3. Benchmark analytical methods to optimize myeloma care", - "4. Integrate data to tackle myeloma risk stratification ", - "5. Seek new therapies for high-risk myeloma patients" - ] - }, - { - "id": 26, - "slug": "ga4gh-dream-workflow-execution", - "name": "GA4GH-DREAM Workflow Execution", - "headline": "", - "headline_alternatives": [ - "1. Develop technologies to enable distributed genomic data analysis", - "2. Create modular pipelines for reproducible genomic data analysis ", - "3. Build tools to run genomic analyses across distributed datasets", - "4. Design APIs and workflows to find and access genomic resources ", - "5. Leverage containers and pipelines for portable genomic data analysis" - ] - }, - { - "id": 27, - "slug": "parkinsons-disease-digital-biomarker", - "name": "Parkinson's Disease Digital Biomarker", - "headline": "", - "headline_alternatives": [ - "1. Benchmarking methods to develop Parkinson's digital signatures from sensor data", - "2. Extracting predictive features from sensor data for Parkinson's digital biomarkers ", - "3. Developing Parkinson's digital biomarkers from raw sensor time series data", - "4. Predicting Parkinson's pathology from sensor data features in DREAM challenge", - "5. First challenge to extract Parkinson's digital biomarkers from raw sensor data" - ] - }, - { - "id": 28, - "slug": "nci-cptac-proteogenomics", - "name": "NCI-CPTAC Proteogenomics", - "headline": "", - "headline_alternatives": [ - "1. Develop tools to extract insights from cancer proteomics data ", - "2. Create computational methods to analyze tumor proteomes", - "3. Build models linking genome to proteome in cancer", - "4. Advance proteomics to revolutionize cancer research", - "5. Create powerful computational tools for cancer proteomics" - ] - }, - { - "id": 29, - "slug": "multi-targeting-drug", - "name": "Multi-Targeting Drug", - "headline": "", - "headline_alternatives": [ - "1. Seeking Generalizable Methods to Predict Multi-Target Compound Binding", - "2. Develop Techniques to Forecast Binding of Compounds to Multiple Targets ", - "3. Challenge: Predict Compound Binding Across Various Targets and Anti-Targets", - "4. Wanted: Approaches to Anticipate Compound Affinity for Multiple Proteins ", - "5. Can You Devise Ways to Foresee What Compounds Will Bind to Many Targets?" - ] - }, - { - "id": 30, - "slug": "single-cell-transcriptomics", - "name": "Single Cell Transcriptomics", - "headline": "", - "headline_alternatives": [ - "1. Reconstructing Cell Locations in Drosophila Embryo from Transcripts", - "2. Mapping Single Cells in Fly Embryo Using Transcriptomics ", - "3. Locating Cells in Drosophila Embryo Via Single-Cell RNA Data", - "4. Transcriptomics to Map Single Cells in Fruit Fly Embryo ", - "5. Using Transcripts to Pinpoint Cells in Developing Fly Embryo" - ] - }, - { - "id": 31, - "slug": "idg-drug-kinase-binding", - "name": "IDG Drug-Kinase Binding", - "headline": "", - "headline_alternatives": [ - "1. Challenge seeks machine learning for drug-kinase binding prediction", - "2. Evaluating models to predict compound-kinase interactions ", - "3. Mapping kinase inhibitors to targets with machine learning", - "4. Prioritizing potent kinase inhibitor interactions via modeling", - "5. Predicting kinase binding to focus experimental drug discovery" - ] - }, - { - "id": 32, - "slug": "malaria", - "name": "Malaria", - "headline": "", - "headline_alternatives": [ - "1. Predict malaria drug resistance from parasite gene expression", - "2. Model malaria drug resistance using parasite transcription data ", - "3. Forecast Artemisinin resistance in malaria with transcriptomes", - "4. Estimate malaria drug resistance from parasite transcripts", - "5. Predict Artemisinin resistance in malaria parasites computationally" - ] - }, - { - "id": 33, - "slug": "preterm-birth-prediction-transcriptomics", - "name": "Preterm Birth Prediction - Transcriptomics", - "headline": "", - "headline_alternatives": [ - "1. Developing Accurate, Inexpensive Molecular Clock to Determine Gestational Age", - "2. Creating Prediction Models for Gestational Age Using Pregnant Women's Blood", - "3. Identifying and Treating Women at Risk of Preterm Birth and Other Conditions ", - "4. Developing New Ways to Establish Gestational Age to Improve Pregnancy Care", - "5. Using Gene Expression to Build Models Predicting Gestational Age from Blood Samples" - ] - }, - { - "id": 34, - "slug": "single-cell-signaling-in-breast-cancer", - "name": "Single-Cell Signaling in Breast Cancer", - "headline": "", - "headline_alternatives": [ - "1. Exploring heterogeneous signaling in single cancer cells", - "2. Studying variation in breast cancer cell response ", - "3. Mapping diverse signaling in breast cancer lines", - "4. Probing single cell heterogeneity in signaling", - "5. Analyzing large breast cancer signaling dataset" - ] - }, - { - "id": 35, - "slug": "ehr-dream-challenge-patient-mortality-prediction", - "name": "EHR DREAM Challenge - Patient Mortality Prediction", - "headline": "", - "headline_alternatives": [ - "1. New tools to reconstruct cell lineages from CRISPR mutations ", - "2. Assessing algorithms for reconstructing cell lineages from molecular data", - "3. DREAM challenge to accurately reconstruct cell lineages ", - "4. Evaluating lineage reconstruction with diverse tools and datasets", - "5. Machine learning for accurate cell lineage reconstruction" - ] - }, - { - "id": 36, - "slug": "allen-institute-cell-lineage-reconstruction", - "name": "Allen Institute Cell Lineage Reconstruction", - "headline": "", - "headline_alternatives": [ - "1. New tools enable reconstructing complex cell lineages at single-cell resolution", - "2. Assessing algorithms for reconstructing cell lineages from CRISPR mutations ", - "3. DREAM challenge tests reconstructing cell lineages across tools and datasets", - "4. Can machine learning accurately reconstruct diverse cell lineage trees?", - "5. Allen Institute and DREAM partner to benchmark cell lineage reconstruction" - ] - }, - { - "id": 37, - "slug": "tumor-deconvolution", - "name": "Tumor Deconvolution", - "headline": "", - "headline_alternatives": [ - "1. Assess computational methods to deconvolve bulk tumor data into immune components ", - "2. Evaluate computational deconvolution of bulk tumor data into individual immune components", - "3. Test ability of computational methods to deconvolve bulk tumors into immune subpopulations", - "4. Assess deconvolution methods for recovering immune infiltration from bulk tumor data ", - "5. Evaluate computational decomposition of bulk tumors to quantify immune infiltration" - ] - }, - { - "id": 38, - "slug": "ctd2-pancancer-drug-activity", - "name": "CTD2 Pancancer Drug Activity", - "headline": "", - "headline_alternatives": [ - "1. Benchmark algorithms predicting drug targets from gene data", - "2. Develop algorithms to identify drug targets from gene expression", - "3. Predict chemotherapeutic targets using transcriptional profiling ", - "4. Elucidate drug mechanisms of action from gene expression changes", - "5. Identify drug targets across cancers using transcriptomic profiles" - ] - }, - { - "id": 39, - "slug": "ctd2-beataml", - "name": "CTD2 BeatAML", - "headline": "", - "headline_alternatives": [ - "1. Seeking New Drug Targets for Precision AML Treatment", - "2. Discovering Biomarkers to Predict AML Therapy Response ", - "3. Developing a Discovery Cohort to Yield AML Treatment Insights", - "4. Identifying Tailored AML Therapies for Refined Patient Groups", - "5. Studying AML Molecular Alterations and Drug Sensitivity" - ] - }, - { - "id": 40, - "slug": "metadata-automation", - "name": "Metadata Automation", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 41, - "slug": "automated-scoring-of-radiographic-joint-damage", - "name": "Automated Scoring of Radiographic Joint Damage", - "headline": "", - "headline_alternatives": [ - "1. Develop automated method to quantify rheumatoid arthritis joint damage", - "2. Create algorithm to automatically score rheumatoid arthritis radiographs ", - "3. Automate scoring of joint space narrowing in rheumatoid arthritis", - "4. Replace manual scoring with automated rheumatoid arthritis image analysis", - "5. Rapidly quantify rheumatoid arthritis joint damage from radiographs" - ] - }, - { - "id": 42, - "slug": "beat-pd", - "name": "BEAT-PD", - "headline": "", - "headline_alternatives": [ - "1. Develop mobile sensors to remotely monitor Parkinson's disease", - "2. Leverage smartphones and wearables to track Parkinson's symptoms ", - "3. Create digital biomarkers from sensor data for Parkinson's", - "4. Use mobile health to monitor Parkinson's disease progression", - "5. Standardize Parkinson's disease monitoring with mobile sensors" - ] - }, - { - "id": 43, - "slug": "ctd2-pancancer-chemosensitivity", - "name": "CTD2 Pancancer Chemosensitivity", - "headline": "", - "headline_alternatives": [ - "1. Predict drug sensitivity from cell line gene expression", - "2. Benchmark algorithms to predict drug response ", - "3. Develop methods to predict drug sensitivity", - "4. Predict drug sensitivity from RNAseq profiles", - "5. Elucidate drug mechanisms using transcriptional profiles" - ] - }, - { - "id": 44, - "slug": "ehr-dream-challenge-covid-19", - "name": "EHR DREAM Challenge-COVID-19", - "headline": "", - "headline_alternatives": [ - "1. Develop tools to predict COVID-19 risk without sharing data ", - "2. Rapidly discover approaches to characterize COVID-19 using analytics", - "3. Understand risk factors for COVID-19 positive tests from EHRs", - "4. Incorporate machine learning into clinical care to improve COVID-19 outcomes", - "5. Utilize analytics on clinical data to develop early warning for COVID-19" - ] - }, - { - "id": 45, - "slug": "anti-pd1-response-prediction", - "name": "Anti-PD1 Response Prediction", - "headline": "", - "headline_alternatives": [ - "1. Predicting lung cancer response to immuno-oncology therapy", - "2. Modeling outcomes of anti-PD-1 therapy in lung cancer ", - "3. Improving predictions of I-O benefit in lung cancer patients", - "4. Leveraging data to predict I-O response in lung cancer", - "5. Gaining insights into improving I-O therapy for lung cancer" - ] - }, - { - "id": 46, - "slug": "brats-2021-challenge", - "name": "BraTS 2021 Challenge", - "headline": "", - "headline_alternatives": [ - "1. Developing ML methods to analyze brain tumor MRI scans", - "2. Assessing ML techniques for segmenting glioblastoma in MRI images ", - "3. Evaluating approaches for classifying diffuse gliomas in mpMRI data", - "4. Benchmarking algorithms that detect brain tumors in MRI scans", - "5. Advancing image analysis methods for glioblastoma segmentation" - ] - }, - { - "id": 47, - "slug": "cancer-data-registry-nlp", - "name": "Cancer Data Registry NLP", - "headline": "", - "headline_alternatives": [ - "1. Unlocking Clinical Trial Data Hidden in Medical Records", - "2. Natural Language Processing to Improve Clinical Trial Matching ", - "3. Developing NLP to Extract Patient Data from Medical Records", - "4. Evaluating Algorithms to Match Patients to Clinical Trials", - "5. Accessing EHR Text Data to Advance Translational Research" - ] - }, - { - "id": 48, - "slug": "barda-community-challenge-pediatric-covid-19-data-challenge", - "name": "BARDA Community Challenge - Pediatric COVID-19 Data Challenge", - "headline": "", - "headline_alternatives": [ - "1. Models to predict severe COVID-19 in children sought", - "2. Data challenge seeks pediatric COVID-19 risk models ", - "3. Competition seeks models predicting COVID-19 severity in kids", - "4. Challenge seeks tools to identify high-risk pediatric COVID-19 ", - "5. Data competition aims to predict severe pediatric COVID-19" - ] - }, - { - "id": 49, - "slug": "brats-continuous-evaluation", - "name": "BraTS Continuous Evaluation", - "headline": "", - "headline_alternatives": [ - "1. Seeking Innovations To Improve Brain Tumor Diagnosis And Treatment", - "2. Developing New Therapies To Combat Deadly Brain Cancers ", - "3. Overcoming Barriers To Treating Heterogeneous, Treatment-Resistant Brain Tumors", - "4. Improving Brain Tumor Survival Rates And Access To Care Globally", - "5. Advancing Research To Increase Brain Tumor Survival Beyond 15 Months" - ] - }, - { - "id": 50, - "slug": "fets-2022", - "name": "FeTS 2022", - "headline": "", - "headline_alternatives": [ - "1. Benchmarking methods for federated learning in brain tumor segmentation ", - "2. Evaluating weight aggregation and generalizability in federated learning", - "3. Federated learning methods for multi-institutional brain tumor data", - "4. Real-world federated learning for brain tumor segmentation ", - "5. Testing federated training and evaluation for clinical brain scans" - ] - }, - { - "id": 51, - "slug": "random-promotor", - "name": "Random Promotor", - "headline": "", - "headline_alternatives": [ - "1. Decoding Gene Regulation to Understand Disease", - "2. Modeling Complex Gene Expression Regulation ", - "3. Learning Cis-Regulatory Logic of Human Genome", - "4. Understanding Origins of Disease Through Gene Regulation", - "5. Overcoming Limitations to Learn Gene Regulation Models" - ] - }, - { - "id": 52, - "slug": "preterm-birth-prediction-microbiome", - "name": "Preterm Birth Prediction - Microbiome", - "headline": "", - "headline_alternatives": [ - "1. Predict preterm births to reduce infant mortality", - "2. Identify women at risk of preterm delivery ", - "3. Prevent preterm births and improve infant health", - "4. Reduce preterm births and long-term complications ", - "5. Forecast preterm births to enable timely treatment" - ] - }, - { - "id": 53, - "slug": "finrisk", - "name": "FINRISK - Heart Failure and Microbiome", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 54, - "slug": "scrna-seq-and-scatac-seq-data-analysis", - "name": "scRNA-seq and scATAC-seq Data Analysis", - "headline": "", - "headline_alternatives": [ - "1. Assess computational methods for scRNA-seq and scATAC-seq analysis", - "2. Evaluate signal correction and peak identification for single cell sequencing ", - "3. Benchmark methods for sparse data analysis in single cell assays", - "4. Improve quantification and cell typing via better scRNA-seq analysis ", - "5. Develop accurate computational methods for sparse single cell data" - ] - }, - { - "id": 55, - "slug": "cough-diagnostic-algorithm-for-tuberculosis", - "name": "COugh Diagnostic Algorithm for Tuberculosis", - "headline": "", - "headline_alternatives": [ - "1. Develop low-cost cough screening tools to improve TB diagnosis", - "2. Create non-invasive digital cough tests for TB detection ", - "3. Improve TB diagnosis with new cough sound biomarkers ", - "4. Design scalable cough-based TB screening to boost detection", - "5. Build accessible digital cough diagnostics to find missing TB cases" - ] - }, - { - "id": 56, - "slug": "nih-long-covid-computational-challenge", - "name": "NIH Long COVID Computational Challenge", - "headline": "", - "headline_alternatives": [ - "1. Understanding Prevalence and Outcomes of Post-COVID Syndrome", - "2. Analyzing Longitudinal Data to Uncover Post-COVID Sequelae ", - "3. Using Advanced Analytics to Study Post-Acute COVID-19 Symptoms", - "4. Investigating Breadth of Post-COVID Conditions and Outcomes", - "5. Applying Innovative Methods to Assess Post-Acute COVID Sequelae" - ] - }, - { - "id": 57, - "slug": "bridge2ai", - "name": "Bridge2AI", - "headline": "What makes a good color palette?", - "headline_alternatives": [ - "1. Creating an appealing, cohesive color palette ", - "2. Designing color palettes for visual harmony", - "3. Choosing colors that work well together ", - "4. Developing color schemes with visual impact", - "5. Selecting colors for aesthetically pleasing palettes" - ] - }, - { - "id": 58, - "slug": "rare-x-open-data-science", - "name": "RARE-X Open Data Science", - "headline": "", - "headline_alternatives": [ - "1. Unlocking rare disease mysteries through open science collaboration", - "2. Researchers compete to analyze rare disease patient data ", - "3. Data challenge taps researchers to solve pediatric neurodevelopmental unknowns", - "4. Collaboration key to unraveling rare pediatric disease mysteries", - "5. Open science data challenge targets rare childhood brain conditions" - ] - }, - { - "id": 59, - "slug": "cagi5-regulation-saturation", - "name": "CAGI5: Regulation saturation", - "headline": "", - "headline_alternatives": [ - "1. Predicting effects of variants in disease-linked enhancers and promoters", - "2. Assessing variants in regulatory regions of disease genes via reporters ", - "3. Massively parallel reporter assays test variants in enhancers and promoters", - "4. Variant effects on expression: saturated mutagenesis of 14 regulatory regions", - "5. Can we predict regulatory variant effects from saturated mutagenesis data?" - ] - }, - { - "id": 60, - "slug": "cagi5-calm1", - "name": "CAGI5: CALM1", - "headline": "", - "headline_alternatives": [ - "1. Predicting effects of calmodulin variants on yeast growth", - "2. Assessing calmodulin variant impacts on yeast complementation", - "3. Evaluating calmodulin mutations using yeast assay ", - "4. Can yeast growth predict calmodulin variant function?", - "5. High-throughput yeast assay to test calmodulin variants" - ] - }, - { - "id": 61, - "slug": "cagi5-pcm1", - "name": "CAGI5: PCM1", - "headline": "", - "headline_alternatives": [ - "1. Assessing PCM1 variants' impact on zebrafish ventricle", - "2. Do PCM1 mutations affect zebrafish brain ventricles? ", - "3. Testing if PCM1 variants change zebrafish ventricle size", - "4. Schizophrenia PCM1 variants' effects on zebrafish brain", - "5. Zebrafish model tests PCM1 variants' ventricular effects" - ] - }, - { - "id": 62, - "slug": "cagi5-frataxin", - "name": "CAGI5: Frataxin", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 63, - "slug": "cagi5-tpmt", - "name": "CAGI5: TPMT and p10", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 64, - "slug": "cagi5-annotate-all-missense", - "name": "CAGI5: Annotate all nonsynonymous variants", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 65, - "slug": "cagi5-gaa", - "name": "CAGI5: GAA", - "headline": "", - "headline_alternatives": [ - "1. Predict enzyme activity of GAA mutants in Pompe disease", - "2. Assess fractional activity of GAA variants compared to wild-type ", - "3. Model impact of GAA mutations on enzyme function in Pompe", - "4. Estimate relative activity levels for GAA variants found in humans", - "5. Predict effects of GAA missense mutations on enzymatic activity" - ] - }, - { - "id": 66, - "slug": "cagi5-chek2", - "name": "CAGI5: CHEK2", - "headline": "", - "headline_alternatives": [ - "1. Estimate CHEK2 gene variant probabilities in Latino breast cancer cases", - "2. Assess CHEK2 variants in Latina breast cancer cases versus controls ", - "3. Analyze CHEK2 gene variants in Latina breast cancer cohort", - "4. Determine CHEK2 variant probabilities in Latinas with breast cancer", - "5. Calculate likelihood of CHEK2 variants in Latina breast cancer cases" - ] - }, - { - "id": 67, - "slug": "cagi5-enigma", - "name": "CAGI5: ENIGMA", - "headline": "", - "headline_alternatives": [ - "1. Predicting cancer risk from BRCA1/2 gene variants", - "2. Assessing breast cancer risk from BRCA mutations ", - "3. Evaluating BRCA1/2 variants for breast cancer risk", - "4. Identifying high-risk BRCA mutations for breast cancer", - "5. Predicting breast cancer risk from BRCA1/2 mutations" - ] - }, - { - "id": 68, - "slug": "cagi5-mapsy", - "name": "CAGI5: MaPSy", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 69, - "slug": "cagi5-vex-seq", - "name": "CAGI5: Vex-seq", - "headline": "", - "headline_alternatives": [ - "1. Predict splicing changes from variants in globin gene", - "2. Assess variant effects on splicing of globin construct ", - "3. Quantify splicing changes from globin variants in cells", - "4. Estimate globin splicing alterations from DNA variants", - "5. Model globin splicing differences caused by mutations" - ] - }, - { - "id": 70, - "slug": "cagi5-sickkids5", - "name": "CAGI5: SickKids clinical genomes", - "headline": "", - "headline_alternatives": [ - "1. Predict genetic disorders from 30 child genomes and phenotypes. ", - "2. Match 30 child genomes to clinical descriptions to identify disorders.", - "3. Identify disease classes and variants in 30 child genomes and phenotypes. ", - "4. Predict disorders and high-risk variants from 30 child genomes.", - "5. Link 30 child genomes to phenotypes to diagnose genetic diseases." - ] - }, - { - "id": 71, - "slug": "cagi5-intellectual-disability", - "name": "CAGI5: ID Panel", - "headline": "", - "headline_alternatives": [ - "1. Predict phenotypes and variants from gene panel sequences", - "2. Identify variants causing intellectual disability from sequences ", - "3. Predict intellectual disability phenotypes from gene panel data", - "4. Determine phenotypes and causal variants from panel sequences", - "5. Analyze gene sequences to predict neurodevelopmental phenotypes" - ] - }, - { - "id": 72, - "slug": "cagi5-clotting-disease", - "name": "CAGI5: Clotting disease exomes", - "headline": "", - "headline_alternatives": [ - "1. Predicting venous thromboembolism risk in African Americans", - "2. Distinguishing VTE from atrial fibrillation in African Americans ", - "3. Identifying genetic VTE risk factors in African Americans", - "4. Developing tools to anticipate VTE in African Americans", - "5. Using exome data to understand VTE in African Americans" - ] - }, - { - "id": 73, - "slug": "cagi6-sickkids", - "name": "CAGI6: SickKids clinical genomes and transcriptomes", - "headline": "The SickKids Genome Clinic is providing clinical phenotypic information in t...", - "headline_alternatives": [ - "1. Identify genes causing rare diseases using transcriptomics", - "2. Solve undiagnosed genetic disorders with transcriptomics ", - "3. Use transcriptomics to diagnose sick children's diseases", - "4. Transcriptome analysis to identify genetic mechanisms in kids ", - "5. Rare disease diagnosis through transcriptome sequencing" - ] - }, - { - "id": 74, - "slug": "cagi6-cam", - "name": "CAGI6: CaM", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 75, - "slug": "cami-ii", - "name": "CAMI II", - "headline": "", - "headline_alternatives": [ - "1. Assembling and Classifying Microbial Genomes in Complex Samples", - "2. Detecting Pathogens and Profiling Microbial Communities from Metagenomes ", - "3. Binning and Profiling Microbial Taxa Across Diverse Environmental Datasets", - "4. Challenges in Metagenomic Assembly, Binning and Clinical Pathogen Detection", - "5. Assembling, Binning, Profiling Microbial Genomes from Multiple Environments" - ] - }, - { - "id": 76, - "slug": "camda18-metasub-forensics", - "name": "CAMDA18-MetaSUB Forensics", - "headline": "", - "headline_alternatives": [ - "1. Building a metagenomic map of mass-transit systems globally", - "2. Creating a longitudinal map of microbes in mass-transit systems ", - "3. Analyzing microbes in mass-transit systems across multiple cities", - "4. Multi-city analysis of microbes on global mass-transit systems", - "5. First ever global analysis of mass-transit metagenomics across cities" - ] - }, - { - "id": 77, - "slug": "camda18-cmap-drug-safety", - "name": "CAMDA18-CMap Drug Safety", - "headline": "", - "headline_alternatives": [ - "1. Predicting drug toxicity using cell-based gene expression data", - "2. Mitigating drug risk via cell-based genomic profiling ", - "3. Evaluating cell screens to predict drug-induced liver injury", - "4. Understanding toxicity from cell-based genomic responses", - "5. Exploiting cell data to predict human liver drug reactions" - ] - }, - { - "id": 78, - "slug": "camda18-cancer-data-integration", - "name": "CAMDA18-Cancer Data Integration", - "headline": "", - "headline_alternatives": [ - "1. Unify data integration approaches for breast cancer and neuroblastoma ", - "2. Improve data integration for breast cancer and childhood cancer", - "3. Integrate data to advance breast and pediatric cancer care ", - "4. Data integration to enhance breast and neuroblastoma diagnosis", - "5. Harness data to beat breast cancer and neuroblastoma" - ] - }, - { - "id": 79, - "slug": "cafa-4", - "name": "CAFA 4", - "headline": "", - "headline_alternatives": [ - "1. Assessing algorithms for predicting protein function", - "2. Evaluating automated methods to predict protein ontology terms ", - "3. Critical test of protein function prediction algorithms", - "4. Benchmarking protein sequence annotation methods", - "5. Comparing computational protein function predictions" - ] - }, - { - "id": 80, - "slug": "casp13", - "name": "CASP13", - "headline": "", - "headline_alternatives": [ - "1. CASP assesses protein structure prediction methods", - "2. CASP compares computational models to experimental structures ", - "3. CASP advances protein structure modeling capabilities", - "4. CASP evaluates progress in modeling protein structures", - "5. CASP measures accuracy of protein structure predictions" - ] - }, - { - "id": 81, - "slug": "casp14", - "name": "CASP14", - "headline": "", - "headline_alternatives": [ - "1. Assessing progress in protein structure prediction", - "2. Advancing methods for modeling protein structures ", - "3. Community experiment evaluates protein modeling", - "4. Blind assessment tests protein structure prediction", - "5. Modeling protein structures from sequence in CASP14" - ] - }, - { - "id": 82, - "slug": "cfsan-pathogen-detection", - "name": "CFSAN Pathogen Detection", - "headline": "", - "headline_alternatives": [ - "1. Rapidly Identify Food Sources of Outbreaks", - "2. Stop Foodborne Illness Outbreaks Faster ", - "3. Link Food Sources to Outbreaks via Genomics", - "4. Improve Food Safety with Next-Gen Sequencing", - "5. Prevent Foodborne Illness Deaths and Hospitalizations" - ] - }, - { - "id": 83, - "slug": "cdrh-biothreat", - "name": "CDRH Biothreat", - "headline": "", - "headline_alternatives": [ - "1. Identifying infectious diseases from clinical samples using sequencing technology. ", - "2. Diagnosing infections without prior knowledge via next-gen sequencing.", - "3. Revealing disease-causing microbes in patients through genomic fingerprinting. ", - "4. Improving infectious disease diagnostics with high-throughput sequencing.", - "5. Using sequencing to identify pathogens from clinical samples." - ] - }, - { - "id": 84, - "slug": "multi-omics-enabled-sample-mislabeling-correction", - "name": "Multi-omics Enabled Sample Mislabeling Correction", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 85, - "slug": "biocompute-object-app-a-thon", - "name": "BioCompute Object App-a-thon", - "headline": "", - "headline_alternatives": [ - "1. Seeking Standards for Reproducible Bioinformatics Analysis", - "2. Developing Framework for Reproducible HTS Computations ", - "3. Partnering for Community Standards in Bioinformatics", - "4. Creating Reproducible Pipelines for Genomic Analysis", - "5. Establishing Schemas for Reproducible Scientific Workflows" - ] - }, - { - "id": 86, - "slug": "brain-cancer-predictive-modeling-and-biomarker-discovery", - "name": "Brain Cancer Predictive Modeling and Biomarker Discovery", - "headline": "", - "headline_alternatives": [ - "1. Seeking novel biomarkers to advance precision medicine for brain tumors", - "2. Identifying new clinical biomarkers to improve glioma prognosis and treatment ", - "3. Advancing precision medicine for brain tumors through multi-omics biomarkers", - "4. Discovering novel biomarkers to advance precision medicine for gliomas", - "5. Developing new prognostic and predictive markers for glioma treatment" - ] - }, - { - "id": 87, - "slug": "gaining-new-insights-by-detecting-adverse-event-anomalies", - "name": "Gaining New Insights by Detecting Adverse Event Anomalies", - "headline": "", - "headline_alternatives": [ - "1. Seeking Algorithms to Detect Adverse Events in FDA Data", - "2. Developing Methods to Find Anomalies in Public FDA Data ", - "3. Algorithms Wanted for Automatic Adverse Event Detection", - "4. Help Analyze FDA Data to Find Adverse Event Anomalies", - "5. Calling All Developers: Detect Anomalies in FDA Public Data" - ] - }, - { - "id": 88, - "slug": "calling-variants-in-difficult-to-map-regions", - "name": "Calling Variants in Difficult-to-Map Regions", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 89, - "slug": "vha-innovation-ecosystem-and-covid-19-risk-factor-modeling", - "name": "VHA Innovation Ecosystem and COVID-19 Risk Factor Modeling", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 90, - "slug": "covid-19-precision-immunology-app-a-thon", - "name": "COVID-19 Precision Immunology App-a-thon", - "headline": "", - "headline_alternatives": [ - "1. Seeking insights on COVID-19 pathophysiology to enable effective strategies.", - "2. Understanding COVID-19 mechanisms to improve diagnosis, prognosis, treatment. ", - "3. Investigating COVID-19 physiology for better strategies against transmission.", - "4. Exploring COVID-19 pathophysiology to combat widespread infection, save lives.", - "5. Studying COVID-19 disease mechanisms to enable rapid data-sharing, effective strategies." - ] - }, - { - "id": 91, - "slug": "smarter-food-safety-low-cost-tech-enabled-traceability", - "name": "Smarter Food Safety Low Cost Tech-Enabled Traceability", - "headline": "", - "headline_alternatives": [ - "1. Seeking Affordable Tech Solutions for Food Traceability", - "2. Democratizing Benefits of Digitizing Food Data ", - "3. Exploring Low-Cost Options for Food Traceability Systems", - "4. Advancing Widespread Traceability in Food Industry ", - "5. Integrating Data Streams to Improve Food Traceability" - ] - }, - { - "id": 92, - "slug": "tumor-mutational-burden-tmb-challenge-phase-1", - "name": "Tumor Mutational Burden (TMB) Challenge Phase 1", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 93, - "slug": "kits21", - "name": "Kidney and Kidney Tumor Segmentation", - "headline": "", - "headline_alternatives": [ - "1. Contest Seeks Best Kidney Tumor Segmentation System ", - "2. Teams Compete to Develop Top Kidney Cancer Segmenter", - "3. Challenge Tests Algorithms for Kidney Tumor Detection", - "4. Can You Build the Best Kidney Tumor Identifier?", - "5. KiTS21: Automating Kidney Tumor Segmentation" - ] - }, - { - "id": 94, - "slug": "realnoisemri", - "name": "Real Noise MRI", - "headline": "", - "headline_alternatives": [ - "1. Developing fast MRI techniques without fully sampled data ", - "2. Creating fast MRI methods using under sampled k-space data", - "3. Improving fast MRI acquisition without full k-space sampling", - "4. Advancing fast MRI sans complete k-space information ", - "5. Speeding up MRI minus fully sampled k-space data" - ] - }, - { - "id": 95, - "slug": "deep-generative-model-challenge-for-da-in-surgery", - "name": "Deep Generative Model Challenge for DA in Surgery", - "headline": "", - "headline_alternatives": [ - "1. Challenge aims to adapt algorithms from simulation to mitral valve surgery", - "2. Challenge addresses data issues for automatic analysis of mitral repair", - "3. Challenge formulates domain adaptation from simulator to real surgery ", - "4. Challenge provides data to adapt algorithms from simulator to surgery", - "5. Challenge reduces gap between simulation and real mitral valve surgery" - ] - }, - { - "id": 96, - "slug": "aimdatathon", - "name": "AIM Datathon 2020", - "headline": "Join the AI in Medicine ( AIM ) Datathon 2020", - "headline_alternatives": [] - }, - { - "id": 97, - "slug": "opc-recurrence", - "name": "Oropharynx Cancer (OPC) Radiomics Challenge :: Local Recurrence Prediction", - "headline": "Determine from CT data whether a tumor will be controlled by definitive radi...", - "headline_alternatives": [] - }, - { - "id": 98, - "slug": "oropharynx-radiomics-hpv", - "name": "Oropharynx Cancer (OPC) Radiomics Challenge :: Human Papilloma Virus (HPV) Status Prediction", - "headline": "Predict from CT data the HPV phenotype of oropharynx tumors; compare to grou...", - "headline_alternatives": [] - }, - { - "id": 99, - "slug": "data-science-bowl-2017", - "name": "Data Science Bowl 2017", - "headline": "Can you improve lung cancer detection?", - "headline_alternatives": [] - }, - { - "id": 100, - "slug": "predict-impact-of-air-quality-on-death-rates", - "name": "Predict impact of air quality on mortality rates", - "headline": "Predict CVD and cancer caused mortality rates in England using air quality d...", - "headline_alternatives": [ - "1. Predicting England's CVD and Cancer Deaths from Air Pollution Data ", - "2. Air Quality Data to Forecast CVD and Cancer Mortality Rates", - "3. Copernicus Data Used to Predict England's CVD and Cancer Death Toll", - "4. Estimating England's CVD and Cancer Mortality Using Atmospheric Data", - "5. Air Monitoring Service Data to Estimate CVD and Cancer Deaths in England" - ] - }, - { - "id": 101, - "slug": "intel-mobileodt-cervical-cancer-screening", - "name": "Intel & MobileODT Cervical Cancer Screening", - "headline": "Which cancer treatment will be most effective?", - "headline_alternatives": [] - }, - { - "id": 102, - "slug": "msk-redefining-cancer-treatment", - "name": "Personalized Medicine-Redefining Cancer Treatment", - "headline": "Predict the effect of Genetic Variants to enable Personalized Medicine", - "headline_alternatives": [ - "1. Predicting Genetic Variant Effects for Personalized Medicine", - "2. Genetic Variants' Effects Predicted to Enable Precision Medicine ", - "3. Forecasting Genetic Variants' Impacts to Allow Tailored Medicine", - "4. Projecting Genetic Variants' Influences for Customized Medicine", - "5. Estimating Genetic Variants' Consequences to Facilitate Individualized Medicine" - ] - }, - { - "id": 103, - "slug": "mubravo", - "name": "Predicting Cancer Diagnosis", - "headline": "Bravo's machine learning competition!", - "headline_alternatives": [ - "1. Bravo Hosts Machine Learning Competition for Innovators", - "2. Bravo Challenges Innovators in Machine Learning Contest ", - "3. Bravo's Contest Challenges Machine Learning Innovations", - "4. Bravo Invites Innovative Minds to Machine Learning Contest", - "5. Bravo Seeks Innovators for Machine Learning Competition" - ] - }, - { - "id": 104, - "slug": "histopathologic-cancer-detection", - "name": "Histopathologic Cancer Detection", - "headline": "Identify metastatic tissue in histopathologic scans of lymph node sections", - "headline_alternatives": [ - "1. Seeking AI to Detect Cancer Spread in Tissue Scans ", - "2. Can AI Spot Metastasis in Lymph Node Histology?", - "3. Automated Detection of Metastasis in Tissue Images", - "4. Identifying Cancer Spread from Histopathology Scans", - "5. Metastatic Tissue Detection in Lymph Node Sections" - ] - }, - { - "id": 105, - "slug": "tjml1920-decision-trees", - "name": "TJML 2019-20 Breast Cancer Detection Competition", - "headline": "Use a decision tree to identify malignant breast cancer tumors", - "headline_alternatives": [] - }, - { - "id": 106, - "slug": "prostate-cancer-grade-assessment", - "name": "Prostate cANcer graDe Assessment (PANDA) Challenge", - "headline": "Prostate cancer diagnosis using the Gleason grading system", - "headline_alternatives": [ - "1. AI for Prostate Cancer Diagnosis via Gleason Grading", - "2. Gleason-Based AI to Diagnose Prostate Cancer ", - "3. AI System to Grade Prostate Cancer Using Gleason Score", - "4. AI to Diagnose Prostate Cancer Through Gleason Grading ", - "5. Using AI and Gleason System to Diagnose Prostate Cancer" - ] - }, - { - "id": 107, - "slug": "breast-cancer", - "name": "Breast Cancer", - "headline": "Use cell nuclei categories to predict breast cancer tumor.", - "headline_alternatives": [] - }, - { - "id": 108, - "slug": "breast-cancer-detection", - "name": "Breast Cancer Detection", - "headline": "breast cancer detection", - "headline_alternatives": [ - "1. Developing AI to detect breast cancer early", - "2. Creating automated breast cancer screening tools ", - "3. Building algorithms to identify breast tumors", - "4. Advancing technology for breast cancer diagnosis", - "5. Improving breast cancer detection through innovation" - ] - }, - { - "id": 109, - "slug": "hrpred", - "name": "Prediction of High Risk Patients", - "headline": "Classification of high and low risk cancer patients", - "headline_alternatives": [ - "1. Identifying High and Low Cancer Risk Patients", - "2. Classifying Cancer Patients by Risk Level ", - "3. Categorizing Cancer Risk in Patients", - "4. Assessing Cancer Patient Risk Levels", - "5. Determining High vs Low Risk Cancer Patients" - ] - }, - { - "id": 110, - "slug": "ml4moleng-cancer", - "name": "MIT ML4MolEng-Predicting Cancer Progression", - "headline": "MIT 3.100, 10.402, 20.301 In class ML competition (Spring 2021)", - "headline_alternatives": [ - "1. MIT students compete to build best ML model", - "2. MIT classes hold machine learning competition ", - "3. MIT engineering students vie in ML contest", - "4. MIT classes challenge students in ML building", - "5. ML model building contest held for MIT classes" - ] - }, - { - "id": 111, - "slug": "uw-madison-gi-tract-image-segmentation", - "name": "UW-Madison GI Tract Image Segmentation", - "headline": "Track healthy organs in medical scans to improve cancer treatment", - "headline_alternatives": [ - "1. Scans Track Healthy Organs to Boost Cancer Care", - "2. Tracking Organs in Scans Advances Cancer Treatment ", - "3. Organ Tracking in Scans Improves Cancer Therapies", - "4. Healthy Organ Scans to Enhance Cancer Treatment", - "5. Scanning Organs Helps Improve Cancer Treatments" - ] - }, - { - "id": 112, - "slug": "rsna-miccai-brain-tumor-radiogenomic-classification", - "name": "RSNA-MICCAI Brain Tumor Radiogenomic Classification", - "headline": "Predict the status of a genetic biomarker important for brain cancer treatment", - "headline_alternatives": [ - "1. BraTS challenge evaluates brain tumor segmentation methods", - "2. BraTS evaluates glioblastoma segmentation and MGMT classification ", - "3. BraTS challenge tests brain tumor segmentation and methylation prediction", - "4. BraTS challenge focuses on glioblastoma segmentation and classification", - "5. BraTS celebrates 10 years evaluating brain tumor analysis methods" - ] - }, - { - "id": 113, - "slug": "breastcancer", - "name": "Breast Cancer - Beginners ML", - "headline": "Beginners hands-on experience with ML basics", - "headline_alternatives": [ - "1. Gaining Hands-On ML Basics For Newcomers", - "2. Beginners Get Hands-On With Machine Learning Fundamentals ", - "3. Hands-On Intro To ML Essentials For Novices", - "4. Starter's Hands-On Primer For ML Core Principles", - "5. Newbies Tackle Hands-On Machine Learning Groundwork" - ] - }, - { - "id": 114, - "slug": "ml-olympiad-health-and-education", - "name": "ML Olympiad -Let's Fight lung cancer", - "headline": "Use your ML expertise to help us step another step toward defeating cancer [...", - "headline_alternatives": [ - "1. Join the fight, help defeat cancer through ML", - "2. ML experts unite to advance cancer research ", - "3. Calling all ML experts - let's beat cancer together", - "4. ML community rallies to find cancer breakthroughs", - "5. ML challenge takes on cancer - starts February 14th" - ] - }, - { - "id": 115, - "slug": "cs98-22-dl-task1", - "name": "CS98X-22-DL-Task1", - "headline": "This competition is related to Task 1 in coursework-breast cancer classification", - "headline_alternatives": [ - "1. Classifying Breast Cancer Tumors via Machine Learning", - "2. Applying AI to Diagnose Breast Cancer from Images ", - "3. Using Deep Learning for Breast Cancer Detection", - "4. Automated Breast Cancer Classification with Neural Nets", - "5. Machine Learning Model for Breast Cancer Diagnosis" - ] - }, - { - "id": 116, - "slug": "parasitedetection-iiitb2019", - "name": "Parasite detection", - "headline": "detect if cell image has parasite or is uninfected", - "headline_alternatives": [] - }, - { - "id": 117, - "slug": "hpa-single-cell-image-classification", - "name": "Human Protein Atlas -Single Cell Classification", - "headline": "Find individual human cell differences in microscope images", - "headline_alternatives": [] - }, - { - "id": 118, - "slug": "stem-cell-predcition", - "name": "Stem Cell Predcition", - "headline": "Classify stem and non-stem cells using RNA-seq data", - "headline_alternatives": [] - }, - { - "id": 119, - "slug": "sartorius-cell-instance-segmentation", - "name": "Sartorius - Cell Instance Segmentation", - "headline": "Detect single neuronal cells in microscopy images", - "headline_alternatives": [ - "1. Segment neuronal cells in microscopy images to aid neuroresearch", - "2. Delineate distinct neuronal cells to quantify effects of disease ", - "3. Detect and segment neuronal cells to enable neurobiology research", - "4. Identify neuronal cells in images to advance neurological disorder research", - "5. Segment microscopy images of neuronal cells to further neurobiology" - ] - }, - { - "id": 120, - "slug": "pvelad", - "name": "Photovoltaic cell anomaly detection", - "headline": "Hosted by Hebei University of Technology (AIHebut research group) and Beihan...", - "headline_alternatives": [ - "1. Hebei and Beihang Universities Host AI Challenge", - "2. Hebut and NAVE Research Groups Hold Joint AI Contest ", - "3. AIHebut and NAVE Teams Compete in AI Challenge", - "4. Joint AI Challenge Hosted by Hebei and Beihang Universities", - "5. Hebei and Beihang University Groups Host AI Competition" - ] - }, - { - "id": 121, - "slug": "blood-mnist", - "name": "Blood-MNIST", - "headline": "Classifying blood cell types using Weights and Biases", - "headline_alternatives": [ - "1. Challenge: Categorize Blood Cells with Weights and Biases", - "2. Competition: Classify Blood Cells using Weights and Biases ", - "3. Contest: Identify Blood Cell Types via Weights and Biases", - "4. Challenge: Label Blood Cell Categories using Weights and Biases", - "5. Competition: Categorize Blood Cells through Weights and Biases" - ] - }, - { - "id": 122, - "slug": "insilicomolhack", - "name": "MolHack", - "headline": "Apply deep learning to speedup drug validation", - "headline_alternatives": [] - }, - { - "id": 123, - "slug": "codata2019challenge", - "name": "Cell Response Classification", - "headline": "From recorded timeseries of many cells in a well, predict which drug treatme...", - "headline_alternatives": [] - }, - { - "id": 124, - "slug": "drug-solubility-challenge", - "name": "Drug solubility challenge", - "headline": "Solubility is vital to achieve desired concentration of drug for anticipated...", - "headline_alternatives": [ - "1. Improving Drug Solubility to Achieve Optimal Concentrations ", - "2. Maximizing Drug Solubility for Desired Pharmacological Response", - "3. Solubility Key to Reaching Target Drug Concentrations ", - "4. Enhancing Solubility to Attain Effective Drug Concentrations", - "5. Solubility Crucial for Ideal Drug Concentrations and Effects" - ] - }, - { - "id": 125, - "slug": "kinase-inhibition-challenge", - "name": "Kinase inhibition challenge", - "headline": "Protein kinases have become a major class of drug targets, accumulating a hu...", - "headline_alternatives": [ - "1. Developing protein kinase inhibitors as promising new drug targets", - "2. Targeting protein kinases: a major new frontier for drug discovery", - "3. Exploring the vast drug potential of the protein kinase family ", - "4. Protein kinases: a treasure trove of data for drug development", - "5. Mining protein kinase data to advance targeted drug discovery" - ] - }, - { - "id": 126, - "slug": "ai-drug-discovery", - "name": "AI Drug Discovery Workshop and Coding Challenge", - "headline": "Developing Fundamental AI Programming Skills for Drug Discovery", - "headline_alternatives": [ - "1. Learn AI Skills to Advance Drug Discovery Programs", - "2. Acquire AI Expertise for Novel Drug Development ", - "3. Master AI Programming for Pharma Research Innovation", - "4. Gain AI Proficiency to Expedite Drug Discovery ", - "5. Develop AI Talent for Faster Medication Breakthroughs" - ] - }, - { - "id": 127, - "slug": "protein-compound-affinity", - "name": "Structure-free protein-ligand affinity prediction - Task 1 Fitting", - "headline": "Developing new AI models for drug discovery, main portal (Task-1 fitting)", - "headline_alternatives": [ - "1. New AI models aim to advance drug discovery efforts ", - "2. Developing AI to fit models for improved drug discovery", - "3. AI modeling to enhance drug discovery through portal fitting", - "4. Portal fitting with AI models to further drug discovery ", - "5. AI modeling via portal for advancing drug discovery research" - ] - }, - { - "id": 128, - "slug": "cisc873-dm-f21-a5", - "name": "CISC873-DM-F21-A5", - "headline": "Anti-Cancer Drug Activity Prediction", - "headline_alternatives": [] - }, - { - "id": 129, - "slug": "pro-lig-aff-task2-mse", - "name": "Structure-free protein-ligand affinity prediction - Task 2 Fitting", - "headline": "Developing new AI models for drug discovery (Task-2 fitting)", - "headline_alternatives": [ - "1. Creating AI to fit models for drug discovery", - "2. Developing AI to fit models and enable drug discovery ", - "3. Building AI models to fit and advance drug development", - "4. New AI to fit models and boost pharmaceutical discoveries", - "5. AI models developed to fit and progress drug discovery" - ] - }, - { - "id": 130, - "slug": "pro-lig-aff-task1-pearsonr", - "name": "Structure-free protein-ligand affinity prediction - Task 1 Ranking", - "headline": "Developing new AI models for drug discovery (Task-1 ranking)", - "headline_alternatives": [ - "1. Creating AI to Rank Drug Candidates for Discovery", - "2. Building AI Models to Prioritize Drug Compounds ", - "3. Developing AI to Rank Drug Leads for Research", - "4. Designing AI to Order Drug Prospects by Potential", - "5. Making AI to Classify Drug Possibilities for Trials" - ] - }, - { - "id": 131, - "slug": "pro-lig-aff-task2-pearsonr", - "name": "Structure-free protein-ligand affinity prediction - Task 2 Ranking", - "headline": "Developing new AI models for drug discovery (Task-2 ranking)", - "headline_alternatives": [ - "1. Creating AI to Rank Drug Candidates for Discovery", - "2. Using AI to Prioritize Drug Compounds for Research ", - "3. AI Models to Improve Drug Candidate Identification", - "4. AI Systems to Enhance Drug Discovery Processes", - "5. Developing AI to Streamline Drug Development Research" - ] - }, - { - "id": 132, - "slug": "pro-lig-aff-task3-spearmanr", - "name": "Structure-free protein-ligand affinity prediction - Task 3 Ranking", - "headline": "Developing new AI models for drug discovery (Task-3 ranking)", - "headline_alternatives": [ - "1. New AI models sought for drug discovery ranking", - "2. Develop AI to rank drug candidates for discovery ", - "3. Can AI improve drug discovery through candidate ranking?", - "4. Building AI models to rank drug discovery options", - "5. AI drug discovery challenge: rank candidates by potential" - ] - }, - { - "id": 133, - "slug": "hhp", - "name": "Heritage Health Prize", - "headline": "Identify patients who will be admitted to a hospital within the next year us...", - "headline_alternatives": [ - "1. Predicting Future Hospital Admissions from Claims Data", - "2. Forecasting Hospitalizations Using Insurance Claims History ", - "3. Claims Data to Identify Future Hospital Admissions", - "4. Hospital Admissions Prediction from Historical Claims", - "5. Using Past Claims to Foresee Hospitalizations" - ] - }, - { - "id": 134, - "slug": "pf2012", - "name": "Practice Fusion Analyze This! 2012 - Prediction Challenge", - "headline": "Start digging into electronic health records and submit your ideas for the m...", - "headline_alternatives": [] - }, - { - "id": 135, - "slug": "pf2012-at", - "name": "Practice Fusion Analyze This! 2012 - Open Challenge", - "headline": "Start digging into electronic health records and submit your creative, insig...", - "headline_alternatives": [] - }, - { - "id": 136, - "slug": "seizure-detection", - "name": "UPenn and Mayo Clinic's Seizure Detection Challenge", - "headline": "Detect seizures in intracranial EEG recordings", - "headline_alternatives": [ - "1. New contest to detect seizures from brain recordings", - "2. Competition to identify seizures in intracranial EEG ", - "3. Can you detect seizures in intracranial EEG data?", - "4. Help identify seizures from intracranial EEG signals", - "5. Seizure detection challenge using intracranial EEG" - ] - }, - { - "id": 137, - "slug": "seizure-prediction", - "name": "American Epilepsy Society Seizure Prediction Challenge", - "headline": "Predict seizures in intracranial EEG recordings", - "headline_alternatives": [] - }, - { - "id": 138, - "slug": "deephealth-1", - "name": "Deep Health - alcohol", - "headline": "Find Correlations and patterns with Medical data", - "headline_alternatives": [ - "1. Discover Medical Insights Through Data Correlations ", - "2. Uncovering Patterns in Medical Data to Advance Healthcare", - "3. Analyzing Medical Data to Reveal Important Health Connections", - "4. Medical Data Analysis Seeks to Find Key Correlations and Patterns", - "5. Can Medical Data Analysis Yield New Health Insights and Links?" - ] - }, - { - "id": 139, - "slug": "deep-health-3", - "name": "Deep Health - Diabetes 2", - "headline": "This competition is for those attending the Deep Health Hackathon. Predic...", - "headline_alternatives": [ - "1. Predicting diabetes at health hackathon", - "2. Forecasting diabetes for hackathon attendees ", - "3. Deep Health Hackathon: Predict diabetes", - "4. Diabetes prediction challenge at hackathon", - "5. Hackathon attendees compete to predict diabetes" - ] - }, - { - "id": 140, - "slug": "d012554-2021", - "name": "D012554 - 2021", - "headline": "Classify the health of a fetus using CTG data", - "headline_alternatives": [ - "1. Classifying Fetal Health from Cardiotocography Data", - "2. Predicting Fetus Condition with CTG Readings ", - "3. Assessing Fetal Wellbeing via Monitoring Signals", - "4. Determining Fetal Status Through Uterine Data ", - "5. Categorizing Fetal Health Using CTG Measurements" - ] - }, - { - "id": 141, - "slug": "idao-2022-bootcamp-insomnia", - "name": "IDAO 2022. ML Bootcamp - Insomnia", - "headline": "Predict sleep disorder on given human health data", - "headline_alternatives": [ - "1. Forecasting Sleep Issues Using Patient Information", - "2. Anticipating Sleep Disturbances From Health Records ", - "3. Predicting Sleep Disorders From Human Health Data", - "4. Estimating Sleep Problems With Medical Histories", - "5. Projecting Sleep Anomalies Based On Health Profiles" - ] - }, - { - "id": 142, - "slug": "tweet-mental-health-classification", - "name": "Tweet Mental Health Classification", - "headline": "Build Models to classify tweets to determine mental health", - "headline_alternatives": [ - "1. Classify Tweets to Detect Mental Health Signals", - "2. Build Models to Categorize Tweets by Mental State ", - "3. Use Twitter Data to Assess Mental Health Status", - "4. Develop Algorithms to Analyze Tweets for Mental Health", - "5. Create Systems to Classify Tweets for Mental Wellbeing" - ] - }, - { - "id": 143, - "slug": "ml-olympiad-good-health-and-well-being", - "name": "ML Olympiad - GOOD HEALTH AND WELL BEING", - "headline": "Use your ML expertise to classify if a patient has heart disease or not", - "headline_alternatives": [ - "1. ML to Diagnose Heart Disease from Patient Data ", - "2. Applying ML to Classify Heart Disease Risk", - "3. ML Model Predicts Heart Disease in Patients", - "4. ML Classification of Heart Disease from Health Data", - "5. ML Algorithm Detects Heart Disease from Inputs" - ] - }, - { - "id": 144, - "slug": "rsna-breast-cancer-detection", - "name": "RSNA Screening Mammography Breast Cancer Detection", - "headline": "Find breast cancers in screening mammograms", - "headline_alternatives": [] - }, - { - "id": 145, - "slug": "biocreative-vii-text-mining-drug-and-chemical-protein-interactions-drugprot", - "name": "BioCreative VII: Text mining drug and chemical-protein interactions (DrugProt)", - "headline": "", - "headline_alternatives": [ - "1. Develop systems to extract drug-gene relations from text", - "2. Automate extraction of drug-protein interactions from literature ", - "3. Detect relationships between drugs and genes/proteins in text", - "4. Promote systems that identify drug-gene/protein relations", - "5. Evaluate systems that extract drug-protein relations in text" - ] - }, - { - "id": 146, - "slug": "extended-literature-ai-for-drug-induced-liver-injury", - "name": "Extended Literature AI for Drug Induced Liver Injury", - "headline": "", - "headline_alternatives": [ - "1. Develop ML tools to analyze drug texts for liver injury data", - "2. Extract drug toxicity knowledge from free text publications ", - "3. Apply NLP to improve analysis of drug-induced liver injury data", - "4. Create automated ways to process drug texts for liver safety", - "5. Use AI to better understand drug-induced liver injury from texts" - ] - }, - { - "id": 147, - "slug": "anti-microbial-resistance-forensics", - "name": "Anti-Microbial Resistance Forensics", - "headline": "", - "headline_alternatives": [ - "1. Classifying Bacteriophages to Understand Microbial Evolution", - "2. Analyzing Phages to Combat Antimicrobial Resistance ", - "3. Harnessing Phages: Curing Infections Without Antibiotics", - "4. Phage Genomics: Tracing AMR Gene Transfer and Evolution", - "5. Improved Algorithms to Describe Diverse Phage Capabilities" - ] - }, - { - "id": 148, - "slug": "disease-maps-to-modelling-covid-19", - "name": "Disease Maps to Modelling COVID-19", - "headline": "Use the COVID-19 disease map to suggest drugs candidate for repurposing, tha...", - "headline_alternatives": [ - "1. Modeling COVID-19 infection to find drug repurposing candidates", - "2. COVID-19 challenge seeks drug repurposing through disease modeling ", - "3. COVID-19 challenge: model infection, find drug repurposing options", - "4. Modeling COVID-19 mechanisms to enable drug repurposing", - "5. COVID-19 challenge: model disease, repurpose drugs, validate with data" - ] - }, - { - "id": 149, - "slug": "crowdsourced-evaluation-of-inchi-based-tautomer-identification", - "name": "Crowdsourced Evaluation of InChI-based Tautomer Identification", - "headline": "Calling on scientists from industry, government, and academia dealing with c...", - "headline_alternatives": [] - }, - { - "id": 150, - "slug": "nctr-indel-calling-from-oncopanel-sequencing-challenge-phase-2", - "name": "NCTR Indel Calling from Oncopanel Sequencing Challenge Phase 2", - "headline": "In Phase 2, participants who completed in Phase 1 of the challenge have the ...", - "headline_alternatives": [ - "1. Develop standards for oncopanel sequencing quality control", - "2. Create reference sample to benchmark oncopanel performance ", - "3. Assess analytical performance of oncopanels for precision oncology", - "4. Establish quality metrics for clinical oncopanel sequencing ", - "5. Improve regulation of oncopanel sequencing through FDA project" - ] - }, - { - "id": 151, - "slug": "nctr-indel-calling-from-oncopanel-sequencing-data-challenge-phase-1", - "name": "NCTR Indel Calling from Oncopanel Sequencing Data Challenge Phase 1", - "headline": "Genetic variation involving indels (insertions and deletions) in the cancer ...", - "headline_alternatives": [ - "1. Develop standards for oncopanel sequencing quality control", - "2. Benchmark oncopanels with reference sample from FDA-led project ", - "3. Assess analytical performance of oncopanels using genomic reference", - "4. Establish quality metrics for clinical oncopanel sequencing ", - "5. Create protocols for fit-for-purpose next-gen sequencing data use" - ] - }, - { - "id": 152, - "slug": "vha-innovation-ecosystem-and-precisionfda-covid-19-risk-factor-modeling-challenge-phase-2", - "name": "VHA Innovation Ecosystem and precisionFDA COVID-19 Risk Factor Modeling Challenge Phase 2", - "headline": "The focus of Phase 2 was to validate the top performing models on two additi...", - "headline_alternatives": [] - }, - { - "id": 153, - "slug": "tumor-mutational-burden-tmb-challenge-phase-2", - "name": "Tumor Mutational Burden (TMB) Challenge Phase 2", - "headline": "The goal of the Friends of Cancer Research and precisionFDA Tumor Mutational...", - "headline_alternatives": [] - }, - { - "id": 154, - "slug": "predicting-gene-expression-using-millions-of-random-promoter-sequences", - "name": "Predicting Gene Expression Using Millions of Random Promoter Sequences", - "headline": "", - "headline_alternatives": [ - "1. Decoding gene expression regulation to understand disease", - "2. Modeling complex cis-regulatory logic of the human genome ", - "3. Learning models of human regulatory DNA function", - "4. Understanding cis-regulatory logic of disease origins", - "5. Decoding transcriptional regulation in human genome" - ] - }, - { - "id": 155, - "slug": "brats-2023", - "name": "BraTS 2023", - "headline": "", - "headline_alternatives": [ - "1. Benchmarking brain tumor segmentation with expanded dataset", - "2. Segmenting adult and pediatric brain tumors across populations ", - "3. Delineating gliomas and meningiomas in diverse patient groups", - "4. Segmenting brain tumors despite missing clinical data", - "5. BraTS challenge tests brain tumor segmentation methods" - ] - }, - { - "id": 156, - "slug": "cagi7", - "name": "CAGI7", - "headline": "The seventh round of CAGI", - "headline_alternatives": [ - "1. Seventh round of CAGI experiments planned for 2024", - "2. CAGI to hold seventh edition of prediction challenges in 2024 ", - "3. CAGI announces plans for seventh round of experiments in 2024", - "4. Seventh CAGI challenge focused on predictive modeling set for 2024", - "5. CAGI organizing seventh round of predictive modeling experiments for 2024" - ] - }, - { - "id": 157, - "slug": "casp15", - "name": "CASP15", - "headline": "Establish the state-of-art in modeling proteins and protein complexes", - "headline_alternatives": [ - "1. CASP15 Adapts to Advancements in Deep Learning Protein Modeling", - "2. CASP15 Strengthens Focus on Novel Protein Structure Applications ", - "3. CASP15 Evolves Categories to Maximize Deep Learning Insights", - "4. CASP15 Shifts to Emerging Areas Like RNA and Protein Complexes", - "5. CASP15 Partners with CAPRI, CAMEO to Apply New Protein Models" - ] - }, - { - "id": 158, - "slug": "synthrad2023", - "name": "SynthRAD2023", - "headline": "Synthesizing computed tomography for radiotherapy", - "headline_alternatives": [ - "1. Platform Compares sCT Generation Methods", - "2. First Public Benchmark for sCT Algorithms ", - "3. New Platform Evaluates sCT Generation Methods", - "4. Challenge Compares sCT Generation Algorithms", - "5. Public Platform to Evaluate sCT Methods" - ] - }, - { - "id": 159, - "slug": "synthetic-data-for-instrument-segmentation-in-surgery-syn-iss", - "name": "Synthetic Data for Instrument Segmentation in Surgery (Syn-ISS)", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 160, - "slug": "pitvis", - "name": "PitVis", - "headline": "Surgical workflow and instrument recognition in endonasal surgery", - "headline_alternatives": [ - "1. Computer guidance aims to improve pituitary tumor removal ", - "2. Technology assists surgeons removing pituitary growths", - "3. Systems guide surgeons extracting pituitary gland tumors ", - "4. Assisted intervention targets enhanced pituitary surgery", - "5. Computer assistance for precise pituitary tumor extraction" - ] - }, - { - "id": 161, - "slug": "mvseg2023", - "name": "MVSEG2023", - "headline": "Automatically segment mitral valve leaflets from single frame 3D trans-esoph...", - "headline_alternatives": [ - "1. Segment mitral valve from 3D echocardiography for treatment planning ", - "2. Personalize mitral valve repair with automatic leaflet segmentation", - "3. Improve outcomes in mitral repair with patient-specific 3D modeling", - "4. Tailor mitral valve surgery using automated 3D leaflet segmentation ", - "5. Segment mitral valve leaflets from 3D ultrasound for personalized care" - ] - }, - { - "id": 162, - "slug": "crossmoda23", - "name": "crossMoDA23", - "headline": "This challenge proposes is the third edition of the first medical imaging be...", - "headline_alternatives": [ - "1. Challenge tests unsupervised domain adaptation for MRI tumor segmentation ", - "2. Multi-class dataset benchmarks domain adaptation in medical imaging", - "3. First large dataset evaluates domain adaptation techniques for MRI", - "4. Challenge evaluates robustness of ML approaches across medical domains", - "5. Dataset tests domain adaptation for multi-class MRI segmentation task" - ] - }, - { - "id": 163, - "slug": "icr-identify-age-related-conditions", - "name": "ICR - Identifying Age-Related Conditions", - "headline": "Use Machine Learning to detect conditions with measurements of anonymous cha...", - "headline_alternatives": [ - "1. Predict medical conditions from health measurements", - "2. Classify patients by presence of three conditions ", - "3. Model predicts medical conditions from characteristics", - "4. Determine conditions from encoded health characteristics", - "5. Shorten diagnosis using predictive model on measurements" - ] - }, - { - "id": 164, - "slug": "cafa-5-protein-function-prediction", - "name": "CAFA 5: Protein Function Prediction", - "headline": "Predict the biological function of a protein", - "headline_alternatives": [] - }, - { - "id": 165, - "slug": "rsna-2023-abdominal-trauma-detection", - "name": "RSNA 2023 Abdominal Trauma Detection", - "headline": "Detect and classify traumatic abdominal injuries", - "headline_alternatives": [ - "1. AI to Assist Rapid Diagnosis of Abdominal Trauma from CT Scans", - "2. Machine Learning for Detecting and Grading Abdominal Injuries in CT", - "3. Automated Detection and Severity Grading of Abdominal Trauma by AI ", - "4. Rapid AI Diagnosis of Abdominal Injuries from CT Scans ", - "5. AI to Improve Outcomes in Abdominal Trauma Patients" - ] - }, - { - "id": 166, - "slug": "hubmap-hacking-the-human-vasculature", - "name": "HuBMAP: Hacking the Human Vasculature", - "headline": "Segment instances of microvascular structures from healthy human kidney tiss...", - "headline_alternatives": [ - "1. Model segments microvasculature in kidney histology images", - "2. Automate segmentation of capillaries, arterioles, venules ", - "3. Improve understanding of microvascular structures in tissues", - "4. Segment microvascular structures like capillaries in images", - "5. Create model to identify blood vessels in kidney slides" - ] - }, - { - "id": 167, - "slug": "amp-parkinsons-disease-progression-prediction", - "name": "AMP(R)-Parkinson's Disease Progression Prediction", - "headline": "Use protein and peptide data measurements from Parkinson's Disease patients ...", - "headline_alternatives": [ - "1. Predicting Parkinson's progression with MDS-UPDRS scores", - "2. Model to forecast Parkinson's severity via MDS-UPDRS", - "3. Develop model for Parkinson's progression using MDS-UPDRS", - "4. Predict MDS-UPDRS scores to track Parkinson's disease ", - "5. Use MDS-UPDRS to model Parkinson's disease progression" - ] - }, - { - "id": 168, - "slug": "open-problems-multimodal", - "name": "Open Problems -Multimodal Single-Cell Integration", - "headline": "Predict how DNA, RNA & protein measurements co-vary in single cells", - "headline_alternatives": [ - "1. Predict how DNA, RNA, protein relate in blood cell development", - "2. Model how stem cells mature into blood cells using omics data ", - "3. Map genetic data across cell states with time-series data", - "4. Relate DNA, RNA, protein in hematopoietic stem cell differentiation", - "5. Predict modalities from unseen timepoints in blood cell development" - ] - }, - { - "id": 169, - "slug": "multi-atlas-labeling-beyond-the-cranial-vault", - "name": "Multi-Atlas Labeling Beyond the Cranial Vault", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 170, - "slug": "hubmap-organ-segmentation", - "name": "HuBMAP + HPA: Hacking the Human Body", - "headline": "Segment multi-organ functional tissue units", - "headline_alternatives": [ - "1. Segment functional tissue units in human organs", - "2. Identify and segment tissue units across organs ", - "3. Build models to accurately segment functional tissue units", - "4. Accelerate understanding cell organization in tissues", - "5. Freely provide human tissue atlas to improve health " - ] - }, - { - "id": 171, - "slug": "hubmap-kidney-segmentation", - "name": "HuBMAP: Hacking the Kidney", - "headline": "Identify glomeruli in human kidney tissue images", - "headline_alternatives": [ - "1. Detect functional tissue units in human kidney maps ", - "2. Identify glomeruli in kidney images for HuBMAP", - "3. Map human kidney at single cell level to find tissue units", - "4. Develop tools to detect functional units in kidney images", - "5. Identify cell relationships in kidney to understand health" - ] - }, - { - "id": 172, - "slug": "ventilator-pressure-prediction", - "name": "Google Brain: Ventilator Pressure Prediction", - "headline": "Simulate a ventilator connected to a sedated patient's lung", - "headline_alternatives": [ - "1. Simulating ventilator-lung interactions to improve treatments", - "2. Developing affordable ventilator control methods to help patients", - "3. Simulating ventilator-lung dynamics for better patient care ", - "4. Overcoming cost barriers in ventilator control for wider access", - "5. Modeling ventilator-lung systems to adapt treatments to patients" - ] - }, - { - "id": 173, - "slug": "stanford-covid-vaccine", - "name": "OpenVaccine - COVID-19 mRNA Vaccine Degradation Prediction", - "headline": "Urgent need to bring the COVID-19 vaccine to mass production", - "headline_alternatives": [ - "1. Predict RNA degradation rates to aid vaccine design", - "2. Modeling RNA degradation for COVID vaccine mRNA ", - "3. Forecasting RNA decay to optimize mRNA vaccines", - "4. Estimating position-specific RNA degradation rates ", - "5. Data science for modeling RNA degradation rates" - ] - }, - { - "id": 174, - "slug": "openvaccine", - "name": "OpenVaccine", - "headline": "To develop mRNA vaccines stable enough to be deployed to everyone in the wor...", - "headline_alternatives": [ - "1. Crowdsource mRNA vaccine design for enhanced stability", - "2. Improve refrigerator stability of mRNA vaccines", - "3. Develop mRNA vaccine 2-10x more stable than COVID shots ", - "4. Machine learning to optimize mRNA vaccine formulation ", - "5. Transform mRNA vaccine viability via community game design" - ] - }, - { - "id": 175, - "slug": "opentb", - "name": "OpenTB", - "headline": "What if we could use RNA to detect a gene sequence found to be present only ...", - "headline_alternatives": [ - "1. Designing RNA sensors to detect TB gene signature", - "2. Players create RNA sensors to calculate TB gene levels ", - "3. Developing RNA-based sensors to detect active TB", - "4. Creating RNA sensors to detect 3 genes for TB test", - "5. Using RNA designs to build TB diagnostic devices" - ] - }, - { - "id": 176, - "slug": "opencrispr", - "name": "OpenCRISPR", - "headline": "A project to discover design patterns for guide RNAs to make gene editing mo...", - "headline_alternatives": [ - "1. CRISPR gene editing targeted to control diseases", - "2. Developing safe, small molecule switches for CRISPR", - "3. Controlling CRISPR with RNA hairpins and small molecules ", - "4. Tackling diseases with safe, controllable CRISPR editing", - "5. Unlocking CRISPR's potential with molecular on/off switches" - ] - }, - { - "id": 177, - "slug": "openknot", - "name": "OpenKnot", - "headline": "Many important biological processes depend on RNAs that form pseudoknots, an...", - "headline_alternatives": [ - "1. Understanding RNA pseudoknot folding pathways", - "2. Elucidating pseudoknot roles in gene regulation ", - "3. Modeling pseudoknot structures in viral replication", - "4. Analyzing pseudoknot enzymatic activity ", - "5. Exploring pseudoknot biological functions" - ] - }, - { - "id": 178, - "slug": "openaso", - "name": "OpenASO", - "headline": "A research initiative aimed at developing innovative design principles for R...", - "headline_alternatives": [ - "1. Decoding DNA into functional RNA via splicing", - "2. Understanding RNA splicing for protein production ", - "3. Investigating intron removal in mRNA maturation", - "4. Analyzing corrupted RNA splicing in human disease", - "5. Mapping DNA transcription and mRNA maturation" - ] - }, - { - "id": 179, - "slug": "openribosome", - "name": "OpenRibosome", - "headline": "We aim to 1) gain fundamental insights into the ribosome's RNA sequence-fold...", - "headline_alternatives": [] - }, - { - "id": 180, - "slug": "lish-moa", - "name": "Mechanisms of Action (MoA) Prediction", - "headline": "Can you improve the algorithm that classifies drugs based on their biologica...", - "headline_alternatives": [] - }, - { - "id": 181, - "slug": "recursion-cellular-image-classification", - "name": "Recursion Cellular Image Classification", - "headline": "CellSignal-Disentangling biological signal from experimental noise in cellul...", - "headline_alternatives": [ - "1. Classify cell images by genetic perturbation", - "2. Reduce noise in cellular image classification ", - "3. Model cell images by biology not noise", - "4. Improve industry modeling of cellular images", - "5. Decrease treatment costs through cellular image AI" - ] - }, - { - "id": 182, - "slug": "tlvmc-parkinsons-freezing-gait-prediction", - "name": "Parkinson's Freezing of Gait Prediction", - "headline": "Event detection from wearable sensor data", - "headline_alternatives": [ - "1. Detect freezing of gait in Parkinson's patients", - "2. Machine learning to detect freezing episodes in Parkinson's ", - "3. Wearable sensor data to understand freezing of gait", - "4. Improve detection of debilitating freezing in Parkinson's", - "5. Predict and prevent freezing of gait in Parkinson's" - ] - }, - { - "id": 183, - "slug": "chaimeleon", - "name": "CHAIMELEON Open Challenges", - "headline": "", - "headline_alternatives": [ - "1. AI competition seeks cancer diagnosis and treatment solutions", - "2. Developing innovative AI for cancer management and outcomes ", - "3. Advancing cancer research with AI prediction models", - "4. Training AI to answer clinical questions for 5 cancers", - "5. Showcasing AI solutions to improve cancer diagnosis and care" - ] - }, - { - "id": 184, - "slug": "topcow23", - "name": "Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA", - "headline": "", - "headline_alternatives": [ - "1. Segmenting Cerebral Arteries from 3D Angiography Images", - "2. Extracting Circle of Willis Structure from Angiography Data ", - "3. Annotating Vessels in Brain Angiography Scans", - "4. CoW Vessel Segmentation from CTA and MRA Images", - "5. Separating Artery Components in Cerebral Angiograms" - ] - }, - { - "id": 185, - "slug": "circle-of-willis-intracranial-artery-classification-and-quantification-challenge-2023", - "name": "Circle of Willis Intracranial Artery Classification and Quantification Challenge 2023", - "headline": "", - "headline_alternatives": [ - "1. Challenge compares circle of Willis classification methods", - "2. Circle of Willis configuration classification challenge", - "3. Comparing methods for classifying circle of Willis anatomy ", - "4. Challenge to quantify circle of Willis artery diameters", - "5. Circle of Willis anatomy quantification challenge" - ] - }, - { - "id": 186, - "slug": "making-sense-of-electronic-health-record-ehr-race-and-ethnicity-data", - "name": "Making Sense of Electronic Health Record (EHR) Race and Ethnicity Data", - "headline": "The US Food and Drug Administration (FDA) calls on stakeholders, including t...", - "headline_alternatives": [] - }, - { - "id": 187, - "slug": "the-veterans-cardiac-health-and-ai-model-predictions-v-champs", - "name": "The Veterans Cardiac Health and AI Model Predictions (V-CHAMPS)", - "headline": "The Veterans Health Administration Innovation Ecosystem, the Digital Health ...", - "headline_alternatives": [ - "1. Develop AI models predicting heart health in synthetic Veteran records ", - "2. Create ML models for cardiovascular outcomes using fake Veteran data", - "3. Build AI to forecast heart disease risk with simulated Veteran data ", - "4. Synthesize Veteran records to train AI predicting heart issues", - "5. Use artificial data to create ML models for Veteran heart health" - ] - }, - { - "id": 188, - "slug": "predicting-high-risk-breast-cancer-phase-1", - "name": "Predicting High Risk Breast Cancer - Phase 1", - "headline": "Predicting High Risk Breast Cancer-a Nightingale OS & AHLI data challenge", - "headline_alternatives": [ - "1. Mammogram mystery: Why more cancers, not fewer deaths?", - "2. Solving the disturbing disconnect in breast cancer diagnoses ", - "3. Reducing unnecessary breast cancer surgeries and chemo", - "4. Identifying truly dangerous breast cancers to spare women", - "5. Algorithms to predict harmful cancers from biopsy images" - ] - }, - { - "id": 189, - "slug": "predicting-high-risk-breast-cancer-phase-2", - "name": "Predicting High Risk Breast Cancer - Phase 2", - "headline": "Predicting High Risk Breast Cancer-a Nightingale OS & AHLI data challenge", - "headline_alternatives": [ - "1. Seeking to improve breast cancer diagnosis with AI", - "2. Reducing unnecessary breast cancer surgeries with algorithms ", - "3. Using AI to distinguish harmless from harmful breast tumors", - "4. Algorithms to identify truly dangerous breast cancers ", - "5. Can AI spot deadly breast cancers more accurately?" - ] - }, - { - "id": 190, - "slug": "dream-2-in-silico-network-inference", - "name": "DREAM 2 - In Silico Network Inference", - "headline": "Predicting the connectivity and properties of in-silico networks.", - "headline_alternatives": [ - "1. Predict connectivity of simulated biological networks", - "2. Uncover properties of in-silico network dynamics ", - "3. Reveal connections in computational biology models", - "4. Decipher interactions in simulated network systems", - "5. Analyze artificial networks to infer biology" - ] - }, - { - "id": 191, - "slug": "dream-3-in-silico-network-challenge", - "name": "DREAM 3 - In Silico Network Challenge", - "headline": "The goal of the in silico challenges is the reverse engineering of gene netw...", - "headline_alternatives": [ - "1. Reverse engineer gene networks from data", - "2. Predict network topology from gene datasets ", - "3. Reconstruct networks from steady state and time series data", - "4. Infer directed unsigned networks from gene expression", - "5. Uncover gene regulatory networks from simulations" - ] - }, - { - "id": 192, - "slug": "dream-4-in-silico-network-challenge", - "name": "DREAM 4 - In Silico Network Challenge", - "headline": "The goal of the in silico network challenge is to reverse engineer gene regu...", - "headline_alternatives": [ - "1. Reverse engineer gene networks from simulated data", - "2. Infer gene regulation networks from simulated datasets ", - "3. Uncover network structure from simulated gene data", - "4. Reconstruct gene networks using steady-state and time-series data", - "5. Predict network responses to new perturbations from simulated data" - ] - }, - { - "id": 193, - "slug": "dream-5-network-inference-challenge", - "name": "DREAM 5 - Network Inference Challenge", - "headline": "The goal of this Network Inference Challenge is to reverse engineer gene reg...", - "headline_alternatives": [ - "1. Reverse engineer gene networks from arrays", - "2. Infer regulatory networks from gene datasets ", - "3. Challenge to infer networks from microarrays", - "4. Reconstruct networks from microbe gene data", - "5. Infer structure of gene networks from arrays" - ] - }, - { - "id": 194, - "slug": "nlp-sandbox-date-annotation", - "name": "NLP Sandbox Date Annotation", - "headline": "Identify dates in clinical notes.", - "headline_alternatives": [ - "1. Challenge seeks date annotator for clinical notes", - "2. Develop a date annotator for clinical notes ", - "3. Annotate dates in clinical notes with NLP ", - "4. Extract dates from clinical notes using NLP", - "5. Apply NLP to identify dates in clinical notes" - ] - }, - { - "id": 195, - "slug": "nlp-sandbox-person-name-annotation", - "name": "NLP Sandbox Person Name Annotation", - "headline": "Identify person names in clinical notes.", - "headline_alternatives": [ - "1. Challenge Seeks Annotator to Find Names in Clinical Notes", - "2. Develop Annotator to Identify Person Names from Clinical Text ", - "3. Build System to Extract Person Names from Clinical Documents", - "4. Create Annotator to Detect Person Names in Clinical Notes", - "5. Challenge to Build Person Name Annotator for Clinical Text" - ] - }, - { - "id": 196, - "slug": "nlp-sandbox-location-annotation", - "name": "NLP Sandbox Location Annotation", - "headline": "Identify location information in clinical notes.", - "headline_alternatives": [ - "1. Predict locations in clinical notes", - "2. Annotate locations in clinical notes ", - "3. Find locations mentioned in clinical notes", - "4. Identify location annotations in notes", - "5. Locate annotations in clinical notes" - ] - }, - { - "id": 197, - "slug": "nlp-sandbox-contact-annotation", - "name": "NLP Sandbox Contact Annotation", - "headline": "Identify contact information in clinical notes.", - "headline_alternatives": [ - "1. Develop contact annotator for clinical notes", - "2. Annotate contacts in clinical notes with NLP ", - "3. Predict contact annotations in clinical notes", - "4. Identify contacts in clinical notes using NLP", - "5. Apply NLP to extract contacts from notes" - ] - }, - { - "id": 198, - "slug": "nlp-sandbox-id-annotation", - "name": "NLP Sandbox ID Annotation", - "headline": "Identify identifiers in clinical notes.", - "headline_alternatives": [ - "1. Predict patient IDs in clinical notes", - "2. Annotate clinical notes with patient IDs ", - "3. Identify patient IDs in clinical records", - "4. Extract patient identifiers from notes", - "5. Find patient IDs in doctor's notes" - ] - }, - { - "id": 199, - "slug": "dream-2-bcl6-transcriptomic-target-prediction", - "name": "DREAM 2 - BCL6 Transcriptomic Target Prediction", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 200, - "slug": "dream-2-protein-protein-interaction-network-inference", - "name": "DREAM 2 - Protein-Protein Interaction Network Inference", - "headline": "Predict a PPI network of 47 proteins", - "headline_alternatives": [ - "1. Discover new yeast protein interactions using high-throughput methods", - "2. Identify novel yeast protein-protein interactions with repeated experiments ", - "3. Find unknown yeast gene interactions using stringent yeast two-hybrid assays", - "4. Determine yeast protein pairs that interact in multiple tests but not known before ", - "5. Categorize untested yeast gene pairs as interacting or not via experiments" - ] - }, - { - "id": 201, - "slug": "dream-2-genome-scale-network-inference", - "name": "DREAM 2 - Genome-Scale Network Inference", - "headline": "", - "headline_alternatives": [ - "1. Reconstruct genome network from microarray data", - "2. Infer transcriptional network from microarray data ", - "3. Build genome-scale network using microarray data", - "4. Reconstruct transcriptional network using microarrays", - "5. Infer TF-target interactions from microarray data" - ] - }, - { - "id": 202, - "slug": "dream-2-synthetic-five-gene-network-inference", - "name": "DREAM 2 - Synthetic Five-Gene Network Inference", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 203, - "slug": "dream-3-signaling-cascade-identification", - "name": "DREAM 3 - Signaling Cascade Identification", - "headline": "", - "headline_alternatives": [ - "1. Inferring signaling cascade dynamics from flow cytometry data", - "2. Extracting topology of signaling interactions from sparse data ", - "3. Exploring signaling cascade inference from incomplete measurements", - "4. Analyzing signaling cascade dynamics with limited flow data", - "5. Reconstructing signaling pathways from partial flow cytometry" - ] - }, - { - "id": 204, - "slug": "dream-3-gene-expression-prediction", - "name": "DREAM 3 - Gene Expression Prediction", - "headline": "", - "headline_alternatives": [ - "1. Predict gene expression rank in yeast strain", - "2. Order yeast gene expression changes ", - "3. Rank yeast gene repression after perturbation", - "4. Predict relative yeast gene induction ", - "5. Order yeast gene expression with partial data" - ] - }, - { - "id": 205, - "slug": "dream-4-predictive-signaling-network-modelling", - "name": "DREAM 4 - Predictive Signaling Network Modelling", - "headline": "Cell-type specific high-throughput experimental data", - "headline_alternatives": [ - "1. Create cell-specific signaling model for HepG2 using pathways and data", - "2. Build interpretable HepG2 signaling network consistent with data ", - "3. Develop HepG2 signaling model from pathways and high-throughput data", - "4. Infer HepG2-specific signaling network from generic pathways and data", - "5. Construct biological HepG2 signal transduction model matching data" - ] - }, - { - "id": 206, - "slug": "dream-3-signaling-response-prediction", - "name": "DREAM 3 - Signaling Response Prediction", - "headline": "Predict missing protein concentrations from a large corpus of measurements", - "headline_alternatives": [ - "1. Analyze intracellular, extracellular response in normal, cancer cells", - "2. Compare protein, cytokine dynamics between normal, tumor liver cells ", - "3. Measure signaling responses to stimuli in normal, cancerous hepatocytes", - "4. Characterize phosphoprotein, cytokine changes in hepatocytes after stimulation", - "5. Assess signaling pathway perturbations in human liver cells by inhibitors" - ] - }, - { - "id": 207, - "slug": "dream-4-peptide-recognition-domain-prd-specificity-prediction", - "name": "DREAM 4 - Peptide Recognition Domain (PRD) Specificity Prediction", - "headline": "", - "headline_alternatives": [ - "1. Predict binding specificity of protein domains", - "2. Model peptide recognition of protein domains ", - "3. Infer interaction profiles of peptide binding domains", - "4. Compute specificity matrices for domain-peptide binding", - "5. Estimate position weight matrices for protein interactions" - ] - }, - { - "id": 208, - "slug": "dream-5-transcription-factor-dna-motif-recognition-challenge", - "name": "DREAM 5 - Transcription-Factor, DNA-Motif Recognition Challenge", - "headline": "", - "headline_alternatives": [ - "1. Predict binding intensities for transcription factors from motifs", - "2. Model transcription factor binding specificities from genomic sequences ", - "3. Infer transcription factor binding strengths from DNA motifs", - "4. Estimate transcription factor affinities using sequence motifs", - "5. Predict transcription factor binding signals from DNA sequences" - ] - }, - { - "id": 209, - "slug": "dream-5-epitope-antibody-recognition-ear-challenge", - "name": "DREAM 5 - Epitope-Antibody Recognition (EAR) Challenge", - "headline": "Predict the binding specificity of peptide-antibody interactions.", - "headline_alternatives": [] - }, - { - "id": 210, - "slug": "dream-gene-expression-prediction-challenge", - "name": "DREAM Gene Expression Prediction Challenge", - "headline": "Predict gene expression levels from promoter sequences in eukaryotes", - "headline_alternatives": [ - "1. Predict promoter activity from sequence and condition", - "2. Quantify transcription regulation in yeast gene promoters ", - "3. Model transcriptional output of yeast ribosomal promoters", - "4. Decode regulatory code in yeast ribosomal protein genes", - "5. Infer ribosomal protein promoter strengths from sequences" - ] - }, - { - "id": 211, - "slug": "dream-5-systems-genetics-challenge", - "name": "DREAM 5 - Systems Genetics Challenge", - "headline": "Predict disease phenotypes and infer Gene Networks from Systems Genetics data", - "headline_alternatives": [ - "1. Inferring causal gene networks from randomized genetic perturbations ", - "2. Elucidating predictive models of biological networks using systems genetics", - "3. Gaining system-level understanding of networks through randomized experiments", - "4. Using randomized genetics to reconstruct causal biological networks", - "5. Systems genetics data reveals causal relationships in gene networks" - ] - }, - { - "id": 212, - "slug": "dream-6-estimation-of-model-parameters-challenge", - "name": "DREAM 6 - Estimation of Model Parameters Challenge", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 213, - "slug": "dream-6-flowcap2-molecular-classification-of-acute-myeloid-leukemia-challenge", - "name": "DREAM 6 - FlowCAP2 Molecular Classification of Acute Myeloid Leukemia Challenge", - "headline": "The goal of this challenge is to diagnose Acute Myeloid Leukaemia from patie...", - "headline_alternatives": [ - "1. Automating Identification of Cell Populations in Flow Cytometry Data", - "2. Developing Reliable Tools to Interpret High-Dimensional Flow Cytometry Data ", - "3. Advancing Analysis of Complex Flow Cytometry Datasets ", - "4. Modernizing Flow Cytometry Analysis with Machine Learning", - "5. Tackling Manual Analysis Bottleneck in Flow Cytometry" - ] - }, - { - "id": 214, - "slug": "dream-6-alternative-splicing-challenge", - "name": "DREAM 6 - Alternative Splicing Challenge", - "headline": "", - "headline_alternatives": [ - "1. Assess accuracy of mRNA-seq alternative splicing reconstruction", - "2. Compare mRNA-seq methods on primate and rhino transcripts ", - "3. mRNA-seq challenge evaluates transcriptome assembly methods", - "4. mRNA-seq methods tested on primate, rhino, and stem cells", - "5. Novel biology discovery goal of mRNA-seq splicing challenge" - ] - }, - { - "id": 215, - "slug": "causalbench-challenge", - "name": "CausalBench Challenge", - "headline": "A machine learning contest for gene network inference from single-cell pertu...", - "headline_alternatives": [ - "1. Mapping gene interactions to generate drug hypotheses", - "2. Advancing networks from single-cell data for causal insights ", - "3. Deriving gene-gene networks to improve causal disease insights", - "4. Machine learning to advance gene network inference from cells", - "5. Generating gene interaction maps to target disease mechanisms" - ] - }, - { - "id": 216, - "slug": "iclr-computational-geometry-and-topology-challenge-2022", - "name": "ICLR Computational Geometry & Topology Challenge 2022", - "headline": "", - "headline_alternatives": [] - }, - { - "id": 217, - "slug": "iclr-computational-geometry-and-topology-challenge-2021", - "name": "ICLR Computational Geometry & Topology Challenge 2021", - "headline": "", - "headline_alternatives": [ - "1. Advancing computational geometry and topology with Python", - "2. Pushing differential geometry and topology forward with Python", - "3. Improving computational methods in geometry and topology ", - "4. Creating new geometric and topological data analysis with Python", - "5. Developing numerical experiments in differential geometry and topology" - ] - }, - { - "id": 218, - "slug": "genedisco-challenge", - "name": "GeneDisco Challenge", - "headline": "", - "headline_alternatives": [ - "1. Exploring experimental design with active learning for genetics", - "2. Evaluating active learning algorithms for genetic perturbation", - "3. Machine learning challenge for exploring genetic experiment design", - "4. Community challenge to optimize active learning in gene experiments ", - "5. Assessing batch active learning in vast genetic perturbation space" - ] - }, - { - "id": 219, - "slug": "hidden-treasures-warm-up", - "name": "Hidden Treasures: Warm Up", - "headline": "", - "headline_alternatives": [ - "1. Assess genome sequencing software accuracy with unknown variants", - "2. Benchmark genome sequencing pipelines with in silico variants ", - "3. Test exome sequencing pipelines with injected variants", - "4. Prepare for upcoming genome sequencing challenge with practice", - "5. Evaluate genome sequencing accuracy before harder fall challenge" - ] - }, - { - "id": 220, - "slug": "data-management-and-graph-extraction-for-large-models-in-the-biomedical-space", - "name": "Data management and graph extraction for large models in the biomedical space", - "headline": "Collaborative hackathon on the topic of data management and graph extraction...", - "headline_alternatives": [ - "1. CMU and DNAnexus partner for biomedical data hackathon", - "2. CMU hackathon tackles biomedical data management ", - "3. CMU hosts hackathon on biomedical data extraction", - "4. Collaborative hackathon focuses on biomedical data", - "5. CMU and DNAnexus hack genomic data challenges" - ] - }, - { - "id": 221, - "slug": "cagi2-asthma-twins", - "name": "CAGI2: Asthma discordant monozygotic twins", - "headline": "With the provided whole genome and RNA sequencing data, identify which two i...", - "headline_alternatives": [ - "1. Identify genetic differences between asthmatic and healthy twins", - "2. Find genomic variants linked to asthma in identical twins ", - "3. Detect genomic and transcriptomic differences between asthmatic twins", - "4. Analyze genomic and RNA-seq data to understand asthma in twins", - "5. Use twin genomes and transcriptomes to elucidate asthma pathogenesis" - ] - }, - { - "id": 222, - "slug": "cagi4-bipolar", - "name": "CAGI4: Bipolar disorder", - "headline": "With the provided exome data, identify which individuals have BD and which i...", - "headline_alternatives": [ - "1. Predicting bipolar disorder from exome data", - "2. Identifying bipolar disorder using exome sequences ", - "3. Detecting bipolar disorder with exome learning", - "4. Classifying bipolar disorder from exomes", - "5. Diagnosing bipolar disorder through exome analysis" - ] - }, - { - "id": 223, - "slug": "cagi3-brca", - "name": "CAGI3: BRCA1 & BRCA2", - "headline": "For each variant, provide the probability that Myriad Genetics has classifie...", - "headline_alternatives": [ - "1. Assess hereditary cancer risk via BRCA gene analysis", - "2. Detect BRCA mutations to identify hereditary cancer risk ", - "3. Proprietary test analyzes BRCA genes for cancer risk", - "4. Analyze BRCA genes to assess hereditary cancer risk", - "5. Test for BRCA mutations, link to hereditary cancer risk" - ] - }, - { - "id": 224, - "slug": "cagi2-breast-cancer-pkg", - "name": "CAGI2: Breast cancer pharmacogenomics", - "headline": "Cancer tissues are specifically responsive to different drugs. For this expe...", - "headline_alternatives": [ - "1. Exploring CHEK2 as a candidate gene for cancer susceptibility", - "2. Investigating the role of CHEK2 in DNA repair and cell cycle regulation ", - "3. Assessing CHEK2 interactions with BRCA1 and TP53 in genome maintenance", - "4. Evaluating CHEK2 in cell cycle control and genome integrity mechanisms", - "5. Identifying CHEK2 involvement in cancer through cell cycle regulation" - ] - }, - { - "id": 225, - "slug": "cagi4-2eqtl", - "name": "CAGI4: eQTL causal SNPs", - "headline": "Participants are asked to submit predictions of the regulatory sequences tha...", - "headline_alternatives": [ - "1. Identify regulatory variants causing gene expression differences", - "2. Find expression-modulating variants for human eQTLs ", - "3. Discover causal alleles for gene expression variation", - "4. Determine sequences and variants underlying eQTLs", - "5. Use MPRA to pinpoint regulatory causes of eQTLs" - ] - }, - { - "id": 226, - "slug": "cagi1-cbs", - "name": "CAGI1: CBS", - "headline": "Participants were asked to submit predictions for the effect of the variants...", - "headline_alternatives": [ - "1. Seeking to understand CBS enzyme function in cysteine production ", - "2. Investigating cofactor dependence of human CBS enzyme activity", - "3. Studying CBS deficiency causing homocystinuria genetic disorder", - "4. Characterizing molecular basis of CBS-dependent homocystinuria ", - "5. Elucidating metabolic defects in CBS-deficient homocystinuria patients" - ] - }, - { - "id": 227, - "slug": "cagi2-cbs", - "name": "CAGI2: CBS", - "headline": "Participants were asked to submit predictions for the effect of the variants...", - "headline_alternatives": [ - "1. Developing treatment for homocystinuria caused by CBS deficiency", - "2. Understanding CBS cofactor dependence for cysteine synthesis ", - "3. Studying CBS mutations causing homocystinuria ", - "4. Characterizing CBS enzyme function in sulfur metabolism", - "5. Analyzing vitamin B6 and heme binding to CBS enzyme" - ] - }, - { - "id": 228, - "slug": "cagi1-chek2", - "name": "CAGI1: CHEK2", - "headline": "Variants in the ATM & CHEK2 genes are associated with breast cancer.", - "headline_alternatives": [] - }, - { - "id": 229, - "slug": "cagi3-fch", - "name": "CAGI3: FCH", - "headline": "The challenge involved exome sequencing data for 5 subjects in an FCH family...", - "headline_alternatives": [ - "1. Seeking to understand genetic basis of common hyperlipidemia disorder", - "2. Uncovering genetics behind prevalent cholesterol and triglyceride disorder ", - "3. Investigating genetics of combined hyperlipidemia, a coronary disease risk", - "4. Studying genetics of complex and variable cholesterol/triglyceride disorder", - "5. Exploring genetics of common hyperlipidemia linked to heart disease" - ] - }, - { - "id": 230, - "slug": "cagi3-ha", - "name": "CAGI3: HA", - "headline": "The dataset for this challenge comprises of exome sequencing data for 4 subj...", - "headline_alternatives": [ - "1. Raising HDL levels to reduce heart disease risk", - "2. Increasing HDL and APOA1 to combat low HDL levels ", - "3. Boosting HDL cholesterol in hypoalphalipoproteinemia patients", - "4. Targeting low HDL as a coronary artery disease risk", - "5. Correcting HDL deficiency to improve cardiovascular health" - ] - }, - { - "id": 231, - "slug": "cagi2-croshn-s", - "name": "CAGI2: Crohn's disease", - "headline": "With the provided exome data, identify which individuals have Crohn's diseas...", - "headline_alternatives": [ - "1. Seeking genes linked to Crohn's, an inflammatory bowel disease", - "2. Identifying genetic factors in Crohn's disease, a chronic GI disorder ", - "3. Understanding the genetics behind Crohn's disease, an inflammatory GI condition", - "4. Studying chronic inflammation in Crohn's disease, a complex genetic disorder", - "5. Exploring genetic links to relapsing inflammation in Crohn's disease" - ] - }, - { - "id": 232, - "slug": "cagi3-crohn-s", - "name": "CAGI3: Crohn's disease", - "headline": "With the provided exome data, identify which individuals have Crohn's diseas...", - "headline_alternatives": [ - "1. Understanding the genetics behind Crohn's disease", - "2. Exploring chronic inflammation in Crohn's disease ", - "3. Investigating the complexity of Crohn's disease", - "4. Analyzing gastrointestinal involvement in Crohn's disease", - "5. Characterizing the relapsing nature of Crohn's disease" - ] - }, - { - "id": 233, - "slug": "cagi4-chron-s-exome", - "name": "CAGI4: Crohn's exomes", - "headline": "With the provided exome data, identify which individuals have Crohn's diseas...", - "headline_alternatives": [ - "1. Seeking to understand genetic basis of Crohn's bowel disease", - "2. Uncovering genomic factors in chronic gastrointestinal inflammation ", - "3. Investigating genetics behind Crohn's inflammatory bowel disorder", - "4. Exploring complex genetics of relapsing bowel inflammation in Crohn's ", - "5. Studying genes involved in chronic inflammatory Crohn's disease" - ] - }, - { - "id": 234, - "slug": "cagi4-hopkins", - "name": "CAGI4: Hopkins clinical panel", - "headline": "Participants were tasked with identifying the disease class for each of 106 ...", - "headline_alternatives": [ - "1. Exonic sequences of 83 genes linked to 14 diseases analyzed", - "2. 83 gene exons associated with 14 disease classes examined ", - "3. Examine exonic sequences of 83 genes related to 14 diseases", - "4. Analyze exonic sequences for 83 genes linked to 14 disease classes", - "5. Study exonic sequences of 83 genes associated with 14 disorders" - ] - }, - { - "id": 235, - "slug": "cagi2-mouse-exomes", - "name": "CAGI2: Mouse exomes", - "headline": "The challenge involved identifying the causative variants leading to one of ...", - "headline_alternatives": [ - "1. Predict causative variants from exome sequencing data. ", - "2. Identify variants causing unpublished phenotypes from exome data.", - "3. Compare computational predictions to unpublished causative variants. ", - "4. Predict unpublished causative variants using exome sequencing.", - "5. Determine if variants explain unpublished phenotypes from exomes." - ] - }, - { - "id": 236, - "slug": "cagi3-mrn-mre11", - "name": "CAGI3: MRE11", - "headline": "Genomes are subject to constant threat by damaging agents that generate DNA ...", - "headline_alternatives": [] - }, - { - "id": 237, - "slug": "cagi4-naglu", - "name": "CAGI4: NAGLU", - "headline": "Participants are asked to submit predictions on the effect of the variants o...", - "headline_alternatives": [ - "1. Predicting enzymatic activity of NAGLU mutants", - "2. Assessing fractional activity of NAGLU variants ", - "3. Evaluating mutants of lysosomal enzyme NAGLU", - "4. Estimating activity of NAGLU mutants in Sanfilippo B", - "5. Modeling effects of mutations on NAGLU function" - ] - }, - { - "id": 238, - "slug": "cagi4-npm-alk", - "name": "CAGI4: NPM: ALK", - "headline": "Participants are asked to submit predictions of both the kinase activity and...", - "headline_alternatives": [ - "1. Predicting kinase activity of NPM-ALK fusion mutants", - "2. Assessing NPM-ALK fusion protein mutations in cells ", - "3. Evaluating NPM-ALK mutant effects on kinase and binding", - "4. Quantifying NPM-ALK mutant kinase and binding changes", - "5. Modeling impacts of NPM-ALK mutations in vitro" - ] - }, - { - "id": 239, - "slug": "cagi3-mrn-nbs1", - "name": "CAGI3: NBS1", - "headline": "Genomes are subject to constant threat by damaging agents that generate DNA ...", - "headline_alternatives": [ - "1. Predicting Pathogenicity of Rare MRE11 and NBS1 Variants", - "2. Assessing Pathogenic Potential of Rare MRE11/NBS1 Mutations ", - "3. Rating Pathogenic Likelihood of Uncommon MRE11 and NBS1 Alleles", - "4. Estimating Disease Risk from Rare MRE11 and NBS1 Variants", - "5. Scoring Probability of Pathogenicity for Rare MRE11/NBS1 Variants" - ] - }, - { - "id": 240, - "slug": "cagi3-p16", - "name": "CAGI3: p16", - "headline": "CDKN2A is the most common, high penetrance, susceptibility gene identified t...", - "headline_alternatives": [ - "1. Assessing p16 protein variants' effects on cell growth", - "2. Testing if p16 variants can still halt cell proliferation ", - "3. Do mutations change p16's ability to stop cell division?", - "4. Evaluating if p16 variants retain anti-proliferative activity", - "5. Can p16 protein variants still inhibit cell proliferation?" - ] - }, - { - "id": 241, - "slug": "cagi2-p53", - "name": "CAGI2: p53 reactivation", - "headline": "Predictors are asked to submit predictions on the effect of the cancer rescu...", - "headline_alternatives": [] - }, - { - "id": 242, - "slug": "cagi1-pgp", - "name": "CAGI1: PGP", - "headline": "PGP challenge requires matching of full genome sequences to extensive phenot...", - "headline_alternatives": [ - "1. Participants share sequence and profile data publicly", - "2. Project makes participant data open for analysis ", - "3. Participants publicly release full genetic data profiles", - "4. Project opens participant sequence and phenotype data", - "5. Participants publicly share complete sequence and trait data" - ] - }, - { - "id": 243, - "slug": "cagi2-pgp", - "name": "CAGI2: PGP", - "headline": "PGP challenge requires matching of full genome sequences to extensive phenot...", - "headline_alternatives": [ - "1. Sequencing project shares data for prediction challenges", - "2. Participants openly provide sequences for prediction contests ", - "3. Prediction contests utilize shared sequence and profile data", - "4. Contests use pre-release data from collaborative sequencing project", - "5. Challenges based on pre-release collaboration sequence data" - ] - }, - { - "id": 244, - "slug": "cagi3-pgp", - "name": "CAGI3: PGP", - "headline": "PGP challenge requires matching of full genome sequences to extensive phenot...", - "headline_alternatives": [ - "1. Participants Share Genomic Data for Analysis Challenges", - "2. Genomic Data Released for Computational Prediction Tests ", - "3. Public Genomic Data Used in Prediction Competition ", - "4. Participants Make Genomes Public for Assessment Events", - "5. Genomic Sequence and Profile Data Shared Openly" - ] - }, - { - "id": 245, - "slug": "cagi4-pgp", - "name": "CAGI4: PGP", - "headline": "PGP challenge requires matching of full genome sequences to extensive phenot...", - "headline_alternatives": [] - }, - { - "id": 246, - "slug": "cagi4-pyruvate-kinase", - "name": "CAGI4: Pyruvate kinase", - "headline": "Participants are asked to submit predictions on the effect of the mutations ...", - "headline_alternatives": [ - "1. Predicting mutation impacts on pyruvate kinase activity and regulation", - "2. Assessing pyruvate kinase variant effects on allosteric regulation ", - "3. Modeling mutations in glycolytic enzyme pyruvate kinase ", - "4. Evaluating mutations in pyruvate kinase allosteric sites", - "5. Analyzing variants of pyruvate kinase for enzymatic defects" - ] - }, - { - "id": 247, - "slug": "cagi2-rad50", - "name": "CAGI2: RAD50", - "headline": "Predict the probability of the variant occurring in a case individual.", - "headline_alternatives": [ - "1. Assessing RAD50 variants for breast cancer risk", - "2. Evaluating RAD50 variants in breast cancer cases and controls ", - "3. Identifying RAD50 variants associated with breast cancer", - "4. Determining if RAD50 is a breast cancer gene ", - "5. Testing RAD50 as a breast cancer susceptibility gene" - ] - }, - { - "id": 248, - "slug": "cagi2-risksnps", - "name": "CAGI2: riskSNPs", - "headline": "The goal of these challenges is to investigate the community\u2019s ability to id...", - "headline_alternatives": [ - "1. Exploring molecular mechanisms linking SNPs to disease risk", - "2. Investigating potential mechanisms underlying SNP-disease associations ", - "3. Assigning putative mechanisms to SNP-disease risk loci", - "4. Cataloging plausible molecular mechanisms for SNP-disease links", - "5. Elucidating molecular underpinnings of SNP associations with disease" - ] - }, - { - "id": 249, - "slug": "cagi3-risksnps", - "name": "CAGI3: riskSNPs", - "headline": "The goal of these challenges is to investigate the community\u2019s ability to id...", - "headline_alternatives": [ - "1. Exploring molecular mechanisms linking SNPs to disease risk", - "2. Investigating possible mechanisms for SNP-disease associations ", - "3. Assigning potential mechanisms to SNP-disease risk loci", - "4. Can SNP-disease mechanisms be confidently determined?", - "5. Cataloging plausible mechanisms underlying SNP-disease links" - ] - }, - { - "id": 250, - "slug": "cagi2-nav1-5", - "name": "CAGI2: SCN5A", - "headline": "Predictors are asked to submit predictions on the effect of the mutants on t...", - "headline_alternatives": [] - }, - { - "id": 251, - "slug": "cagi2-mr-1", - "name": "CAGI2: Shewanella oneidensis strain MR-1", - "headline": "Shewanella oneidensis strain MR-1 (formerly known as S. putrefaciens) is a m...", - "headline_alternatives": [] - }, - { - "id": 252, - "slug": "cagi3-mr-1", - "name": "CAGI3: Shewanella oneidensis strain MR-1", - "headline": "Shewanella oneidensis strain MR-1 (formerly known as S. putrefaciens) is a m...", - "headline_alternatives": [] - }, - { - "id": 253, - "slug": "cagi4-sickkids", - "name": "CAGI4: SickKids", - "headline": "The challenge presented here is to use computational methods to match each g...", - "headline_alternatives": [ - "1. Predict phenotypes from genome sequences of children", - "2. Match genome sequences to clinical descriptions in kids ", - "3. Identify variants predicting genetic disorders from genomes", - "4. Link genome sequences and phenotypes in pediatric cases", - "5. Infer traits and disease risk from children's genomes" - ] - }, - { - "id": 254, - "slug": "cagi4-sumo-ligase", - "name": "CAGI4: SUMO ligase", - "headline": "Participants are asked to submit predictions of the effect of the variants o...", - "headline_alternatives": [] - }, - { - "id": 255, - "slug": "cagi3-splicing", - "name": "CAGI3: TP53 splicing", - "headline": "With the provided data determine which disease-causing mutations in the TP53...", - "headline_alternatives": [] - }, - { - "id": 256, - "slug": "cagi4-warfarin", - "name": "CAGI4: Warfarin exomes", - "headline": "With the provided exome data and clinical covariates, predict the therapeuti...", - "headline_alternatives": [ - "1. Improve warfarin dosing to reduce adverse events", - "2. Develop better warfarin dosing for fewer complications ", - "3. Optimize warfarin doses using new methods", - "4. Find better warfarin dosing strategies to limit risks", - "5. New approaches to warfarin dosing sought to cut harms" - ] - }, - { - "id": 257, - "slug": "cagi6-calmodulin", - "name": "CAGI6: Calmodulin", - "headline": "participants were asked to submit predictions for the competitive growth sco...", - "headline_alternatives": [] - }, - { - "id": 258, - "slug": "cagi2-splicing", - "name": "CAGI2: splicing", - "headline": "Predictors are asked to compare exons from wild type and disease-associated ...", - "headline_alternatives": [ - "1. Developing methods to improve accuracy of pre-mRNA splicing", - "2. Understanding mechanisms regulating spliceosome assembly on pre-mRNAs ", - "3. Elucidating roles of splicing factors in splice site recognition and intron removal", - "4. Characterizing spliceosome dynamics during catalytic steps of intron excision", - "5. Determining how splicing errors lead to disease-causing protein isoforms" - ] - }, - { - "id": 259, - "slug": "cagi6-arsa", - "name": "CAGI6: ARSA", - "headline": "Predicting the effect of naturally occurring missense mutations on enzymatic...", - "headline_alternatives": [ - "1. Predict enzyme activity for Metachromatic Leukodystrophy mutations", - "2. Forecast ARSA mutant function in lysosomal storage disease ", - "3. Estimate impact of ARSA variants in sulfatide metabolism", - "4. Model effects of missense mutations on ARSA activity", - "5. Quantify mutant protein function in genetic leukodystrophy" - ] - }, - { - "id": 260, - "slug": "predict-hits-for-the-wdr-domain-of-lrrk2", - "name": "CACHE1: PREDICT HITS FOR THE WDR DOMAIN OF LRRK2", - "headline": "Finding ligands targeting the central cavity of the WD-40 repeat (WDR) domai...", - "headline_alternatives": [ - "1. Seeking Compounds Binding to LRRK2's WD40 Parkinson's Protein", - "2. Discovering LRRK2 WD40 Inhibitors to Treat Parkinson's Disease", - "3. Targeting the WD40 Domain of LRRK2 for Parkinson's Therapy", - "4. Can Your Compounds Bind the LRRK2 WD40 Domain? ", - "5. Help Find Inhibitors of LRRK2's WD40 Domain for Parkinson's" - ] - }, - { - "id": 261, - "slug": "finding-ligands-targeting-the-conserved-rna-binding-site-of-sars-cov-2-nsp13", - "name": "CACHE2: FINDING LIGANDS TARGETING THE CONSERVED RNA BINDING SITE OF SARS-CoV-2 NSP13", - "headline": "Finding ligands targeting the conserved RNA binding site of SARS-CoV-2 NSP13.", - "headline_alternatives": [ - "1. New compounds to be tested using enzymatic and binding assays", - "2. Procured compounds evaluated via enzyme and binding experiments ", - "3. Compound library screened through enzymatic and target binding tests", - "4. Purchased molecules assayed enzymatically and for target interaction", - "5. Acquired chemicals tested in enzyme and binding activity assays" - ] - }, - { - "id": 262, - "slug": "finding-ligands-targeting-the-macrodomain-of-sars-cov-2-nsp3", - "name": "CACHE3: Finding ligands targeting the macrodomain of SARS-CoV-2 Nsp3", - "headline": "Severe acute respiratory syndrome coronavirus 2", - "headline_alternatives": [] - }, - { - "id": 263, - "slug": "finding-ligands-targeting-the-tkb-domain-of-cblb", - "name": "CACHE4: Finding ligands targeting the TKB domain of CBLB", - "headline": "Several cancers (PMID-33306199), potential immunotherapy (PMID-24875217), in...", - "headline_alternatives": [ - "1. Seeking Novel Compounds to Bind CBLB's TKB Domain", - "2. Discover New Chemicals that Bind CBLB's Closed Conformation ", - "3. Predict Binders Under 30 Micromolar for CBLB's TKB Domain", - "4. Wanted: Sub 30 Micromolar Binders to CBLB TKB Domain", - "5. Can You Find New Sub 30 Micromolar Binders for CBLB?" - ] - }, - { - "id": 264, - "slug": "jan2024-rare-disease-ai-hackathon", - "name": "Jan2024: Rare Disease AI Hackathon", - "headline": "Researchers and medical experts are invited to collaborate on our patient ca...", - "headline_alternatives": [ - "1. Uniting AI and medicine to aid rare disease diagnosis", - "2. Building open source AI models to unlock rare disease insights ", - "3. Creating open access to rare disease expertise with AI", - "4. Using AI to find connections between rare diseases", - "5. Launching open source AI models to improve rare disease care" - ] - }, - { - "id": 265, - "slug": "cometh-benchmark", - "name": "COMETH Benchmark", - "headline": "Quantify tumor heterogeneity-how many cell types are present and in which pr...", - "headline_alternatives": [ - "1. Quantifying Cancer Heterogeneity Using Statistical Methods", - "2. Estimating Cell Types in Cancer Samples with Omics Data ", - "3. Exploring Statistical Methods to Quantify Tumor Heterogeneity", - "4. Statistical Approaches to Deconvolute Cancer Samples ", - "5. Assessing Intra-tumor Heterogeneity Through Statistical Analysis" - ] - }, - { - "id": 266, - "slug": "the-miccai-2014-machine-learning-challenge", - "name": "The MICCAI 2014 Machine Learning Challenge", - "headline": "Predicting Binary and Continuous Phenotypes from Structural Brain MRI Data", - "headline_alternatives": [ - "1. Benchmark study to compare machine learning tools for brain MRI analysis", - "2. Standardized datasets to validate new machine learning tools for brain MRI ", - "3. MICCAI challenge to benchmark machine learning for brain MRI prediction", - "4. Assess state-of-the-art machine learning for brain MRI analysis", - "5. MICCAI competition compares machine learning tools for brain MRI" - ] - }, - { - "id": 267, - "slug": "cagi6-annotate-all-missense", - "name": "CAGI6: Annotate All Missense", - "headline": "Predictors are asked to predict the functional effect predict each coding SNV.", - "headline_alternatives": [ - "1. Predict functional impact of 81 million human protein variants", - "2. Assess effects of missense and nonsense variants across genome ", - "3. Ongoing assessment of variant function using new annotations", - "4. Compare predictions to new data on protein-altering variant effects", - "5. Can we predict the functional impact of every genomic variant?" - ] - }, - { - "id": 268, - "slug": "cagi6-hmbs", - "name": "CAGI6: HMBS", - "headline": "Participants are asked to submit predictions of the fitness score for each o...", - "headline_alternatives": [] - }, - { - "id": 269, - "slug": "cagi6-intellectual-disability-panel", - "name": "CAGI6: Intellectual Disability Panel", - "headline": "In this challenge predictors are asked to analyze the sequence data for the ...", - "headline_alternatives": [] - }, - { - "id": 270, - "slug": "cagi6-mapk1", - "name": "CAGI6: MAPK1", - "headline": "For each variant, participants are asked to predict the \u0394\u0394GH20 value for the...", - "headline_alternatives": [ - "1. Predict MAPK1 variant stability and catalytic efficiency", - "2. Assess impact of MAPK1 mutations on stability and function ", - "3. Quantify effects of MAPK1 variants on stability and kinetics", - "4. Calculate unfolding energies and catalytic efficiency of MAPK1 mutants", - "5. Model MAPK1 variant thermodynamic stability and enzymatic activity" - ] - }, - { - "id": 271, - "slug": "cagi6-mapk3", - "name": "CAGI6: MAPK3", - "headline": "For each variant, participants are asked to predict the \u0394\u0394GH20 value for the...", - "headline_alternatives": [ - "1. Predict stability and activity changes for MAPK3 variants", - "2. Quantify stability and function of MAPK3 mutants", - "3. Model effects of mutations on MAPK3 stability and catalysis ", - "4. Calculate unfolding energies and kinetics for MAPK3 mutants", - "5. Analyze thermodynamic and catalytic impacts of MAPK3 variants" - ] - }, - { - "id": 272, - "slug": "cagi6-mthfr", - "name": "CAGI6: MTHFR", - "headline": "Participants are asked to submit predictions of the fitness score for each m...", - "headline_alternatives": [] - }, - { - "id": 273, - "slug": "cagi6-polygenic-risk-scores", - "name": "CAGI6: Polygenic Risk Scores", - "headline": "Participants will be expected to provide a fully trained prediction model th...", - "headline_alternatives": [] - }, - { - "id": 274, - "slug": "cagi6-rare-genomes-project", - "name": "CAGI6: Rare Genomes Project", - "headline": "The prediction challenge involves approximately 30 families.The prediction s...", - "headline_alternatives": [ - "1. Identify causative variants in rare disease genomes to advance diagnosis", - "2. Analyze rare disease genomes to find variants causing participants' symptoms ", - "3. Use genome sequencing to diagnose rare diseases and discover new genes", - "4. Find variants causing rare diseases by analyzing RGP participant genomes", - "5. Diagnose rare diseases by identifying causative variants in RGP genomes" - ] - }, - { - "id": 275, - "slug": "cagi6-sherloc-clinical-classification", - "name": "CAGI6: Sherloc clinical classification", - "headline": "Over 122,000 coding (missense, silent, frameshift, stop gained, in-frame cod...", - "headline_alternatives": [ - "1. Predict pathogenicity of 122,000 uncharacterized variants for submission to ClinVar", - "2. Assess clinical utility of pathogenicity predictions for 122,000 variants to submit to ClinVar ", - "3. Interpret 122,000 variants and predict pathogenicity before submission to ClinVar", - "4. ClinVar submission: predict pathogenicity of 122,000 uncharacterized genetic variants ", - "5. Pathogenicity predictions of 122,000 variants for clinical utility assessment and ClinVar submission" - ] - }, - { - "id": 276, - "slug": "cagi6-splicing-vus", - "name": "CAGI6: Splicing VUS", - "headline": "Predict whether the experimentally validated variants of unknown significanc...", - "headline_alternatives": [ - "1. Predict splicing disruption from variants of unknown significance", - "2. Identify variants causing aberrant splicing from diagnostic sequencing ", - "3. Diagnose disorders by predicting splicing disruption from VUS variants", - "4. Predict which VUS variants disrupt splicing based on whole-blood RT-PCR", - "5. Identify missed diagnoses: predict splicing disruption from VUS variants" - ] - }, - { - "id": 277, - "slug": "cagi6-stk11", - "name": "CAGI6: STK11", - "headline": "Participants are asked to submit predictions on the impact of the variants l...", - "headline_alternatives": [] - }, - { - "id": 278, - "slug": "qbi-hackathon", - "name": "QBI hackathon", - "headline": "A 48-hour event connecting the Bay Area developer community with scientists ...", - "headline_alternatives": [ - "1. Hackathon connects developers and scientists to advance biomedical research ", - "2. 48-hour hackathon applies AI to biomedical data ", - "3. Hackathon pushes science ahead through latest algorithms", - "4. Developers and scientists collaborate on biomedical problems", - "5. Hackathon establishes connection between developers and scientists" - ] - }, - { - "id": 279, - "slug": "niddk-central-repository-data-centric-challenge", - "name": "NIDDK Central Repository Data-Centric Challenge", - "headline": "Enhancing NIDDK datasets for future Artificial Intelligence (AI) applications.", + "headline": "Crowdsourcing challenge to find disease modules in genomic networks for Dise...", "headline_alternatives": [ - "1. Challenge Seeks to Standardize Data for AI Discovery", - "2. Data Challenge Aims to Ready Datasets for AI Research ", - "3. Challenge Targets Data Standardization to Enable AI Insights", - "4. Data Challenge Focuses on Preparing Data for AI Analysis", - "5. Challenge Works to Improve Data for AI Research Discovery" + "1. Assessing module identification methods on genomic networks to find disease pathways (84 characters)", + "2. Discovering novel modules and pathways in genomic networks related to complex diseases (91 characters)", + "3. Leveraging crowdsourcing to identify disease modules in genomic networks (88 characters) ", + "4. Community effort to evaluate module identification in genomic networks for disease (93 characters)", + "5. Finding disease pathways by assessing module identification methods on genomic networks (97 characters)" ] } ] \ No newline at end of file diff --git a/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py b/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py index d7bf542379..9fecbaf71a 100644 --- a/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py +++ b/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py @@ -80,8 +80,11 @@ def generate_challenge_headlines(text, num_headlines): prompt = ( - f"Please generate {num_headlines} headlines that have a maximum ten words from the " - "following challenge description. The headline must summarize the goal of the challenge. " + f"Please generate {num_headlines} headlines that have less than 100 characters from the " + "following challenge description. The headlines must summarize the goal of the challenge. " + "The headlines must not include the name of the challenge. " + "The headlines must reads naturally and effectively communicates the topic of the page " + "content. " f"Description: \n{text}" ) response = Bedrock( @@ -118,7 +121,7 @@ def process_challenge(challenge): return obj -challenge_headlines = list(map(process_challenge, challenges)) +challenge_headlines = list(map(process_challenge, challenges[:20])) # SAVE OUTPUT TO FILE From 61919c548a4a9ee87c48ec29864e1eebcbf84360 Mon Sep 17 00:00:00 2001 From: Thomas Schaffter Date: Tue, 14 Nov 2023 18:21:54 +0000 Subject: [PATCH 2/4] Rename the script --- apps/openchallenges/notebook/README.md | 9 +- .../notebook/challenge_headlines.json | 167 ++---------------- ...llm.py => generate_challenge_headlines.py} | 12 +- 3 files changed, 27 insertions(+), 161 deletions(-) rename apps/openchallenges/notebook/src/challenge_headline/{challenge_headline_llm.py => generate_challenge_headlines.py} (89%) diff --git a/apps/openchallenges/notebook/README.md b/apps/openchallenges/notebook/README.md index 4c79644e42..a9cbf2d1ed 100644 --- a/apps/openchallenges/notebook/README.md +++ b/apps/openchallenges/notebook/README.md @@ -11,4 +11,11 @@ API and other related APIs. - `.python-version` - `prepare-python.sh` - `pyproject.toml` -2. Run `nx prepare openchallenges-notebook` \ No newline at end of file +2. Run `nx prepare openchallenges-notebook` + +## Generate challenge headlines + +``` +cd apps/openchallenges/notebook +poetry run python src/challenge_headline/generate_challenge_headlines.py +``` \ No newline at end of file diff --git a/apps/openchallenges/notebook/challenge_headlines.json b/apps/openchallenges/notebook/challenge_headlines.json index 1d696a4b09..6d28696805 100644 --- a/apps/openchallenges/notebook/challenge_headlines.json +++ b/apps/openchallenges/notebook/challenge_headlines.json @@ -11,7 +11,13 @@ "slug": "breast-cancer-prognosis", "name": "Breast Cancer Prognosis", "headline": "Predict breast cancer survival from clinical and genomic data for Breast Can...", - "headline_alternatives": [] + "headline_alternatives": [ + "1. Assess models predicting breast cancer survival from tumor and molecular data (79 characters)", + "2. Evaluate breast cancer prognosis predictions from clinical and genomic profiles (78 characters)", + "3. Test computational models forecasting breast cancer patient survival (76 characters) ", + "4. Can models accurately predict breast cancer prognosis from tumor/gene data? (79 characters)", + "5. Judging accuracy of breast cancer survival predictions from patient data (79 characters)" + ] }, { "id": 3, @@ -25,166 +31,19 @@ "slug": "drug-sensitivity-and-drug-synergy-prediction", "name": "Drug Sensitivity and Drug Synergy Prediction", "headline": "Revolutionizing Cancer Therapeutics: Predicting Drug Sensitivity in Human Ce...", - "headline_alternatives": [ - "1. Seeking computational methods to predict chemotherapeutic response from cancer cell line data (98 characters)", - "2. Develop models predicting drug response in cancer using cell line genomic profiles (93 characters) ", - "3. Improve cancer treatment by modeling drug sensitivity from cell line data (84 characters)", - "4. Identify chemotherapeutic response using computational analysis of cell lines (95 characters)", - "5. Create new ways to predict best cancer drugs from cell line experiments (97 characters)" - ] + "headline_alternatives": [] }, { "id": 5, "slug": "niehs-ncats-unc-toxicogenetics", "name": "NIEHS-NCATS-UNC Toxicogenetics", "headline": "Predicting cytotoxicity from genomic and chemical data for NIEHS-NCATS-UNC T...", - "headline_alternatives": [] - }, - { - "id": 6, - "slug": "whole-cell-parameter-estimation", - "name": "Whole-Cell Parameter Estimation", - "headline": "Seeking innovative parameter estimation methods for large models for Whole-C...", - "headline_alternatives": [] - }, - { - "id": 7, - "slug": "hpn-dream-breast-cancer-network-inference", - "name": "HPN-DREAM Breast Cancer Network Inference", - "headline": "Inferring causal signaling networks in breast cancer for HPN-DREAM Breast Ca...", - "headline_alternatives": [] - }, - { - "id": 8, - "slug": "rheumatoid-arthritis-responder", - "name": "Rheumatoid Arthritis Responder", - "headline": "Unlocking Anti-TNF Response Predictors: A Crowdsourced Breakthrough in RA Th...", - "headline_alternatives": [] - }, - { - "id": 9, - "slug": "icgc-tcga-dream-mutation-calling", - "name": "ICGC-TCGA DREAM Mutation Calling", - "headline": "Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection for ICGC-...", - "headline_alternatives": [ - "1. Global contest to advance cancer mutation detection in genome sequences. (100 characters)", - "2. International competition to improve identification of cancer mutations from DNA data. (99 characters) ", - "3. Worldwide effort to enhance techniques for finding cancer mutations in genomes. (97 characters)", - "4. Open challenge to progress methods for detecting genomic changes linked to cancer. (95 characters)", - "5. Crowdsourced contest pushing innovation in cancer genomics analysis methods. (99 characters)" - ] - }, - { - "id": 10, - "slug": "acute-myeloid-leukemia-outcome-prediction", - "name": "Acute Myeloid Leukemia Outcome Prediction", - "headline": "Uncover drivers of AML using clinical and proteomic data for Acute Myeloid L...", - "headline_alternatives": [ - "1. Uncover drivers of AML using clinical, genomic, and proteomic data for 271 AML patients. (99 characters)", - "2. Interpret rich AML dataset to predict outcomes and tailor therapies for leukemia patients. (91 characters)", - "3. Leverage clinical, mutation, and protein data to understand AML biology and improve patient care. (99 characters) ", - "4. Analyze proteomic profiles of 271 AML patients to uncover disease drivers and inform treatment. (99 characters)", - "5. Harness multi-omics AML data to accelerate leukemia drug development and precision medicine. (97 characters)" - ] - }, - { - "id": 11, - "slug": "broad-dream-gene-essentiality-prediction", - "name": "Broad-DREAM Gene Essentiality Prediction", - "headline": "Crowdsourcing Models to Predict Cancer Cell Gene Dependencies for Broad-DREA...", - "headline_alternatives": [ - "1. Crowdsourcing models to predict essential cancer genes from cell features (82 characters)", - "2. Inferring cancer cell gene dependencies from genomic biomarkers (76 characters)", - "3. Modeling cancer cell viability using gene expression and mutations (71 characters) ", - "4. Predicting essential genes in cancer cells via crowdsourcing (69 characters)", - "5. Crowd-based models to find key cancer genes and biomarkers (69 characters)" - ] - }, - { - "id": 12, - "slug": "alzheimers-disease-big-data", - "name": "Alzheimer's Disease Big Data", - "headline": "Seeking Accurate Predictive Biomarkers for Alzheimer's Diagnosis for Alzheim...", - "headline_alternatives": [] - }, - { - "id": 13, - "slug": "olfaction-prediction", - "name": "Olfaction Prediction", - "headline": "Predicting smell from molecule features for Olfaction Prediction", - "headline_alternatives": [ - "1. Predicting odor from molecular features to understand smell perception (82 characters)", - "2. Linking molecular properties to odor for fragrance design breakthroughs (91 characters)", - "3. Modeling how molecules' features relate to smell to advance fragrance creation (99 characters) ", - "4. Connecting chemical qualities to odor perception, accelerating fragrance development (93 characters)", - "5. Understanding smell from molecules, enabling faster fragrance ingredient discovery (97 characters)" - ] - }, - { - "id": 14, - "slug": "prostate-cancer", - "name": "Prostate Cancer", - "headline": "Predict survival of docetaxel treatment in mCRPC patients for Prostate Cancer", - "headline_alternatives": [] - }, - { - "id": 15, - "slug": "als-stratification-prize4life", - "name": "ALS Stratification Prize4Life", - "headline": "Advancing ALS Treatment: Predicting Disease Progression and Survival with Data.", - "headline_alternatives": [] - }, - { - "id": 16, - "slug": "astrazeneca-sanger-drug-combination-prediction", - "name": "AstraZeneca-Sanger Drug Combination Prediction", - "headline": "Predict effective drug combinations using genomic data for AstraZeneca-Sange...", - "headline_alternatives": [] - }, - { - "id": 17, - "slug": "smc-dna-meta", - "name": "SMC-DNA Meta", - "headline": "Seeking Most Accurate Somatic Mutation Detection Pipeline for SMC-DNA Meta", - "headline_alternatives": [ - "1. Seeking most accurate pipeline for detecting cancer mutations from callers", - "2. Establishing state-of-the-art in somatic mutation detection from predictors ", - "3. Identifying best meta-pipeline for somatic mutation calls from variants", - "4. Understanding complementarity of algorithms for cancer mutation detection", - "5. Highlighting advantages and deficiencies of somatic mutation callers" - ] - }, - { - "id": 18, - "slug": "smc-het", - "name": "SMC-Het", - "headline": "Crowdsourcing Challenge to Improve Tumor Subclonal Reconstruction for SMC-Het", - "headline_alternatives": [ - "1. Crowdsourcing challenge to improve subclonal reconstruction from tumor sequencing data. (99 characters)", - "2. Open challenge to advance quantification and genotyping of tumor subclones. (87 characters)", - "3. International effort to enhance tumor heterogeneity profiling from sequencing. (97 characters)", - "4. Collaborative challenge to progress tumor subclonal reconstruction methods. (97 characters) ", - "5. Crowdsourcing tumor heterogeneity profiling through subclonal reconstruction. (99 characters)" - ] - }, - { - "id": 19, - "slug": "respiratory-viral", - "name": "Respiratory Viral", - "headline": "Unraveling Viral Susceptibility: Early Predictors of Respiratory Infection a...", - "headline_alternatives": [] - }, - { - "id": 20, - "slug": "disease-module-identification", - "name": "Disease Module Identification", - "headline": "Crowdsourcing challenge to find disease modules in genomic networks for Dise...", "headline_alternatives": [ - "1. Assessing module identification methods on genomic networks to find disease pathways (84 characters)", - "2. Discovering novel modules and pathways in genomic networks related to complex diseases (91 characters)", - "3. Leveraging crowdsourcing to identify disease modules in genomic networks (88 characters) ", - "4. Community effort to evaluate module identification in genomic networks for disease (93 characters)", - "5. Finding disease pathways by assessing module identification methods on genomic networks (97 characters)" + "1. Predict cytotoxicity from genomic and chemical data", + "2. Model cytotoxicity responses to toxicants using genetics", + "3. Forecast cytotoxic effects of drugs with AI models ", + "4. Estimate cytotoxicity in cell lines via compound structures", + "5. AI to predict cytotoxicity from genomes and chemicals" ] } ] \ No newline at end of file diff --git a/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py similarity index 89% rename from apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py rename to apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py index 9fecbaf71a..0430fa9914 100644 --- a/apps/openchallenges/notebook/src/challenge_headline/challenge_headline_llm.py +++ b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py @@ -80,11 +80,11 @@ def generate_challenge_headlines(text, num_headlines): prompt = ( - f"Please generate {num_headlines} headlines that have less than 100 characters from the " - "following challenge description. The headlines must summarize the goal of the challenge. " - "The headlines must not include the name of the challenge. " - "The headlines must reads naturally and effectively communicates the topic of the page " - "content. " + f"Please generate {num_headlines} headlines that have less than 80 characters from the " + "following challenge description. " + "The headlines must summarize the goal of the challenge. " + # "The headlines must not include the name of the challenge. " + "The headlines must reads naturally. " f"Description: \n{text}" ) response = Bedrock( @@ -121,7 +121,7 @@ def process_challenge(challenge): return obj -challenge_headlines = list(map(process_challenge, challenges[:20])) +challenge_headlines = list(map(process_challenge, challenges[:5])) # SAVE OUTPUT TO FILE From a6a0dd99b90c2765425f4f1d315fb55f89dbd8c3 Mon Sep 17 00:00:00 2001 From: Thomas Schaffter Date: Tue, 14 Nov 2023 23:17:51 +0000 Subject: [PATCH 3/4] Update headlines --- .../notebook/challenge_headlines.json | 2642 ++++++++++++++++- .../generate_challenge_headlines.py | 2 +- 2 files changed, 2633 insertions(+), 11 deletions(-) diff --git a/apps/openchallenges/notebook/challenge_headlines.json b/apps/openchallenges/notebook/challenge_headlines.json index 6d28696805..37e4043ce9 100644 --- a/apps/openchallenges/notebook/challenge_headlines.json +++ b/apps/openchallenges/notebook/challenge_headlines.json @@ -12,11 +12,11 @@ "name": "Breast Cancer Prognosis", "headline": "Predict breast cancer survival from clinical and genomic data for Breast Can...", "headline_alternatives": [ - "1. Assess models predicting breast cancer survival from tumor and molecular data (79 characters)", - "2. Evaluate breast cancer prognosis predictions from clinical and genomic profiles (78 characters)", - "3. Test computational models forecasting breast cancer patient survival (76 characters) ", - "4. Can models accurately predict breast cancer prognosis from tumor/gene data? (79 characters)", - "5. Judging accuracy of breast cancer survival predictions from patient data (79 characters)" + "1. Assess models predicting breast cancer survival using clinical & molecular data (77 characters)", + "2. Evaluate breast cancer prognosis models with clinical and genomic profiles (79 characters)", + "3. Test accuracy of models predicting breast cancer outcomes with tumor data (76 characters) ", + "4. Benchmark computational models for breast cancer patient survival rates (79 characters)", + "5. Assessing breast cancer prognosis predictions using tumor and gene data (80 characters)" ] }, { @@ -39,11 +39,2633 @@ "name": "NIEHS-NCATS-UNC Toxicogenetics", "headline": "Predicting cytotoxicity from genomic and chemical data for NIEHS-NCATS-UNC T...", "headline_alternatives": [ - "1. Predict cytotoxicity from genomic and chemical data", - "2. Model cytotoxicity responses to toxicants using genetics", - "3. Forecast cytotoxic effects of drugs with AI models ", - "4. Estimate cytotoxicity in cell lines via compound structures", - "5. AI to predict cytotoxicity from genomes and chemicals" + "1. Predict cytotoxicity from genomic profiles and chemical structures (78 characters)", + "2. Model cytotoxicity in cell lines using genetics and chemical attributes (77 characters)", + "3. Forecast cytotoxic effects of compounds via genomic and structural data (78 characters) ", + "4. Estimate cytotoxicity in cell lines from genetics and chemistry (66 characters)", + "5. Predict variability in chemical toxicity using genomic and structural features (79 characters)" ] + }, + { + "id": 6, + "slug": "whole-cell-parameter-estimation", + "name": "Whole-Cell Parameter Estimation", + "headline": "Seeking innovative parameter estimation methods for large models for Whole-C...", + "headline_alternatives": [ + "1. Seeking innovative parameter estimation for large models (56 characters)", + "2. Developing optimization for parameter estimation of large models (65 characters)", + "3. Form teams to estimate parameters of heterogeneous models (65 characters) ", + "4. Compare approaches to estimate parameters of complex models (66 characters)", + "5. Explore methods to select informative experiments for models (69 characters)" + ] + }, + { + "id": 7, + "slug": "hpn-dream-breast-cancer-network-inference", + "name": "HPN-DREAM Breast Cancer Network Inference", + "headline": "Inferring causal signaling networks in breast cancer for HPN-DREAM Breast Ca...", + "headline_alternatives": [ + "1. Infer breast cancer signaling networks from perturbation data (65 characters)", + "2. Predict phosphorylation dynamics in breast cancer cells (54 characters)", + "3. Advance network inference in breast cancer with perturbation data (79 characters) ", + "4. Infer causal signaling networks in breast cancer (44 characters)", + "5. Use perturbation data to model breast cancer cell signaling (61 characters)" + ] + }, + { + "id": 8, + "slug": "rheumatoid-arthritis-responder", + "name": "Rheumatoid Arthritis Responder", + "headline": "Unlocking Anti-TNF Response Predictors: A Crowdsourced Breakthrough in RA Th...", + "headline_alternatives": [] + }, + { + "id": 9, + "slug": "icgc-tcga-dream-mutation-calling", + "name": "ICGC-TCGA DREAM Mutation Calling", + "headline": "Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection for ICGC-...", + "headline_alternatives": [ + "1. ICGC & TCGA launch challenge to improve cancer mutation detection in genomes (79 characters)", + "2. Crowdsourcing better methods for finding cancer mutations in genomes (76 characters) ", + "3. Open challenge seeks improved approaches for identifying cancer mutations (69 characters)", + "4. Dream challenge aims to advance cancer mutation identification from genomes (78 characters)", + "5. ICGC & TCGA partner on open challenge to boost cancer mutation calling (79 characters)" + ] + }, + { + "id": 10, + "slug": "acute-myeloid-leukemia-outcome-prediction", + "name": "Acute Myeloid Leukemia Outcome Prediction", + "headline": "Uncover drivers of AML using clinical and proteomic data for Acute Myeloid L...", + "headline_alternatives": [ + "1. Uncover drivers of AML using rich clinical and protein dataset (76 characters)", + "2. Interpret unique AML dataset to predict outcomes and tailor therapy (79 characters)", + "3. Access rich AML data to uncover drivers and predict patient outcomes (77 characters) ", + "4. Help predict AML outcomes using clinical and protein data (63 characters)", + "5. Uncover AML drivers using clinical, genetic and protein data (69 characters)" + ] + }, + { + "id": 11, + "slug": "broad-dream-gene-essentiality-prediction", + "name": "Broad-DREAM Gene Essentiality Prediction", + "headline": "Crowdsourcing Models to Predict Cancer Cell Gene Dependencies for Broad-DREA...", + "headline_alternatives": [] + }, + { + "id": 12, + "slug": "alzheimers-disease-big-data", + "name": "Alzheimer's Disease Big Data", + "headline": "Seeking Accurate Predictive Biomarkers for Alzheimer's Diagnosis for Alzheim...", + "headline_alternatives": [] + }, + { + "id": 13, + "slug": "olfaction-prediction", + "name": "Olfaction Prediction", + "headline": "Predicting smell from molecule features for Olfaction Prediction", + "headline_alternatives": [ + "1. Predicting how molecules smell from features", + "2. Linking molecular features to odor perception", + "3. Accelerating fragrance design through smell prediction ", + "4. Models to predict smell from molecule structure", + "5. Connecting molecular properties to olfactory perception" + ] + }, + { + "id": 14, + "slug": "prostate-cancer", + "name": "Prostate Cancer", + "headline": "Predict survival of docetaxel treatment in mCRPC patients for Prostate Cancer", + "headline_alternatives": [ + "1. Predict survival, toxicity for docetaxel mCRPC treatment", + "2. Improve prognostic modeling for mCRPC patients on docetaxel ", + "3. Benchmark models predicting mCRPC survival on docetaxel", + "4. Models to predict mCRPC survival, toxicity with docetaxel ", + "5. Establish benchmarks for mCRPC prognosis on docetaxel" + ] + }, + { + "id": 15, + "slug": "als-stratification-prize4life", + "name": "ALS Stratification Prize4Life", + "headline": "Advancing ALS Treatment: Predicting Disease Progression and Survival with Data.", + "headline_alternatives": [] + }, + { + "id": 16, + "slug": "astrazeneca-sanger-drug-combination-prediction", + "name": "AstraZeneca-Sanger Drug Combination Prediction", + "headline": "Predict effective drug combinations using genomic data for AstraZeneca-Sange...", + "headline_alternatives": [] + }, + { + "id": 17, + "slug": "smc-dna-meta", + "name": "SMC-DNA Meta", + "headline": "Seeking Most Accurate Somatic Mutation Detection Pipeline for SMC-DNA Meta", + "headline_alternatives": [ + "1. Identify best meta-pipeline for detecting cancer mutations (49 characters)", + "2. Establish state-of-the-art somatic mutation detection from callers (77 characters) ", + "3. Determine most accurate approach to identify cancer mutations (56 characters)", + "4. Assess complementarity of mutation calling algorithms for cancer (77 characters) ", + "5. Benchmark mutation detection pipelines to advance cancer genomics (79 characters)" + ] + }, + { + "id": 18, + "slug": "smc-het", + "name": "SMC-Het", + "headline": "Crowdsourcing Challenge to Improve Tumor Subclonal Reconstruction for SMC-Het", + "headline_alternatives": [ + "1. Crowdsourcing challenge to improve subclonal reconstruction in tumours (77 characters)", + "2. Challenge seeks better quantification of tumour heterogeneity (76 characters) ", + "3. Open competition to advance tumour subclonal reconstruction (79 characters)", + "4. Dream challenge for improving tumour heterogeneity analysis (79 characters)", + "5. ICGC & TCGA launch contest to quantify tumour subclones (79 characters)" + ] + }, + { + "id": 19, + "slug": "respiratory-viral", + "name": "Respiratory Viral", + "headline": "Unraveling Viral Susceptibility: Early Predictors of Respiratory Infection a...", + "headline_alternatives": [] + }, + { + "id": 20, + "slug": "disease-module-identification", + "name": "Disease Module Identification", + "headline": "Crowdsourcing challenge to find disease modules in genomic networks for Dise...", + "headline_alternatives": [ + "1. Crowdsourcing challenge to identify disease modules in genomic networks (79 characters)", + "2. Open challenge to find disease modules in genomic networks (63 characters) ", + "3. DREAM challenge to assess module ID methods on disease networks (79 characters)", + "4. Community effort to find novel disease modules in genomic networks (76 characters) ", + "5. DREAM challenge leverages crowds to find disease modules in networks (79 characters)" + ] + }, + { + "id": 21, + "slug": "encode", + "name": "ENCODE", + "headline": "Predict transcription factor binding sites from limited data for ENCODE", + "headline_alternatives": [ + "1. Predict TF binding sites from limited ChIP-seq data", + "2. Computational methods to expand TF binding site knowledge ", + "3. Improve TF binding site prediction with incomplete data", + "4. Fill knowledge gaps in TF binding landscapes ", + "5. Accurately predict TF binding without full experiments" + ] + }, + { + "id": 22, + "slug": "idea", + "name": "Idea", + "headline": "Fostering Collaborative Solutions in Health: The DREAM Idea Challenge", + "headline_alternatives": [ + "1. DREAM Challenge connects modelers, experimentalists to solve health questions (79 characters)", + "2. DREAM Idea Challenge enables modeler-experimentalist collaborations (76 characters)", + "3. DREAM Challenge builds wall of models to improve human health (79 characters) ", + "4. DREAM Idea Challenge shapes solutions to health through collaboration (78 characters)", + "5. DREAM Challenge fosters modeler-experimentalist partnerships for health (79 characters)" + ] + }, + { + "id": 23, + "slug": "smc-rna", + "name": "SMC-RNA", + "headline": "Crowdsourcing Challenge Seeks to Improve Cancer Mutation Detection from RNA ...", + "headline_alternatives": [] + }, + { + "id": 24, + "slug": "digital-mammography-dream-challenge", + "name": "Digital Mammography DREAM Challenge", + "headline": "Improve mammography prediction to detect breast cancer early for Digital Mam...", + "headline_alternatives": [] + }, + { + "id": 25, + "slug": "multiple-myeloma", + "name": "Multiple Myeloma", + "headline": "Develop precise risk model for myeloma patients for Multiple Myeloma", + "headline_alternatives": [] + }, + { + "id": 26, + "slug": "ga4gh-dream-workflow-execution", + "name": "GA4GH-DREAM Workflow Execution", + "headline": "Develop technologies to enable distributed genomic data analysis for GA4GH-D...", + "headline_alternatives": [] + }, + { + "id": 27, + "slug": "parkinsons-disease-digital-biomarker", + "name": "Parkinson's Disease Digital Biomarker", + "headline": "Benchmarking methods to develop Parkinson's digital signatures from sensor d...", + "headline_alternatives": [ + "1. Extract features from sensor data to predict Parkinson's pathology", + "2. Benchmark methods to process sensor data for Parkinson's biomarkers ", + "3. Develop digital signatures of Parkinson's from raw sensor data", + "4. Assess algorithms extracting predictive features from motor task data ", + "5. Evaluate approaches to extract Parkinson's biomarkers from sensor time series" + ] + }, + { + "id": 28, + "slug": "nci-cptac-proteogenomics", + "name": "NCI-CPTAC Proteogenomics", + "headline": "Develop tools to extract insights from cancer proteomics data for NCI-CPTAC ...", + "headline_alternatives": [] + }, + { + "id": 29, + "slug": "multi-targeting-drug", + "name": "Multi-Targeting Drug", + "headline": "Seeking Generalizable Methods to Predict Multi-Target Compound Binding for M...", + "headline_alternatives": [ + "1. Predict compounds binding to targets, avoiding anti-targets (79 characters)", + "2. Develop generalizable multi-target binding prediction methods (77 characters) ", + "3. Incentivize multi-target binding prediction model development (79 characters)", + "4. Predict compounds binding specific targets, avoiding other binding (77 characters) ", + "5. Develop reusable methods to predict selective compound binding (78 characters)" + ] + }, + { + "id": 30, + "slug": "single-cell-transcriptomics", + "name": "Single Cell Transcriptomics", + "headline": "Reconstructing Cell Locations in Drosophila Embryo from Transcripts for Sing...", + "headline_alternatives": [] + }, + { + "id": 31, + "slug": "idg-drug-kinase-binding", + "name": "IDG Drug-Kinase Binding", + "headline": "Challenge seeks machine learning for drug-kinase binding prediction for IDG ...", + "headline_alternatives": [] + }, + { + "id": 32, + "slug": "malaria", + "name": "Malaria", + "headline": "Predict malaria drug resistance from parasite gene expression for Malaria", + "headline_alternatives": [] + }, + { + "id": 33, + "slug": "preterm-birth-prediction-transcriptomics", + "name": "Preterm Birth Prediction - Transcriptomics", + "headline": "Developing Accurate, Inexpensive Molecular Clock to Determine Gestational Ag...", + "headline_alternatives": [ + "1. Developing accurate, low-cost molecular clock to establish pregnancy timeline", + "2. Creating prediction models for gestational age from blood samples ", + "3. Identifying women at risk of preterm birth and other complications", + "4. Improving pregnancy care through better assessment of gestational age", + "5. Using gene expression to establish molecular clock for pregnancy" + ] + }, + { + "id": 34, + "slug": "single-cell-signaling-in-breast-cancer", + "name": "Single-Cell Signaling in Breast Cancer", + "headline": "Exploring heterogeneous signaling in single cancer cells for Single-Cell Sig...", + "headline_alternatives": [] + }, + { + "id": 35, + "slug": "ehr-dream-challenge-patient-mortality-prediction", + "name": "EHR DREAM Challenge: Patient Mortality Prediction", + "headline": "New tools to reconstruct cell lineages from CRISPR mutations for EHR DREAM C...", + "headline_alternatives": [] + }, + { + "id": 36, + "slug": "allen-institute-cell-lineage-reconstruction", + "name": "Allen Institute Cell Lineage Reconstruction", + "headline": "New tools enable reconstructing complex cell lineages at single-cell resolut...", + "headline_alternatives": [] + }, + { + "id": 37, + "slug": "tumor-deconvolution", + "name": "Tumor Deconvolution", + "headline": "Assess computational methods to deconvolve bulk tumor data into immune compo...", + "headline_alternatives": [ + "1. Assess computational methods to deconvolve bulk tumor data into immune components (77 characters)", + "2. Evaluate algorithms for deconvolving bulk tumor data into individual cell types (79 characters)", + "3. Test computational deconvolution of bulk tumor data into specific immune cells (69 characters) ", + "4. Assess deconvolution methods on bulk tumor data to quantify infiltration (71 characters)", + "5. Evaluate computational infiltration analysis from bulk tumor profiling (66 characters)" + ] + }, + { + "id": 38, + "slug": "ctd2-pancancer-drug-activity", + "name": "CTD2 Pancancer Drug Activity", + "headline": "Benchmark algorithms predicting drug targets from gene data for CTD2 Pancanc...", + "headline_alternatives": [] + }, + { + "id": 39, + "slug": "ctd2-beataml", + "name": "CTD2 BeatAML", + "headline": "Seeking New Drug Targets for Precision AML Treatment for CTD2 BeatAML", + "headline_alternatives": [] + }, + { + "id": 40, + "slug": "metadata-automation", + "name": "Metadata Automation", + "headline": "Semi-Automating Metadata Annotation for Enhanced Data Sharing in Cancer Research", + "headline_alternatives": [ + "1. Develop tools to semi-automate metadata annotation for cancer data sharing (76 characters)", + "2. Semi-automate metadata annotation to enable cancer data transformations (72 characters)", + "3. Create tools to annotate metadata to share cancer research data (65 characters) ", + "4. Build semi-automated tools for metadata annotation of cancer data (69 characters)", + "5. Develop semi-automated annotation tools to transform cancer data (71 characters)" + ] + }, + { + "id": 41, + "slug": "automated-scoring-of-radiographic-joint-damage", + "name": "Automated Scoring of Radiographic Joint Damage", + "headline": "Develop automated method to quantify rheumatoid arthritis joint damage for A...", + "headline_alternatives": [] + }, + { + "id": 42, + "slug": "beat-pd", + "name": "BEAT-PD", + "headline": "Develop mobile sensors to remotely monitor Parkinson's disease for BEAT-PD", + "headline_alternatives": [] + }, + { + "id": 43, + "slug": "ctd2-pancancer-chemosensitivity", + "name": "CTD2 Pancancer Chemosensitivity", + "headline": "Predict drug sensitivity from cell line gene expression for CTD2 Pancancer C...", + "headline_alternatives": [] + }, + { + "id": 44, + "slug": "ehr-dream-challenge-covid-19", + "name": "EHR DREAM Challenge: COVID-19", + "headline": "Develop tools to predict COVID-19 risk without sharing data for EHR DREAM Ch...", + "headline_alternatives": [] + }, + { + "id": 45, + "slug": "anti-pd1-response-prediction", + "name": "Anti-PD1 Response Prediction", + "headline": "Predicting lung cancer response to immuno-oncology therapy", + "headline_alternatives": [ + "1. Develop models predicting lung cancer response to I-O therapy (79 characters)", + "2. Gain insights on improving I-O therapy response prediction in lung cancer (78 characters) ", + "3. Leverage data to predict lung cancer patient response to I-O treatment (76 characters)", + "4. Improve prediction of I-O therapy benefit for lung cancer patients (58 characters)", + "5. Predictive modeling of lung cancer response to immuno-oncology therapy (79 characters)" + ] + }, + { + "id": 46, + "slug": "brats-2021-challenge", + "name": "BraTS 2021 Challenge", + "headline": "Developing ML methods to analyze brain tumor MRI scans", + "headline_alternatives": [ + "1. ML methods to analyze brain tumor MRI scans (49 characters)", + "2. Assessing ML for segmenting glioblastoma in MRI (56 characters) ", + "3. Evaluating ML segmentation of brain tumors (49 characters)", + "4. BraTS challenge tests ML for glioblastoma MRI analysis (63 characters)", + "5. Can ML improve glioblastoma tumor detection in MRI? (59 characters)" + ] + }, + { + "id": 47, + "slug": "cancer-data-registry-nlp", + "name": "Cancer Data Registry NLP", + "headline": "Predicting lung cancer response to immuno-oncology therapy", + "headline_alternatives": [ + "1. Unlock hidden clinical data with NLP for research", + "2. Develop NLP to tap unstructured EHR data for trials ", + "3. Improve clinical trial matching with NLP algorithms", + "4. Evaluate NLP methods to access PHI-sensitive data ", + "5. Advance NLP solutions to leverage clinical text data" + ] + }, + { + "id": 48, + "slug": "barda-community-challenge-pediatric-covid-19-data-challenge", + "name": "BARDA Community Challenge - Pediatric COVID-19 Data Challenge", + "headline": "Models to predict severe COVID-19 in children sought", + "headline_alternatives": [] + }, + { + "id": 49, + "slug": "brats-continuous-evaluation", + "name": "BraTS Continuous Evaluation", + "headline": "Seeking Innovations To Improve Brain Tumor Diagnosis And Treatment", + "headline_alternatives": [] + }, + { + "id": 50, + "slug": "fets-2022", + "name": "FeTS 2022", + "headline": "Federated Learning Challenge 2022: Advancing Brain Tumor Segmentation Algorithms", + "headline_alternatives": [] + }, + { + "id": 51, + "slug": "random-promotor", + "name": "Random Promotor", + "headline": "Deciphering Gene Regulation: Training Models to Predict Gene Expression Patterns", + "headline_alternatives": [] + }, + { + "id": 52, + "slug": "preterm-birth-prediction-microbiome", + "name": "Preterm Birth Prediction - Microbiome", + "headline": "Seeking Innovations To Improve Brain Tumor Diagnosis And Treatment", + "headline_alternatives": [ + "1. Predicting preterm births to reduce infant mortality", + "2. Identifying preterm birth risks for timely treatment ", + "3. Forecasting preterm deliveries to improve infant health", + "4. Detecting high preterm birth risk for preventative care", + "5. Estimating preterm likelihood to administer proper care" + ] + }, + { + "id": 53, + "slug": "finrisk", + "name": "FINRISK - Heart Failure and Microbiome", + "headline": "FINRISK - Heart Failure and Microbiome: (No headline provided)", + "headline_alternatives": [] + }, + { + "id": 54, + "slug": "scrna-seq-and-scatac-seq-data-analysis", + "name": "scRNA-seq and scATAC-seq Data Analysis", + "headline": "Assess computational methods for scRNA-seq and scATAC-seq analysis", + "headline_alternatives": [] + }, + { + "id": 55, + "slug": "cough-diagnostic-algorithm-for-tuberculosis", + "name": "COugh Diagnostic Algorithm for Tuberculosis", + "headline": "Assess computational methods for scRNA-seq and scATAC-seq analysis", + "headline_alternatives": [] + }, + { + "id": 56, + "slug": "nih-long-covid-computational-challenge", + "name": "NIH Long COVID Computational Challenge", + "headline": "Understanding Prevalence and Outcomes of Post-COVID Syndrome", + "headline_alternatives": [ + "1. Seeking analytics to understand prevalence and outcomes of long COVID symptoms (79 characters)", + "2. Can advanced analytics extract insights on long COVID from complex health data? (76 characters) ", + "3. Harnessing analytics to characterize long COVID syndrome prevalence and duration (77 characters)", + "4. Using analytics to elucidate long COVID symptoms, outcomes, and heterogeneity (74 characters)", + "5. Applying advanced analytics to unravel long COVID prevalence, symptoms, and outcomes (79 characters)" + ] + }, + { + "id": 57, + "slug": "bridge2ai", + "name": "Bridge2AI", + "headline": "What makes a good color palette?", + "headline_alternatives": [] + }, + { + "id": 58, + "slug": "rare-x-open-data-science", + "name": "RARE-X Open Data Science", + "headline": "Unlocking rare disease mysteries through open science collaboration", + "headline_alternatives": [] + }, + { + "id": 59, + "slug": "cagi5-regulation-saturation", + "name": "CAGI5: Regulation saturation", + "headline": "Predicting effects of variants in disease-linked enhancers and promoters", + "headline_alternatives": [] + }, + { + "id": 60, + "slug": "cagi5-calm1", + "name": "CAGI5: CALM1", + "headline": "Predicting effects of calmodulin variants on yeast growth", + "headline_alternatives": [] + }, + { + "id": 61, + "slug": "cagi5-pcm1", + "name": "CAGI5: PCM1", + "headline": "Assessing PCM1 variants' impact on zebrafish ventricle", + "headline_alternatives": [ + "1. Assessing PCM1 variants' impact on zebrafish brain ventricle size", + "2. Do PCM1 mutations linked to schizophrenia affect zebrafish ventricles?", + "3. Testing if PCM1 variants alter zebrafish ventricular area ", + "4. Evaluating zebrafish ventricles with PCM1 mutations tied to schizophrenia", + "5. Can PCM1 variants' effects on zebrafish predict schizophrenia risk?" + ] + }, + { + "id": 62, + "slug": "cagi5-frataxin", + "name": "CAGI5: Frataxin", + "headline": "Unveiling Protein Stability: Predicting \u0394\u0394GH20 for Frataxin Variants", + "headline_alternatives": [] + }, + { + "id": 63, + "slug": "cagi5-tpmt", + "name": "CAGI5: TPMT and p10", + "headline": "Cracking the Code: Predicting TPMT and PTEN Protein Stability Variants", + "headline_alternatives": [ + "1. Predict effect of PTEN/TPMT mutations on protein stability", + "2. Assess PTEN/TPMT variant stability using multiplexed profiling ", + "3. Quantify protein stability changes from PTEN/TPMT mutation library", + "4. Model impacts of genetic variants on PTEN and TPMT stability", + "5. Estimate protein abundance changes from fusion assay on mutants" + ] + }, + { + "id": 64, + "slug": "cagi5-annotate-all-missense", + "name": "CAGI5: Annotate all nonsynonymous variants", + "headline": "Annotate all nonsynonymous variants", + "headline_alternatives": [] + }, + { + "id": 65, + "slug": "cagi5-gaa", + "name": "CAGI5: GAA", + "headline": "Predict enzyme activity of GAA mutants in Pompe disease", + "headline_alternatives": [] + }, + { + "id": 66, + "slug": "cagi5-chek2", + "name": "CAGI5: CHEK2", + "headline": "Estimate CHEK2 gene variant probabilities in Latino breast cancer cases", + "headline_alternatives": [ + "1. Estimate CHEK2 variant probabilities in Latino breast cancer cases (78 characters)", + "2. Predict CHEK2 variant probabilities from Latino breast cancer cohort (77 characters) ", + "3. Calculate probabilities of CHEK2 variants in Latino breast cancer (76 characters)", + "4. Model CHEK2 variant probabilities in Latina breast cancer cases (79 characters)", + "5. Estimate likelihood of CHEK2 variants in Latina breast cancer patients (79 characters)" + ] + }, + { + "id": 67, + "slug": "cagi5-enigma", + "name": "CAGI5: ENIGMA", + "headline": "Predicting cancer risk from BRCA1/2 gene variants", + "headline_alternatives": [] + }, + { + "id": 68, + "slug": "cagi5-mapsy", + "name": "CAGI5: MaPSy", + "headline": "Predicting the Impact of Genetic Variants on Splicing Mechanisms", + "headline_alternatives": [] + }, + { + "id": 69, + "slug": "cagi5-vex-seq", + "name": "CAGI5: Vex-seq", + "headline": "Predict splicing changes from variants in globin gene", + "headline_alternatives": [] + }, + { + "id": 70, + "slug": "cagi5-sickkids5", + "name": "CAGI5: SickKids clinical genomes", + "headline": "Predict genetic disorders from 30 child genomes and phenotypes.", + "headline_alternatives": [] + }, + { + "id": 71, + "slug": "cagi5-intellectual-disability", + "name": "CAGI5: ID Panel", + "headline": "Predict phenotypes and variants from gene panel sequences", + "headline_alternatives": [] + }, + { + "id": 72, + "slug": "cagi5-clotting-disease", + "name": "CAGI5: Clotting disease exomes", + "headline": "Predicting venous thromboembolism risk in African Americans", + "headline_alternatives": [] + }, + { + "id": 73, + "slug": "cagi6-sickkids", + "name": "CAGI6: SickKids clinical genomes and transcriptomes", + "headline": "Identify genes causing rare diseases using transcriptomics", + "headline_alternatives": [] + }, + { + "id": 74, + "slug": "cagi6-cam", + "name": "CAGI6: CaM", + "headline": "Predicting the Impact of Point Mutations on Calmodulin Stability", + "headline_alternatives": [] + }, + { + "id": 75, + "slug": "cami-ii", + "name": "CAMI II", + "headline": "Assembling and Classifying Microbial Genomes in Complex Samples", + "headline_alternatives": [ + "1. CAMI II challenges for genome and taxonomic binning of environmental data", + "2. CAMI II: Assembling and analyzing multi-sample microbiome data ", + "3. CAMI II: Binning genomes and profiling taxa from diverse environments", + "4. CAMI II offers microbiome analysis challenges on clinical, marine samples", + "5. CAMI II challenges: genome assembly, binning genomes and taxa " + ] + }, + { + "id": 76, + "slug": "camda18-metasub-forensics", + "name": "CAMDA18-MetaSUB Forensics", + "headline": "Building a metagenomic map of mass-transit systems globally", + "headline_alternatives": [ + "1. Building a metagenomic map of mass transit systems across the globe (79 characters)", + "2. Analyzing metagenomic data from global city sampling days (76 characters)", + "3. Multi-city forensic analyses using metagenomic data from mass transit (78 characters) ", + "4. Longitudinal study of microbes in mass transit systems worldwide (77 characters)", + "5. Metagenomic mapping of microbes in public spaces globally over time (78 characters)" + ] + }, + { + "id": 77, + "slug": "camda18-cmap-drug-safety", + "name": "CAMDA18-CMap Drug Safety", + "headline": "Predicting drug toxicity using cell-based gene expression data", + "headline_alternatives": [] + }, + { + "id": 78, + "slug": "camda18-cancer-data-integration", + "name": "CAMDA18-Cancer Data Integration", + "headline": "Unify data integration approaches for breast cancer and neuroblastoma", + "headline_alternatives": [ + "1. Unify data integration to beat state of art in breast and neuroblastoma", + "2. Improve breast and neuroblastoma outcomes via data integration ", + "3. Data integration to advance breast cancer and neuroblastoma care", + "4. Integrate data to outperform current methods in breast and neuroblastoma ", + "5. Data integration to match state of art in breast cancer and neuroblastoma" + ] + }, + { + "id": 79, + "slug": "cafa-4", + "name": "CAFA 4", + "headline": "Assessing algorithms for predicting protein function", + "headline_alternatives": [ + "1. Assessing algorithms for predicting protein function from sequences (58 characters)", + "2. Evaluating automated methods to predict protein function (53 characters)", + "3. Benchmarking protein function prediction algorithms (56 characters) ", + "4. Critical test of computational protein annotation methods (63 characters)", + "5. Testing algorithms that computationally assign functions to proteins (63 characters)" + ] + }, + { + "id": 80, + "slug": "casp13", + "name": "CASP13", + "headline": "CASP assesses protein structure prediction methods", + "headline_alternatives": [ + "1. CASP tests progress in predicting protein structures from sequences (78 characters)", + "2. CASP12 drew protein structure models for 82 targets from 100 groups (77 characters) ", + "3. Every 2 years, CASP assesses progress in modeling protein structures (65 characters)", + "4. CASP community experiment benchmarks protein structure prediction (56 characters)", + "5. 50,000 models on 82 targets submitted for CASP12 protein challenge (79 characters)" + ] + }, + { + "id": 81, + "slug": "casp14", + "name": "CASP14", + "headline": "Assessing progress in protein structure prediction", + "headline_alternatives": [ + "1. CASP tests progress in predicting protein structure from sequence (73 characters)", + "2. CASP14 drew 100 groups to model 90 protein targets (66 characters) ", + "3. Every 2 years CASP assesses protein structure prediction methods (69 characters)", + "4. CASP community experiment benchmarks protein modeling techniques (76 characters)", + "5. 67,000 models on 90 targets in recent CASP protein structure challenge (79 characters)" + ] + }, + { + "id": 82, + "slug": "cfsan-pathogen-detection", + "name": "CFSAN Pathogen Detection", + "headline": "Rapidly Identify Food Sources of Outbreaks", + "headline_alternatives": [] + }, + { + "id": 83, + "slug": "cdrh-biothreat", + "name": "CDRH Biothreat", + "headline": "Identifying infectious diseases from clinical samples using sequencing techn...", + "headline_alternatives": [] + }, + { + "id": 84, + "slug": "multi-omics-enabled-sample-mislabeling-correction", + "name": "Multi-omics Enabled Sample Mislabeling Correction", + "headline": "Multi-omics Enabled Sample Mislabeling Correction: (No headline provided)", + "headline_alternatives": [] + }, + { + "id": 85, + "slug": "biocompute-object-app-a-thon", + "name": "BioCompute Object App-a-thon", + "headline": "Seeking Standards for Reproducible Bioinformatics Analysis", + "headline_alternatives": [] + }, + { + "id": 86, + "slug": "brain-cancer-predictive-modeling-and-biomarker-discovery", + "name": "Brain Cancer Predictive Modeling and Biomarker Discovery", + "headline": "Seeking novel biomarkers to advance precision medicine for brain tumors", + "headline_alternatives": [ + "1. Seeking novel biomarkers for glioma prognosis and treatment (76 characters)", + "2. Advancing precision medicine for brain tumors via new biomarkers (79 characters)", + "3. Identifying multi-omics markers to improve brain tumor outcomes (71 characters) ", + "4. Can new biomarkers advance precision medicine for gliomas? (63 characters)", + "5. Calling for innovative glioma biomarkers to enable precision care (79 characters)" + ] + }, + { + "id": 87, + "slug": "gaining-new-insights-by-detecting-adverse-event-anomalies", + "name": "Gaining New Insights by Detecting Adverse Event Anomalies", + "headline": "Seeking Algorithms to Detect Adverse Events in FDA Data", + "headline_alternatives": [] + }, + { + "id": 88, + "slug": "calling-variants-in-difficult-to-map-regions", + "name": "Calling Variants in Difficult-to-Map Regions", + "headline": "Precision Benchmarking: Evaluating Variant Calling in Complex Genomic Regions", + "headline_alternatives": [] + }, + { + "id": 89, + "slug": "vha-innovation-ecosystem-and-covid-19-risk-factor-modeling", + "name": "VHA Innovation Ecosystem and COVID-19 Risk Factor Modeling", + "headline": "AI for COVID-19: Predicting Health Outcomes in the Veteran Population", + "headline_alternatives": [] + }, + { + "id": 90, + "slug": "covid-19-precision-immunology-app-a-thon", + "name": "COVID-19 Precision Immunology App-a-thon", + "headline": "Seeking insights on COVID-19 pathophysiology to enable effective strategies.", + "headline_alternatives": [] + }, + { + "id": 91, + "slug": "smarter-food-safety-low-cost-tech-enabled-traceability", + "name": "Smarter Food Safety Low Cost Tech-Enabled Traceability", + "headline": "Seeking Affordable Tech Solutions for Food Traceability", + "headline_alternatives": [] + }, + { + "id": 92, + "slug": "tumor-mutational-burden-tmb-challenge-phase-1", + "name": "Tumor Mutational Burden (TMB) Challenge Phase 1", + "headline": "Standardizing Tumor Mutational Burden (TMB) Calculation in Cancer Research", + "headline_alternatives": [] + }, + { + "id": 93, + "slug": "kits21", + "name": "Kidney and Kidney Tumor Segmentation", + "headline": "Contest Seeks Best Kidney Tumor Segmentation System", + "headline_alternatives": [] + }, + { + "id": 94, + "slug": "realnoisemri", + "name": "Real Noise MRI", + "headline": "Developing fast MRI techniques without fully sampled data", + "headline_alternatives": [ + "1. Develop fast MRI techniques without relying on fully sampled data", + "2. Improve MRI speed without using fully sampled images as ground truth ", + "3. Fast MRI acquisition through innovative methods not needing full data", + "4. Speed up MRI sans full k-space data as benchmark for undersampling", + "5. Faster MRI sans complete Fourier data as reference for undersampling" + ] + }, + { + "id": 95, + "slug": "deep-generative-model-challenge-for-da-in-surgery", + "name": "Deep Generative Model Challenge for DA in Surgery", + "headline": "Challenge aims to adapt algorithms from simulation to mitral valve surgery", + "headline_alternatives": [] + }, + { + "id": 96, + "slug": "aimdatathon", + "name": "AIM Datathon 2020", + "headline": "AIM Datathon 2020: \"Join the AI in Medicine (AIM) Datathon 2020\"", + "headline_alternatives": [] + }, + { + "id": 97, + "slug": "opc-recurrence", + "name": "Oropharynx Cancer (OPC) Radiomics Challenge :: Local Recurrence Prediction", + "headline": "Determine from CT data whether a tumor will be controlled by definitive radi...", + "headline_alternatives": [] + }, + { + "id": 98, + "slug": "oropharynx-radiomics-hpv", + "name": "Oropharynx Cancer (OPC) Radiomics Challenge :: Human Papilloma Virus (HPV) Status Prediction", + "headline": "Human Papilloma Virus (HPV) Status Prediction: \"Predict from CT data the HPV...", + "headline_alternatives": [] + }, + { + "id": 99, + "slug": "data-science-bowl-2017", + "name": "Data Science Bowl 2017", + "headline": "\"Can you improve lung cancer detection?\"", + "headline_alternatives": [] + }, + { + "id": 100, + "slug": "predict-impact-of-air-quality-on-death-rates", + "name": "Predict impact of air quality on mortality rates", + "headline": "\"Predict CVD and cancer caused mortality rates in England using air quality ...", + "headline_alternatives": [ + "1. Predict mortality in England from air quality data (34 characters)", + "2. Forecast CVD and cancer deaths using air monitoring (43 characters) ", + "3. Model England mortality rates with Copernicus air data (49 characters)", + "4. Estimate CVD and cancer mortality in England from air quality (56 characters)", + "5. Use Copernicus air monitoring to predict CVD and cancer deaths (59 characters)" + ] + }, + { + "id": 101, + "slug": "intel-mobileodt-cervical-cancer-screening", + "name": "Intel & MobileODT Cervical Cancer Screening", + "headline": "\"Which cancer treatment will be most effective?\"", + "headline_alternatives": [] + }, + { + "id": 102, + "slug": "msk-redefining-cancer-treatment", + "name": "Personalized Medicine-Redefining Cancer Treatment", + "headline": "Predict the effect of Genetic Variants to enable Personalized Medicine", + "headline_alternatives": [ + "1. Predicting Genetic Variants for Personalized Medicine (34 characters)", + "2. Enabling Personalized Medicine Through Genetic Analysis (43 characters)", + "3. Genetic Variant Effects Key to Personalized Care (34 characters) ", + "4. Unlocking Personalized Medicine with Genetic Predictions (43 characters)", + "5. Predicting Variants to Customize Medical Treatments (44 characters)" + ] + }, + { + "id": 103, + "slug": "mubravo", + "name": "Predicting Cancer Diagnosis", + "headline": "Bravo's machine learning competition!", + "headline_alternatives": [ + "1. ML competition hosted by Bravo", + "2. Bravo hosts machine learning contest ", + "3. Bravo challenges ML experts in new contest", + "4. Bravo seeks top ML solutions in competition", + "5. Bravo competition for best machine learning" + ] + }, + { + "id": 104, + "slug": "histopathologic-cancer-detection", + "name": "Histopathologic Cancer Detection", + "headline": "Identify metastatic tissue in histopathologic scans of lymph node sections", + "headline_alternatives": [] + }, + { + "id": 105, + "slug": "tjml1920-decision-trees", + "name": "TJML 2019-20 Breast Cancer Detection Competition", + "headline": "Use a decision tree to identify malignant breast cancer tumors", + "headline_alternatives": [] + }, + { + "id": 106, + "slug": "prostate-cancer-grade-assessment", + "name": "Prostate cANcer graDe Assessment (PANDA) Challenge", + "headline": "Prostate cancer diagnosis using the Gleason grading system", + "headline_alternatives": [ + "1. Gleason grading for prostate cancer diagnosis (34 characters)", + "2. Using Gleason system to grade prostate tumors (43 characters)", + "3. Grading prostate cancers with Gleason system (44 characters) ", + "4. Gleason grading to diagnose prostate cancer (41 characters)", + "5. Diagnose prostate cancer with Gleason grading (45 characters)" + ] + }, + { + "id": 107, + "slug": "breast-cancer", + "name": "Breast Cancer", + "headline": "Use cell nuclei categories to predict breast cancer tumor.", + "headline_alternatives": [] + }, + { + "id": 108, + "slug": "breast-cancer-detection", + "name": "Breast Cancer Detection", + "headline": "breast cancer detection", + "headline_alternatives": [] + }, + { + "id": 109, + "slug": "hrpred", + "name": "Prediction of High Risk Patients", + "headline": "Classification of high and low risk cancer patients", + "headline_alternatives": [] + }, + { + "id": 110, + "slug": "ml4moleng-cancer", + "name": "MIT ML4MolEng-Predicting Cancer Progression", + "headline": "MIT 3.100, 10.402, 20.301 In class ML competition (Spring 2021)", + "headline_alternatives": [ + "1. MIT classes compete in machine learning contest", + "2. MIT students battle in ML competition ", + "3. MIT classes face off in in-class ML contest", + "4. MIT classes hold ML competition during semester ", + "5. MIT students compete in machine learning challenge" + ] + }, + { + "id": 111, + "slug": "uw-madison-gi-tract-image-segmentation", + "name": "UW-Madison GI Tract Image Segmentation", + "headline": "Track healthy organs in medical scans to improve cancer treatment", + "headline_alternatives": [ + "1. Tracking organs in scans to boost cancer care", + "2. Scanning organs to enhance cancer treatment ", + "3. Organ tracking in scans improves cancer therapy", + "4. Monitoring organs via imaging aids cancer treatment", + "5. Organ imaging analysis boosts cancer treatments" + ] + }, + { + "id": 112, + "slug": "rsna-miccai-brain-tumor-radiogenomic-classification", + "name": "RSNA-MICCAI Brain Tumor Radiogenomic Classification", + "headline": "Predict the status of a genetic biomarker important for brain cancer treatment", + "headline_alternatives": [ + "1. BraTS challenge tests brain tumor segmentation methods (56 characters)", + "2. BraTS evaluates glioblastoma segmentation and classification (56 characters)", + "3. BraTS challenge focuses on brain tumor segmentation, prediction (59 characters) ", + "4. BraTS tests MRI-based brain tumor segmentation, MGMT prediction (65 characters)", + "5. BraTS challenge evaluates segmentation, classification of brain tumors (63 characters)" + ] + }, + { + "id": 113, + "slug": "breastcancer", + "name": "Breast Cancer - Beginners ML", + "headline": "Beginners hands-on experience with ML basics", + "headline_alternatives": [ + "1. Learn ML basics hands-on as a beginner (34 characters)", + "2. Hands-on ML for beginners to gain experience (43 characters) ", + "3. Beginners: Get hands-on with ML fundamentals (44 characters)", + "4. Hands-on ML basics for beginners' first experience (51 characters)", + "5. Beginners: Gain hands-on experience with ML basics (54 characters)" + ] + }, + { + "id": 114, + "slug": "ml-olympiad-health-and-education", + "name": "ML Olympiad -Let's Fight lung cancer", + "headline": "Use your ML expertise to help us step another step toward defeating cancer...", + "headline_alternatives": [ + "1. Join the fight against cancer with ML", + "2. Help defeat cancer with your ML skills ", + "3. ML experts: lend your skills to beat cancer", + "4. Can your ML help us defeat cancer?", + "5. Calling all ML experts - help us beat cancer" + ] + }, + { + "id": 115, + "slug": "cs98-22-dl-task1", + "name": "CS98X-22-DL-Task1", + "headline": "This competition is related to Task 1 in coursework-breast cancer classification", + "headline_alternatives": [ + "1. Breast cancer classification challenge via machine learning", + "2. Using AI to classify breast cancer from medical images ", + "3. Applying deep learning to breast cancer diagnosis", + "4. Automated breast cancer detection through image classification", + "5. Machine learning for breast cancer diagnosis from scans" + ] + }, + { + "id": 116, + "slug": "parasitedetection-iiitb2019", + "name": "Parasite detection", + "headline": "Detect if cell image has parasite or is uninfected", + "headline_alternatives": [] + }, + { + "id": 117, + "slug": "hpa-single-cell-image-classification", + "name": "Human Protein Atlas -Single Cell Classification", + "headline": "Find individual human cell differences in microscope images", + "headline_alternatives": [] + }, + { + "id": 118, + "slug": "stem-cell-predcition", + "name": "Stem Cell Predcition", + "headline": "Classify stem and non-stem cells using RNA-seq data", + "headline_alternatives": [] + }, + { + "id": 119, + "slug": "sartorius-cell-instance-segmentation", + "name": "Sartorius - Cell Instance Segmentation", + "headline": "Detect single neuronal cells in microscopy images", + "headline_alternatives": [ + "1. Segment neuronal cells in microscopy images to aid neuroresearch", + "2. Delineate distinct objects in cell images to quantify neurological data ", + "3. Detect and segment neuronal cells to enable neurobiology research", + "4. Identify neuronal cells in images to study neurological disorders", + "5. Segment cell images to measure effects of diseases and treatments" + ] + }, + { + "id": 120, + "slug": "pvelad", + "name": "Photovoltaic cell anomaly detection", + "headline": "Photovoltaic cell anomaly detection", + "headline_alternatives": [ + "1. Hebei U and Beihang U Host AI Competition", + "2. Hebei and Beihang Universities Host AI Challenge ", + "3. AIHebut and NAVE Groups Host AI Competition", + "4. Hebei U and Beihang U Host AI Challenge", + "5. Universities Host AI Competition for Research Groups" + ] + }, + { + "id": 121, + "slug": "blood-mnist", + "name": "Blood-MNIST", + "headline": "Classifying blood cell types using Weights and Biases", + "headline_alternatives": [ + "1. Classify Blood Cells with Weights and Biases (34 characters)", + "2. Using Weights and Biases for Blood Cell Classification (49 characters) ", + "3. Blood Cell Type Classification via Weights and Biases (56 characters)", + "4. Weights and Biases to Classify Blood Cell Types (51 characters) ", + "5. Classifying Blood Cells with W&B Machine Learning (56 characters)" + ] + }, + { + "id": 122, + "slug": "insilicomolhack", + "name": "MolHack", + "headline": "Apply deep learning to speedup drug validation", + "headline_alternatives": [ + "1. Deep learning to accelerate drug validation", + "2. Using deep learning for faster drug validation ", + "3. Applying deep learning to hasten drug validation", + "4. Deep learning speeds up drug validation process", + "5. Leveraging deep learning to expedite drug validation" + ] + }, + { + "id": 123, + "slug": "codata2019challenge", + "name": "Cell Response Classification", + "headline": "From recorded timeseries of many cells in a well, predict which drug treatme...", + "headline_alternatives": [] + }, + { + "id": 124, + "slug": "drug-solubility-challenge", + "name": "Drug solubility challenge", + "headline": "Crucial Role of Solubility in Drug Formulation for Optimal Efficacy", + "headline_alternatives": [ + "1. Improving drug solubility for optimal pharmacological response (54 characters)", + "2. Enhancing solubility to achieve desired drug concentrations (56 characters) ", + "3. Optimizing drug solubility for anticipated pharmacological effects (63 characters)", + "4. Solubility key to reaching target drug concentrations (49 characters)", + "5. Tuning solubility to get right drug levels for effects (56 characters)" + ] + }, + { + "id": 125, + "slug": "kinase-inhibition-challenge", + "name": "Kinase inhibition challenge", + "headline": "Unlocking the Therapeutic Potential of Protein Kinases: Big Data Insights", + "headline_alternatives": [] + }, + { + "id": 126, + "slug": "ai-drug-discovery", + "name": "AI Drug Discovery Workshop and Coding Challenge", + "headline": "Fostering Core AI Programming Proficiency for Drug Discovery Advancements", + "headline_alternatives": [ + "1. Honing AI skills for drug discovery (24 characters)", + "2. Building AI programming for drug R&D (32 characters)", + "3. Developing AI abilities for pharma innovation (39 characters) ", + "4. Advancing AI competencies in pharmaceuticals (43 characters)", + "5. Mastering AI coding fundamentals for new drugs (47 characters)" + ] + }, + { + "id": 127, + "slug": "protein-compound-affinity", + "name": "Structure-free protein-ligand affinity prediction - Task 1 Fitting", + "headline": "Developing new AI models for drug discovery, main portal (Task-1 fitting)", + "headline_alternatives": [ + "1. New AI models to advance drug discovery (34 characters)", + "2. Developing AI to accelerate pharmaceutical innovations (51 characters) ", + "3. Creating AI systems for faster drug development (44 characters)", + "4. AI models to enhance drug discovery process (41 characters)", + "5. Leveraging AI to discover new medicines faster (44 characters)" + ] + }, + { + "id": 128, + "slug": "cisc873-dm-f21-a5", + "name": "CISC873-DM-F21-A5", + "headline": "Anti-Cancer Drug Activity Prediction", + "headline_alternatives": [ + "1. Predicting Anti-Cancer Drug Potency with AI (34 characters)", + "2. AI to Forecast Anti-Cancer Drug Efficacy (32 characters) ", + "3. Using AI to Predict Anti-Cancer Drug Activity (40 characters)", + "4. AI Model Predicts Best Anti-Cancer Drugs (31 characters) ", + "5. AI Helps Identify Most Effective Anti-Cancer Drugs (45 characters)" + ] + }, + { + "id": 129, + "slug": "pro-lig-aff-task2-mse", + "name": "Structure-free protein-ligand affinity prediction - Task 2 Fitting", + "headline": "Developing new AI models for drug discovery (Task-2 fitting)", + "headline_alternatives": [] + }, + { + "id": 130, + "slug": "pro-lig-aff-task1-pearsonr", + "name": "Structure-free protein-ligand affinity prediction - Task 1 Ranking", + "headline": "Developing new AI models for drug discovery (Task-1 ranking)", + "headline_alternatives": [ + "1. New AI models to aid drug discovery (21 characters)", + "2. Applying AI to accelerate drug discovery (34 characters) ", + "3. Developing AI models to rank drug candidates (41 characters)", + "4. Using AI for faster, better drug discovery (38 characters)", + "5. AI models to improve drug candidate identification (49 characters)" + ] + }, + { + "id": 131, + "slug": "pro-lig-aff-task2-pearsonr", + "name": "Structure-free protein-ligand affinity prediction - Task 2 Ranking", + "headline": "Developing new AI models for drug discovery (Task-2 ranking)", + "headline_alternatives": [ + "1. Creating AI to Rank Drug Candidates (14 chars)", + "2. AI Models to Prioritize Drug Leads (24 chars)", + "3. AI for Ranking Potential New Drugs (25 chars) ", + "4. Develop AI to Identify Top Drug Candidates (33 chars)", + "5. Building AI to Rank Drug Discovery Results (34 chars)" + ] + }, + { + "id": 132, + "slug": "pro-lig-aff-task3-spearmanr", + "name": "Structure-free protein-ligand affinity prediction - Task 3 Ranking", + "headline": "Developing new AI models for drug discovery (Task-3 ranking)", + "headline_alternatives": [] + }, + { + "id": 133, + "slug": "hhp", + "name": "Heritage Health Prize", + "headline": "Identify patients who will be admitted to a hospital within the next year us...", + "headline_alternatives": [] + }, + { + "id": 134, + "slug": "pf2012", + "name": "Practice Fusion Analyze This! 2012 - Prediction Challenge", + "headline": "Delve into Electronic Health Records: Propose Innovative Predictive Modeling...", + "headline_alternatives": [ + "1. Predict disease risks from electronic health records (53 characters)", + "2. Mine electronic records for impactful modeling ideas (56 characters) ", + "3. Discover predictive signals in patient data (44 characters)", + "4. Electronic health records: a trove for predictive modeling (56 characters)", + "5. Ideate modeling competitions using patient records (49 characters)" + ] + }, + { + "id": 135, + "slug": "pf2012-at", + "name": "Practice Fusion Analyze This! 2012 - Open Challenge", + "headline": "Delve into Electronic Health Records: Propose Innovative Predictive Modeling...", + "headline_alternatives": [] + }, + { + "id": 136, + "slug": "seizure-detection", + "name": "UPenn and Mayo Clinic's Seizure Detection Challenge", + "headline": "Detect seizures in intracranial EEG recordings", + "headline_alternatives": [ + "1. Detecting seizures from brain recordings (34 characters)", + "2. Identifying seizures in EEG data (32 characters) ", + "3. Seizure detection using intracranial EEG (34 characters)", + "4. Finding seizures in brain activity recordings (39 characters)", + "5. Automatically detect seizures from EEG (31 characters)" + ] + }, + { + "id": 137, + "slug": "seizure-prediction", + "name": "American Epilepsy Society Seizure Prediction Challenge", + "headline": "Predict seizures in intracranial EEG recordings", + "headline_alternatives": [] + }, + { + "id": 138, + "slug": "deephealth-1", + "name": "Deep Health - alcohol", + "headline": "Find Correlations and patterns with Medical data", + "headline_alternatives": [ + "1. Uncover Insights in Medical Data", + "2. Discover Patterns in Health Records ", + "3. Medical Data Analysis to Find Links", + "4. Seeking Correlations in Patient Info", + "5. Analyze Medical Data for Connections" + ] + }, + { + "id": 139, + "slug": "deep-health-3", + "name": "Deep Health - Diabetes 2", + "headline": "Deep Health Hackathon: Predicting Future Diabetes Occurrences Challenge", + "headline_alternatives": [] + }, + { + "id": 140, + "slug": "d012554-2021", + "name": "D012554 - 2021", + "headline": "Classify the health of a fetus using CTG data", + "headline_alternatives": [ + "1. Predict fetal health from CTG readings (34 characters)", + "2. Classify fetal health using CTG data (32 characters) ", + "3. Assess fetal wellbeing with CTG analysis (38 characters)", + "4. Determine fetal condition from cardiotocography (56 characters)", + "5. Categorize fetus health through CTG data (39 characters)" + ] + }, + { + "id": 141, + "slug": "idao-2022-bootcamp-insomnia", + "name": "IDAO 2022. ML Bootcamp - Insomnia", + "headline": "Predict sleep disorder on given human health data", + "headline_alternatives": [ + "1. Predicting sleep disorders from health data (34 characters)", + "2. Using health data to forecast sleep disorders (43 characters)", + "3. Can health info predict sleep problems? (34 characters) ", + "4. Sleep disorder prediction via health analytics (43 characters)", + "5. Forecasting sleep disorders with human data (44 characters)" + ] + }, + { + "id": 142, + "slug": "tweet-mental-health-classification", + "name": "Tweet Mental Health Classification", + "headline": "Build Models to classify tweets to determine mental health", + "headline_alternatives": [ + "1. Build Models to Classify Tweets for Mental Health (56 characters)", + "2. Classifying Tweets to Determine Mental Health (49 characters) ", + "3. Modeling Tweets to Assess Mental Health Status (51 characters)", + "4. Develop Models for Mental Health Detection via Tweets (63 characters)", + "5. Using Tweet Classification to Gauge Mental Health (59 characters)" + ] + }, + { + "id": 143, + "slug": "ml-olympiad-good-health-and-well-being", + "name": "ML Olympiad - GOOD HEALTH AND WELL BEING", + "headline": "Use your ML expertise to classify if a patient has heart disease or not", + "headline_alternatives": [ + "1. ML to Diagnose Heart Disease (25 characters)", + "2. AI for Heart Disease Detection (32 characters) ", + "3. Classify Heart Disease with ML (34 characters)", + "4. Detecting Heart Disease with AI (38 characters)", + "5. ML Model Predicts Heart Disease (38 characters)" + ] + }, + { + "id": 144, + "slug": "rsna-breast-cancer-detection", + "name": "RSNA Screening Mammography Breast Cancer Detection", + "headline": "Find breast cancers in screening mammograms", + "headline_alternatives": [] + }, + { + "id": 145, + "slug": "biocreative-vii-text-mining-drug-and-chemical-protein-interactions-drugprot", + "name": "BioCreative VII: Text mining drug and chemical-protein interactions (DrugProt)", + "headline": "Develop systems to extract drug-gene relations from text", + "headline_alternatives": [ + "1. Develop systems to extract drug-gene relations from text (79 characters)", + "2. Automatically detect relations between drugs and proteins in text (78 characters) ", + "3. Build models to identify drug-protein interactions in literature (77 characters)", + "4. Extract and characterize drug-gene relations from biomedical text (78 characters)", + "5. Promote extraction of drug-protein relations to enable drug discovery (79 characters)" + ] + }, + { + "id": 146, + "slug": "extended-literature-ai-for-drug-induced-liver-injury", + "name": "Extended Literature AI for Drug Induced Liver Injury", + "headline": "Develop ML tools to analyze drug texts for liver injury data", + "headline_alternatives": [] + }, + { + "id": 147, + "slug": "anti-microbial-resistance-forensics", + "name": "Anti-Microbial Resistance Forensics", + "headline": "Classifying Bacteriophages to Understand Microbial Evolution", + "headline_alternatives": [ + "1. Develop new methods to classify and analyze bacteriophages' role in AMR spread (78 characters)", + "2. Understand how bacteriophages enable microbial evolution and antibiotic resistance (77 characters) ", + "3. Study correlation between phages and AMR to assess treatment potential (69 characters)", + "4. Improve phage classification amidst contradictory antibiotic replacement role (79 characters) ", + "5. Apply advanced algorithms to precisely describe bacteriophage capabilities (69 characters)" + ] + }, + { + "id": 148, + "slug": "disease-maps-to-modelling-covid-19", + "name": "Disease Maps to Modelling COVID-19", + "headline": "Disease Maps COVID-19 Challenge: Enhancing Drug Repurposing with Omic Data", + "headline_alternatives": [ + "1. Model COVID-19 mechanisms to find drug repurposing candidates (79 characters)", + "2. Leverage expert maps and data to expand COVID-19 knowledge (76 characters) ", + "3. Combine maps and data to understand COVID-19 and repurpose drugs (79 characters)", + "4. Use detailed maps to model COVID-19 and suggest drug repurposing (78 characters)", + "5. Expand biological knowledge of COVID-19 infection via modeling (76 characters)" + ] + }, + { + "id": 149, + "slug": "crowdsourced-evaluation-of-inchi-based-tautomer-identification", + "name": "Crowdsourced Evaluation of InChI-based Tautomer Identification", + "headline": "Crowdsourced Evaluation of InChI-Based Tautomer Identification Challenge", + "headline_alternatives": [] + }, + { + "id": 150, + "slug": "nctr-indel-calling-from-oncopanel-sequencing-challenge-phase-2", + "name": "NCTR Indel Calling from Oncopanel Sequencing Challenge Phase 2", + "headline": "NCTR Indel Calling from Oncopanel Sequencing Data Challenge", + "headline_alternatives": [ + "1. Develop standards for oncopanel sequencing quality control (77 characters)", + "2. Benchmark oncopanels with reference sample from FDA's SEQC2 project (79 characters) ", + "3. Assess analytical performance of oncopanels using SEQC2 reference sample (76 characters)", + "4. Establish quality metrics for clinical oncopanel sequencing (69 characters)", + "5. Standardize analysis protocols for oncopanel sequencing data (61 characters)" + ] + }, + { + "id": 151, + "slug": "nctr-indel-calling-from-oncopanel-sequencing-data-challenge-phase-1", + "name": "NCTR Indel Calling from Oncopanel Sequencing Data Challenge Phase 1", + "headline": "NCTR Indel Calling from Oncopanel Sequencing Data Challenge", + "headline_alternatives": [ + "1. Develop standards for oncopanel sequencing quality control (69 characters)", + "2. Benchmark oncopanels with reference sample from FDA's SEQC2 project (77 characters) ", + "3. Assess analytical performance of oncopanels using SEQC2 reference sample (76 characters)", + "4. Establish quality metrics for oncopanel sequencing in precision oncology (77 characters)", + "5. Create protocols for fit-for-purpose use of oncopanel NGS data (69 characters)" + ] + }, + { + "id": 152, + "slug": "vha-innovation-ecosystem-and-precisionfda-covid-19-risk-factor-modeling-challenge-phase-2", + "name": "VHA Innovation Ecosystem and precisionFDA COVID-19 Risk Factor Modeling Challenge Phase 2", + "headline": "The focus of Phase 2 was to validate the top performing models on two additi...", + "headline_alternatives": [] + }, + { + "id": 153, + "slug": "tumor-mutational-burden-tmb-challenge-phase-2", + "name": "Tumor Mutational Burden (TMB) Challenge Phase 2", + "headline": "The goal of the Friends of Cancer Research and precisionFDA Tumor Mutational...", + "headline_alternatives": [] + }, + { + "id": 154, + "slug": "predicting-gene-expression-using-millions-of-random-promoter-sequences", + "name": "Predicting Gene Expression Using Millions of Random Promoter Sequences", + "headline": "Decoding gene expression regulation to understand disease.", + "headline_alternatives": [] + }, + { + "id": 155, + "slug": "brats-2023", + "name": "BraTS 2023", + "headline": "Benchmarking brain tumor segmentation with expanded dataset.", + "headline_alternatives": [ + "1. BraTS challenge focuses on benchmarking brain tumor segmentation with expanded dataset. (79 characters)", + "2. BraTS challenge expands brain tumor dataset to advance segmentation. (56 characters) ", + "3. BraTS seeks to advance brain tumor segmentation with larger dataset. (59 characters)", + "4. BraTS challenge grows dataset to boost brain tumor segmentation. (59 characters)", + "5. BraTS challenge expands dataset to advance brain tumor delineation. (63 characters)" + ] + }, + { + "id": 156, + "slug": "cagi7", + "name": "CAGI7", + "headline": "The seventh round of CAGI.", + "headline_alternatives": [] + }, + { + "id": 157, + "slug": "casp15", + "name": "CASP15", + "headline": "Establish the state-of-art in modeling proteins and protein complexes.", + "headline_alternatives": [ + "1. CASP15 updates categories to advance deep learning for protein structures (76 characters)", + "2. CASP15 strengthens protein modeling with new categories, deep learning focus (79 characters) ", + "3. CASP15 evolves protein modeling categories to boost deep learning impact (76 characters)", + "4. CASP15 adds categories to drive deep learning advances in protein structures (79 characters)", + "5. CASP15 shifts categories to maximize deep learning insights for proteins (77 characters)" + ] + }, + { + "id": 158, + "slug": "synthrad2023", + "name": "SynthRAD2023", + "headline": "Synthesizing computed tomography for radiotherapy.", + "headline_alternatives": [ + "1. Platform to evaluate and compare sCT generation methods (79 characters)", + "2. Public benchmark for sCT generation algorithms (56 characters) ", + "3. First platform to evaluate sCT generation methods (59 characters)", + "4. Challenge to compare sCT generation algorithms (49 characters)", + "5. Public metrics to evaluate sCT generation methods (59 characters)" + ] + }, + { + "id": 159, + "slug": "synthetic-data-for-instrument-segmentation-in-surgery-syn-iss", + "name": "Synthetic Data for Instrument Segmentation in Surgery (Syn-ISS)", + "headline": "Challenging Machine Learning in Surgical Instrument Segmentation with Synthe...", + "headline_alternatives": [] + }, + { + "id": 160, + "slug": "pitvis", + "name": "PitVis", + "headline": "Surgical workflow and instrument recognition in endonasal surgery.", + "headline_alternatives": [ + "1. Guiding surgeons to remove pituitary tumors in tight spaces", + "2. Assisting surgeons with computer guidance for pituitary surgery ", + "3. Improving outcomes in complex pituitary tumor removal", + "4. Computer-assisted intervention for challenging pituitary surgeries", + "5. Enhancing surgical technique for pituitary tumor treatment" + ] + }, + { + "id": 161, + "slug": "mvseg2023", + "name": "MVSEG2023", + "headline": "Automatically segment mitral valve leaflets from single frame 3D trans-esoph...", + "headline_alternatives": [] + }, + { + "id": 162, + "slug": "crossmoda23", + "name": "crossMoDA23", + "headline": "This challenge proposes is the third edition of the first medical imaging be...", + "headline_alternatives": [] + }, + { + "id": 163, + "slug": "icr-identify-age-related-conditions", + "name": "ICR - Identifying Age-Related Conditions", + "headline": "Use Machine Learning to detect conditions with measurements of anonymous cha...", + "headline_alternatives": [] + }, + { + "id": 164, + "slug": "cafa-5-protein-function-prediction", + "name": "CAFA 5: Protein Function Prediction", + "headline": "Predict the biological function of a protein.", + "headline_alternatives": [] + }, + { + "id": 165, + "slug": "rsna-2023-abdominal-trauma-detection", + "name": "RSNA 2023 Abdominal Trauma Detection", + "headline": "Detect and classify traumatic abdominal injuries.", + "headline_alternatives": [] + }, + { + "id": 166, + "slug": "hubmap-hacking-the-human-vasculature", + "name": "HuBMAP: Hacking the Human Vasculature", + "headline": "Segment instances of microvascular structures from healthy human kidney tiss...", + "headline_alternatives": [ + "1. Segment microvascular structures in kidney histology images (56 characters)", + "2. Model to identify capillaries, arterioles, venules in tissues (56 characters)", + "3. Automate segmentation of blood vessels in kidney slides (51 characters) ", + "4. Improve understanding of microvasculature in tissues (51 characters)", + "5. Segment capillaries, arterioles, venules in kidney images (59 characters)" + ] + }, + { + "id": 167, + "slug": "amp-parkinsons-disease-progression-prediction", + "name": "AMP(R)-Parkinson's Disease Progression Prediction", + "headline": "Use protein and peptide data measurements from Parkinson's Disease patients ...", + "headline_alternatives": [] + }, + { + "id": 168, + "slug": "open-problems-multimodal", + "name": "Open Problems -Multimodal Single-Cell Integration", + "headline": "Predict how DNA, RNA & protein measurements co-vary in single cells.", + "headline_alternatives": [] + }, + { + "id": 169, + "slug": "multi-atlas-labeling-beyond-the-cranial-vault", + "name": "Multi-Atlas Labeling Beyond the Cranial Vault", + "headline": "Innovative Multi-Atlas Labeling for Soft Tissue Segmentation on Clinical CT", + "headline_alternatives": [] + }, + { + "id": 170, + "slug": "hubmap-organ-segmentation", + "name": "HuBMAP + HPA: Hacking the Human Body", + "headline": "Segment multi-organ functional tissue units.", + "headline_alternatives": [ + "1. Segment functional tissue units in human organs to understand cell relationships (79 characters)", + "2. Identify tissue units across organs to reveal cell organization insights (79 characters)", + "3. Segment tissue images to map cell relationships and advance research (78 characters) ", + "4. Map functional tissue units across organs to unlock cell organization (77 characters)", + "5. Segment tissue images to construct atlas revealing cell relationships (78 characters)" + ] + }, + { + "id": 171, + "slug": "hubmap-kidney-segmentation", + "name": "HuBMAP: Hacking the Kidney", + "headline": "Identify glomeruli in human kidney tissue images.", + "headline_alternatives": [ + "1. Map kidney at single cell level, detect functional tissue units", + "2. Identify functional tissue units in human kidney to understand cell relationships ", + "3. Build tools to map kidney and identify cell blocks affecting health", + "4. Detect functional tissue units in kidney to advance cell atlas ", + "5. Identify cell blocks in kidney images to understand impact on human health" + ] + }, + { + "id": 172, + "slug": "ventilator-pressure-prediction", + "name": "Google Brain: Ventilator Pressure Prediction", + "headline": "Simulate a ventilator connected to a sedated patient's lung.", + "headline_alternatives": [] + }, + { + "id": 173, + "slug": "stanford-covid-vaccine", + "name": "OpenVaccine - COVID-19 mRNA Vaccine Degradation Prediction", + "headline": "Urgent need to bring the COVID-19 vaccine to mass production.", + "headline_alternatives": [ + "1. Predict RNA degradation rates to aid COVID vaccine design (79 characters)", + "2. Model RNA degradation for COVID vaccine mRNAs (52 characters) ", + "3. Leverage data science for RNA degradation prediction (56 characters)", + "4. Develop models of RNA degradation rates (34 characters)", + "5. Predict mRNA vaccine degradation with machine learning (56 characters)" + ] + }, + { + "id": 174, + "slug": "openvaccine", + "name": "OpenVaccine", + "headline": "A research initiative aimed at developing innovative design principles for R...", + "headline_alternatives": [ + "1. Seeking more stable mRNA vaccines to enable worldwide access", + "2. Can you design a more stable mRNA vaccine? ", + "3. Help create fridge-stable mRNA vaccines for global use", + "4. Improve mRNA vaccine stability for worldwide immunization", + "5. Enhance mRNA vaccines: 2x-10x more stable formulations wanted" + ] + }, + { + "id": 175, + "slug": "opentb", + "name": "OpenTB", + "headline": "We aim to gain fundamental insights into the ribosome's RNA sequence-folding.", + "headline_alternatives": [] + }, + { + "id": 176, + "slug": "opencrispr", + "name": "OpenCRISPR", + "headline": "Can you improve the algorithm that classifies drugs based on their biologica...", + "headline_alternatives": [ + "1. Develop small molecule switches to control CRISPR gene editing (76 characters)", + "2. Create on/off switches for CRISPR to enable safe gene editing (77 characters) ", + "3. Enable turning CRISPR on/off with small molecules for safe use (76 characters)", + "4. Design small molecule switches to control CRISPR activity (63 characters)", + "5. Develop safe, controllable CRISPR gene editing using small molecules (78 characters)" + ] + }, + { + "id": 177, + "slug": "openknot", + "name": "OpenKnot", + "headline": "CellSignal - Disentangling biological signal from experimental noise in cell...", + "headline_alternatives": [ + "1. Understanding folding pathways and dynamics of RNA pseudoknots (76 characters)", + "2. Elucidating structure and function of crucial RNA pseudoknots (59 characters) ", + "3. Investigating role of RNA pseudoknots in gene regulation (52 characters)", + "4. Analyzing viral replication mechanisms of RNA pseudoknots (56 characters)", + "5. Exploring enzymatic activity and catalysis by RNA pseudoknots (59 characters)" + ] + }, + { + "id": 178, + "slug": "openaso", + "name": "OpenASO", + "headline": "Event detection from wearable sensor data.", + "headline_alternatives": [] + }, + { + "id": 179, + "slug": "openribosome", + "name": "OpenRibosome", + "headline": "AI competition seeks cancer diagnosis and treatment solutions.", + "headline_alternatives": [] + }, + { + "id": 180, + "slug": "lish-moa", + "name": "Mechanisms of Action (MoA) Prediction", + "headline": "Segmenting Cerebral Arteries from 3D Angiography Images.", + "headline_alternatives": [] + }, + { + "id": 181, + "slug": "recursion-cellular-image-classification", + "name": "Recursion Cellular Image Classification", + "headline": "Challenge compares Circle of Willis classification methods.", + "headline_alternatives": [] + }, + { + "id": 182, + "slug": "tlvmc-parkinsons-freezing-gait-prediction", + "name": "Parkinson's Freezing of Gait Prediction", + "headline": "The US Food and Drug Administration (FDA) calls on stakeholders, including t...", + "headline_alternatives": [ + "1. Detect freezing of gait in Parkinson's using wearable sensor data (77 characters)", + "2. Machine learning to detect freezing of gait from sensor data (63 characters) ", + "3. Improve understanding of freezing in Parkinson's with ML (63 characters)", + "4. ML model to detect freezing episodes in Parkinson's (63 characters)", + "5. Wearable sensors to monitor freezing of gait in Parkinson's (79 characters)" + ] + }, + { + "id": 183, + "slug": "chaimeleon", + "name": "CHAIMELEON Open Challenges", + "headline": "The Veterans Health Administration Innovation Ecosystem, the Digital Health ...", + "headline_alternatives": [ + "1. CHAIMELEON challenges train AI to answer cancer questions (56 characters)", + "2. Competition refines AI for cancer diagnosis and treatment (54 characters) ", + "3. CHAIMELEON: AI collaboration to advance cancer care (56 characters)", + "4. Developing trustworthy AI for cancer prognosis and outcomes (66 characters)", + "5. Advancing cancer AI - CHAIMELEON open competition (49 characters)" + ] + }, + { + "id": 184, + "slug": "topcow23", + "name": "Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA", + "headline": "Predicting High Risk Breast Cancer - a Nightingale OS & AHLI data challenge.", + "headline_alternatives": [] + }, + { + "id": 185, + "slug": "circle-of-willis-intracranial-artery-classification-and-quantification-challenge-2023", + "name": "Circle of Willis Intracranial Artery Classification and Quantification Challenge 2023", + "headline": "Predicting High Risk Breast Cancer - a Nightingale OS & AHLI data challenge.", + "headline_alternatives": [ + "1. Challenge compares methods for CoW classification and quantification (77 characters)", + "2. CoW challenge: Classify configuration, quantify diameters and angles (79 characters)", + "3. CoW challenge: Compare methods for classification and measurement (65 characters) ", + "4. Challenge to evaluate CoW configuration classification and measurement (79 characters)", + "5. Comparing methods for CoW configuration classification and measurement (79 characters)" + ] + }, + { + "id": 186, + "slug": "making-sense-of-electronic-health-record-ehr-race-and-ethnicity-data", + "name": "Making Sense of Electronic Health Record (EHR) Race and Ethnicity Data", + "headline": "Predicting the connectivity and properties of in-silico networks.", + "headline_alternatives": [] + }, + { + "id": 187, + "slug": "the-veterans-cardiac-health-and-ai-model-predictions-v-champs", + "name": "The Veterans Cardiac Health and AI Model Predictions (V-CHAMPS)", + "headline": "The goal of the in silico challenges is the reverse engineering of gene netw...", + "headline_alternatives": [] + }, + { + "id": 188, + "slug": "predicting-high-risk-breast-cancer-phase-1", + "name": "Predicting High Risk Breast Cancer - Phase 1", + "headline": "The goal of the in silico network challenge is to reverse engineer gene regu...", + "headline_alternatives": [ + "1. Developing algorithms to predict harmful breast cancers, reduce overtreatment (76 characters)", + "2. Reducing invasive breast cancer procedures via AI analysis of biopsies (73 characters)", + "3. Algorithms to identify harmful breast cancers, limit unnecessary treatment (78 characters) ", + "4. Using AI to analyze biopsies, identify aggressive breast cancers (63 characters)", + "5. Harnessing AI to reduce invasive procedures for harmless breast cancers (77 characters)" + ] + }, + { + "id": 189, + "slug": "predicting-high-risk-breast-cancer-phase-2", + "name": "Predicting High Risk Breast Cancer - Phase 2", + "headline": "The goal of this Network Inference Challenge is to reverse engineer gene reg...", + "headline_alternatives": [ + "1. AI to identify harmful breast cancers, reduce unnecessary procedures (79 characters)", + "2. Algorithms to predict metastatic potential, limit overtreatment (78 characters) ", + "3. Using AI on biopsies to distinguish harmful vs harmless cancers (76 characters)", + "4. Reducing invasive breast cancer procedures via AI analysis (71 characters) ", + "5. Can AI identify truly dangerous breast cancers? (43 characters)" + ] + }, + { + "id": 190, + "slug": "dream-2-in-silico-network-inference", + "name": "DREAM 2 - In Silico Network Inference", + "headline": "Identify dates in clinical notes.", + "headline_alternatives": [] + }, + { + "id": 191, + "slug": "dream-3-in-silico-network-challenge", + "name": "DREAM 3 - In Silico Network Challenge", + "headline": "Identify person names in clinical notes.", + "headline_alternatives": [ + "1. Reverse engineer gene networks from steady state & time series data (76 characters)", + "2. Predict directed unsigned network topology from in silico gene datasets (79 characters) ", + "3. Reconstruct gene networks through reverse engineering of in silico data (77 characters)", + "4. Uncover gene network topology from steady state & time series gene data (79 characters)", + "5. Infer directed gene network models from simulated steady state & time series data (79 characters)" + ] + }, + { + "id": 192, + "slug": "dream-4-in-silico-network-challenge", + "name": "DREAM 4 - In Silico Network Challenge", + "headline": "Identify location information in clinical notes.", + "headline_alternatives": [ + "1. Reverse engineer gene networks from simulated data (34 characters)", + "2. Infer gene regulation networks from in silico data (43 characters) ", + "3. Reconstruct gene networks from steady-state and time-series data (59 characters)", + "4. Uncover network structure from simulated gene expression data (59 characters)", + "5. Predict network response to novel perturbations from provided data (65 characters)" + ] + }, + { + "id": 193, + "slug": "dream-5-network-inference-challenge", + "name": "DREAM 5 - Network Inference Challenge", + "headline": "Identify contact information in clinical notes.", + "headline_alternatives": [] + }, + { + "id": 194, + "slug": "nlp-sandbox-date-annotation", + "name": "NLP Sandbox Date Annotation", + "headline": "Identify identifiers in clinical notes.", + "headline_alternatives": [ + "1. Extract dates from clinical notes using NLP", + "2. Identify dates in clinical notes with a date annotator ", + "3. Build a date extractor for clinical notes", + "4. Develop an NLP model to find dates in notes", + "5. Annotate dates in clinical text using Sandbox" + ] + }, + { + "id": 195, + "slug": "nlp-sandbox-person-name-annotation", + "name": "NLP Sandbox Person Name Annotation", + "headline": "Predict BCL6 transcriptomic targets from biological data.", + "headline_alternatives": [ + "1. Predict person names in clinical notes (22 characters)", + "2. Annotate person names in clinical text (27 characters) ", + "3. Identify person names from clinical notes (32 characters)", + "4. Extract person names from clinical documents (37 characters)", + "5. Find and label person names in medical records (44 characters)" + ] + }, + { + "id": 196, + "slug": "nlp-sandbox-location-annotation", + "name": "NLP Sandbox Location Annotation", + "headline": "Predict a protein-protein interaction network of 47 proteins.", + "headline_alternatives": [ + "1. Predict locations in clinical notes (16 characters)", + "2. Annotate locations from clinical notes (24 characters) ", + "3. Extract locations from clinical text (23 characters)", + "4. Identify locations mentioned in notes (26 characters)", + "5. Generate location annotations for notes (34 characters)" + ] + }, + { + "id": 197, + "slug": "nlp-sandbox-contact-annotation", + "name": "NLP Sandbox Contact Annotation", + "headline": "Reconstruct genome-scale networks from microarray data.", + "headline_alternatives": [ + "1. Predict contact annotations in clinical notes (34 characters)", + "2. Annotate contacts found in clinical notes (38 characters) ", + "3. Identify contacts in clinical notes with NLP (43 characters)", + "4. Contact annotation of clinical notes using NLP (50 characters) ", + "5. Predict contacts in clinical notes with an NLP annotator (56 characters)" + ] + }, + { + "id": 198, + "slug": "nlp-sandbox-id-annotation", + "name": "NLP Sandbox ID Annotation", + "headline": "Inferring five-gene networks from synthetic data.", + "headline_alternatives": [ + "1. Predict patient IDs in clinical notes (34 characters)", + "2. Annotate clinical notes with patient IDs (39 characters) ", + "3. Identify patient IDs in unstructured clinical text (45 characters)", + "4. Extract patient identifiers from clinical narratives (56 characters)", + "5. Automatically tag patient IDs in doctor's notes (56 characters)" + ] + }, + { + "id": 199, + "slug": "dream-2-bcl6-transcriptomic-target-prediction", + "name": "DREAM 2 - BCL6 Transcriptomic Target Prediction", + "headline": "Inferring signaling cascade dynamics from flow cytometry data.", + "headline_alternatives": [] + }, + { + "id": 200, + "slug": "dream-2-protein-protein-interaction-network-inference", + "name": "DREAM 2 - Protein-Protein Interaction Network Inference", + "headline": "Predicting gene expression from gene datasets.", + "headline_alternatives": [] + }, + { + "id": 201, + "slug": "dream-2-genome-scale-network-inference", + "name": "DREAM 2 - Genome-Scale Network Inference", + "headline": "Cell-type specific high-throughput experimental data.", + "headline_alternatives": [] + }, + { + "id": 202, + "slug": "dream-2-synthetic-five-gene-network-inference", + "name": "DREAM 2 - Synthetic Five-Gene Network Inference", + "headline": "Predict missing protein concentrations from a large corpus of measurements.", + "headline_alternatives": [] + }, + { + "id": 203, + "slug": "dream-3-signaling-cascade-identification", + "name": "DREAM 3 - Signaling Cascade Identification", + "headline": "Predict binding specificity of peptide-antibody interactions.", + "headline_alternatives": [ + "1. Inferring signaling cascade dynamics from flow cytometry data (76 characters)", + "2. Analyzing signaling cascade topology with incomplete data (77 characters)", + "3. Exploring signaling cascade interactions with flow cytometry (77 characters) ", + "4. Inferring signaling cascade dynamics and topology (69 characters)", + "5. Analyzing signaling cascade properties from flow data (79 characters)" + ] + }, + { + "id": 204, + "slug": "dream-3-gene-expression-prediction", + "name": "DREAM 3 - Gene Expression Prediction", + "headline": "Predict binding intensities for transcription factors from motifs.", + "headline_alternatives": [] + }, + { + "id": 205, + "slug": "dream-4-predictive-signaling-network-modelling", + "name": "DREAM 4 - Predictive Signaling Network Modelling", + "headline": "Predict the binding specificity of peptide-antibody interactions.", + "headline_alternatives": [ + "1. Create cell-type model of signaling using HepG2 data", + "2. Leverage prior knowledge to build HepG2 signaling model ", + "3. Build interpretable HepG2 signaling network consistent with data", + "4. Can existing signaling knowledge explain HepG2 protein activity?", + "5. Evaluate agreement between signaling knowledge and HepG2 data" + ] + }, + { + "id": 206, + "slug": "dream-3-signaling-response-prediction", + "name": "DREAM 3 - Signaling Response Prediction", + "headline": "Predict gene expression levels from promoter sequences in eukaryotes.", + "headline_alternatives": [ + "1. Predicting cell signaling response in liver cells with phospho-protein and cytokine data (79 characters)", + "2. Modeling phospho-protein and cytokine dynamics in normal and cancer liver cells (77 characters) ", + "3. Analyzing stimulation effects on signaling in hepatocytes using multi-omics data (79 characters)", + "4. Mapping signaling networks in liver cells using phospho-protein and cytokine data (76 characters)", + "5. Integrating intracellular and extracellular data to understand liver cell signaling (79 characters)" + ] + }, + { + "id": 207, + "slug": "dream-4-peptide-recognition-domain-prd-specificity-prediction", + "name": "DREAM 4 - Peptide Recognition Domain (PRD) Specificity Prediction", + "headline": "Predict disease phenotypes and infer gene networks from systems genetics data.", + "headline_alternatives": [] + }, + { + "id": 208, + "slug": "dream-5-transcription-factor-dna-motif-recognition-challenge", + "name": "DREAM 5 - Transcription-Factor, DNA-Motif Recognition Challenge", + "headline": "Challenge to estimate model parameters.", + "headline_alternatives": [ + "1. Predict signal intensities for transcription factors binding DNA", + "2. Model transcription factor binding to genomic DNA sequences", + "3. Infer transcription factor binding motifs from genomic sequences", + "4. Quantify transcription factor binding specificities", + "5. Estimate transcription factor affinities from sequence motifs" + ] + }, + { + "id": 209, + "slug": "dream-5-epitope-antibody-recognition-ear-challenge", + "name": "DREAM 5 - Epitope-Antibody Recognition (EAR) Challenge", + "headline": "The goal of this challenge is to diagnose Acute Myeloid Leukemia from patien...", + "headline_alternatives": [] + }, + { + "id": 210, + "slug": "dream-gene-expression-prediction-challenge", + "name": "DREAM Gene Expression Prediction Challenge", + "headline": "Assess accuracy of mRNA-seq alternative splicing reconstruction.", + "headline_alternatives": [] + }, + { + "id": 211, + "slug": "dream-5-systems-genetics-challenge", + "name": "DREAM 5 - Systems Genetics Challenge", + "headline": "A machine learning contest for gene network inference from single-cell pertu...", + "headline_alternatives": [] + }, + { + "id": 212, + "slug": "dream-6-estimation-of-model-parameters-challenge", + "name": "DREAM 6 - Estimation of Model Parameters Challenge", + "headline": "The challenge related to computational geometry and topology for ICLR 2022.", + "headline_alternatives": [ + "1. Estimate parameters and predict outcomes for gene regulation models (79 characters)", + "2. Apply optimization to accurately parameterize gene network models (79 characters)", + "3. Select informative experiments to parameterize gene regulation models (78 characters) ", + "4. Develop methods to predict gene network model perturbations (74 characters)", + "5. Optimize estimation of kinetic parameters in gene networks (77 characters)" + ] + }, + { + "id": 213, + "slug": "dream-6-flowcap2-molecular-classification-of-acute-myeloid-leukemia-challenge", + "name": "DREAM 6 - FlowCAP2 Molecular Classification of Acute Myeloid Leukemia Challenge", + "headline": "Automating Identification of Cell Populations in Flow Cytometry Data", + "headline_alternatives": [] + }, + { + "id": 214, + "slug": "dream-6-alternative-splicing-challenge", + "name": "DREAM 6 - Alternative Splicing Challenge", + "headline": "Compare mRNA-seq methods on primate and rhino transcripts", + "headline_alternatives": [ + "1. Assess accuracy of mRNA-seq transcript reconstruction vs long reads", + "2. Compare mRNA-seq to long reads for transcriptome analysis in stem cells ", + "3. Evaluate mRNA-seq transcript reconstruction on rhino, mandrill cells", + "4. mRNA-seq vs long reads for transcriptomes of stem cells and fibroblasts", + "5. Test mRNA-seq transcript reconstruction against long reads across species" + ] + }, + { + "id": 215, + "slug": "causalbench-challenge", + "name": "CausalBench Challenge", + "headline": "Deriving gene-gene networks to improve causal disease insights", + "headline_alternatives": [ + "1. Mapping gene interactions to advance drug discovery (34 characters)", + "2. Deriving gene networks from single-cell data (32 characters) ", + "3. Advancing gene network inference for drug discovery (43 characters)", + "4. Improving causal insights into biology via gene networks (49 characters)", + "5. Machine learning to map gene interactions for drug discovery (56 characters)" + ] + }, + { + "id": 216, + "slug": "iclr-computational-geometry-and-topology-challenge-2022", + "name": "ICLR Computational Geometry & Topology Challenge 2022", + "headline": "Fostering Geometric Learning: Crowdsourced Algorithms for Reproducible Deep ...", + "headline_alternatives": [] + }, + { + "id": 217, + "slug": "iclr-computational-geometry-and-topology-challenge-2021", + "name": "ICLR Computational Geometry & Topology Challenge 2021", + "headline": "Advancing computational geometry and topology with Python", + "headline_alternatives": [] + }, + { + "id": 218, + "slug": "genedisco-challenge", + "name": "GeneDisco Challenge", + "headline": "Exploring experimental design with active learning for genetics", + "headline_alternatives": [] + }, + { + "id": 219, + "slug": "hidden-treasures-warm-up", + "name": "Hidden Treasures: Warm Up", + "headline": "Assess genome sequencing software accuracy with unknown variants", + "headline_alternatives": [] + }, + { + "id": 220, + "slug": "data-management-and-graph-extraction-for-large-models-in-the-biomedical-space", + "name": "Data management and graph extraction for large models in the biomedical space", + "headline": "CMU Libraries & DNAnexus Data Management Hackathon: Advancing Biomedical Kno...", + "headline_alternatives": [] + }, + { + "id": 221, + "slug": "cagi2-asthma-twins", + "name": "CAGI2: Asthma discordant monozygotic twins", + "headline": "Identify genetic differences between asthmatic and healthy twins", + "headline_alternatives": [ + "1. Identify genomic differences between asthmatic and healthy twins with DNA and RNA data (79 characters)", + "2. Find genetic causes for asthma discordance in identical twins (77 characters) ", + "3. Use genomic and transcriptomic data to understand asthma in twins (65 characters)", + "4. Asthma discordance in twins: genetic factors from genome and RNA sequencing (79 characters)", + "5. Asthma genetics: genome and transcriptome comparison of asthmatic vs healthy twins (78 characters)" + ] + }, + { + "id": 222, + "slug": "cagi4-bipolar", + "name": "CAGI4: Bipolar disorder", + "headline": "Predicting bipolar disorder from exome data", + "headline_alternatives": [ + "1. Predicting bipolar disorder from exome data (34 characters)", + "2. Identifying bipolar disorder using exome sequencing (49 characters) ", + "3. Detecting bipolar disorder with exome data (41 characters)", + "4. Classifying bipolar disorder from exomes (41 characters)", + "5. Diagnosing bipolar disorder through exome analysis (55 characters)" + ] + }, + { + "id": 223, + "slug": "cagi3-brca", + "name": "CAGI3: BRCA1 & BRCA2", + "headline": "Assess hereditary cancer risk via BRCA gene analysis", + "headline_alternatives": [ + "1. Develop open access BRCA1/2 mutation test to assess cancer risk (56 characters)", + "2. Create non-proprietary hereditary breast/ovarian cancer test (54 characters) ", + "3. New open access test for BRCA mutations and cancer risk (51 characters)", + "4. Open source alternative to proprietary BRCA1/2 cancer test (56 characters)", + "5. Non-proprietary test to identify BRCA mutations linked to cancer (63 characters)" + ] + }, + { + "id": 224, + "slug": "cagi2-breast-cancer-pkg", + "name": "CAGI2: Breast cancer pharmacogenomics", + "headline": "Exploring CHEK2 as a candidate gene for cancer susceptibility", + "headline_alternatives": [ + "1. Studying CHEK2 as a cancer susceptibility gene (50 characters)", + "2. Examining CHEK2's role in DNA repair and cell cycle regulation (59 characters)", + "3. Investigating CHEK2 interactions with BRCA1/TP53 in cancer risk (66 characters) ", + "4. Can CHEK2 mutations explain increased cancer susceptibility? (63 characters)", + "5. Evaluating CHEK2's function in genome integrity maintenance (63 characters)" + ] + }, + { + "id": 225, + "slug": "cagi4-2eqtl", + "name": "CAGI4: eQTL causal SNPs", + "headline": "Identify regulatory variants causing gene expression differences", + "headline_alternatives": [] + }, + { + "id": 226, + "slug": "cagi1-cbs", + "name": "CAGI1: CBS", + "headline": "Seeking to understand CBS enzyme function in cysteine production", + "headline_alternatives": [ + "1. Enzyme for cysteine production requires B6 and heme (50 characters)", + "2. CBS deficiency causes rare sulfur amino acid disorder (56 characters) ", + "3. Studying cofactor dependence of cysteine synthase enzyme (56 characters)", + "4. Understanding CBS enzyme function in cysteine biosynthesis (63 characters) ", + "5. Modeling effects of CBS mutations in cysteine metabolism (63 characters)" + ] + }, + { + "id": 227, + "slug": "cagi2-cbs", + "name": "CAGI2: CBS", + "headline": "Developing treatment for homocystinuria caused by CBS deficiency", + "headline_alternatives": [ + "1. Developing treatment for homocystinuria caused by CBS enzyme deficiency (79 characters)", + "2. Targeting CBS enzyme requiring B6 & heme to treat homocystinuria (77 characters) ", + "3. Treating recessive disease homocystinuria by restoring CBS function (76 characters)", + "4. Restoring vitamin-dependent CBS enzyme to treat homocystinuria (74 characters) ", + "5. Fixing defective CBS enzyme needing B6 & heme to treat homocystinuria (79 characters)" + ] + }, + { + "id": 228, + "slug": "cagi1-chek2", + "name": "CAGI1: CHEK2", + "headline": "Variants in the ATM & CHEK2 genes are associated with breast cancer.", + "headline_alternatives": [] + }, + { + "id": 229, + "slug": "cagi3-fch", + "name": "CAGI3: FCH", + "headline": "Seeking to understand genetic basis of common hyperlipidemia disorder", + "headline_alternatives": [ + "1. Identify genetic basis of common hyperlipidemia disorder FCH (76 characters)", + "2. Discover genes linked to elevated cholesterol in FCH patients (79 characters) ", + "3. Uncover genetic factors contributing to high triglycerides, LDL in FCH (78 characters)", + "4. Find genetic variants associated with increased CAD risk in FCH (76 characters)", + "5. Determine genetic causes of variable lipid levels in familial hyperlipidemia (79 characters)" + ] + }, + { + "id": 230, + "slug": "cagi3-ha", + "name": "CAGI3: HA", + "headline": "Raising HDL levels to reduce heart disease risk", + "headline_alternatives": [ + "1. Raising HDL levels to reduce heart disease risk in hypoalphalipoproteinemia (78 characters)", + "2. Treating low HDL & APOA1 levels in hypoalphalipoproteinemia patients (77 characters) ", + "3. Developing new therapies to increase HDL in hypoalphalipoproteinemia (79 characters)", + "4. Targeting low HDL as a risk factor for heart disease in hypoalphalipoproteinemia (79 characters) ", + "5. Improving HDL & APOA1 to lower coronary disease risk in hypoalphalipoproteinemia (78 characters)" + ] + }, + { + "id": 231, + "slug": "cagi2-croshn-s", + "name": "CAGI2: Crohn's disease", + "headline": "Seeking genes linked to Crohn's, an inflammatory bowel disease", + "headline_alternatives": [ + "1. Seeking genetic causes of Crohn's, an inflammatory bowel disease (78 characters)", + "2. Understanding the genetics behind Crohn's disease and GI inflammation (76 characters) ", + "3. Investigating the complex genetics of Crohn's disease (44 characters)", + "4. Identifying genetic factors in Crohn's disease pathology (56 characters) ", + "5. Elucidating the genetics of chronic inflammation in Crohn's disease (63 characters)" + ] + }, + { + "id": 232, + "slug": "cagi3-crohn-s", + "name": "CAGI3: Crohn's disease", + "headline": "Understanding the genetics behind Crohn's disease", + "headline_alternatives": [] + }, + { + "id": 233, + "slug": "cagi4-chron-s-exome", + "name": "CAGI4: Crohn's exomes", + "headline": "Seeking to understand genetic basis of Crohn's bowel disease", + "headline_alternatives": [ + "1. Seeking genetic causes of Crohn's disease, an inflammatory bowel disorder (77 characters)", + "2. Understanding the genetics behind Crohn's disease, a chronic inflammatory bowel disease (76 characters) ", + "3. Investigating the complex genetics of Crohn's disease, an inflammatory bowel disorder (75 characters)", + "4. Studying the genetics of Crohn's, an inflammatory bowel disease with chronic inflammation (79 characters) ", + "5. Exploring the genetic factors in Crohn's disease, a relapsing inflammatory bowel disorder (79 characters)" + ] + }, + { + "id": 234, + "slug": "cagi4-hopkins", + "name": "CAGI4: Hopkins clinical panel", + "headline": "Exonic sequences of 83 genes linked to 14 diseases analyzed", + "headline_alternatives": [ + "1. Hopkins challenge: Classify exonic sequences into 14 disease types", + "2. Hopkins DNA challenge: Categorize 83 gene exonic sequences ", + "3. Hopkins exome challenge: Assign sequences to one of 14 diseases", + "4. Classify 83 Hopkins gene exonic sequences into diseases", + "5. Categorize Hopkins exonic sequences into one of 14 diseases" + ] + }, + { + "id": 235, + "slug": "cagi2-mouse-exomes", + "name": "CAGI2: Mouse exomes", + "headline": "Predict causative variants from exome sequencing data.", + "headline_alternatives": [] + }, + { + "id": 236, + "slug": "cagi3-mrn-mre11", + "name": "CAGI3: MRE11", + "headline": "Genomes are subject to constant threat by damaging agents that generate DNA", + "headline_alternatives": [] + }, + { + "id": 237, + "slug": "cagi4-naglu", + "name": "CAGI4: NAGLU", + "headline": "Predicting enzymatic activity of NAGLU mutants", + "headline_alternatives": [] + }, + { + "id": 238, + "slug": "cagi4-npm-alk", + "name": "CAGI4: NPM: ALK", + "headline": "Predicting kinase activity of NPM-ALK fusion mutants", + "headline_alternatives": [ + "1. Predict kinase activity and binding of NPM-ALK mutants (78 characters)", + "2. Assess impact of mutations on NPM-ALK kinase and binding (77 characters) ", + "3. Model effects of NPM-ALK mutations on activity and binding (79 characters)", + "4. Quantify NPM-ALK mutant kinase activity and Hsp90 binding (79 characters)", + "5. Forecast NPM-ALK mutant kinase function from sequence changes (79 characters)" + ] + }, + { + "id": 239, + "slug": "cagi3-mrn-nbs1", + "name": "CAGI3: NBS1", + "headline": "Predicting Pathogenicity of Rare MRE11 and NBS1 Variants", + "headline_alternatives": [] + }, + { + "id": 240, + "slug": "cagi3-p16", + "name": "CAGI3: p16", + "headline": "Assessing p16 protein variants' effects on cell growth", + "headline_alternatives": [] + }, + { + "id": 241, + "slug": "cagi2-p53", + "name": "CAGI2: p53 reactivation", + "headline": "Predictors are asked to submit predictions on the effect of the cancer rescue...", + "headline_alternatives": [] + }, + { + "id": 242, + "slug": "cagi1-pgp", + "name": "CAGI1: PGP", + "headline": "CAGI Challenges Utilizing Public Genomic and Phenotypic Data Resources", + "headline_alternatives": [] + }, + { + "id": 243, + "slug": "cagi2-pgp", + "name": "CAGI2: PGP", + "headline": "CAGI Challenges Utilizing Public Genomic and Phenotypic Data Resources", + "headline_alternatives": [] + }, + { + "id": 244, + "slug": "cagi3-pgp", + "name": "CAGI3: PGP", + "headline": "CAGI Challenges Utilizing Public Genomic and Phenotypic Data Resources", + "headline_alternatives": [ + "1. Participants share full data to enable CAGI analysis (52 characters)", + "2. CAGI challenges based on participants' shared sequence data (56 characters) ", + "3. Participants publicly share data for CAGI challenge analysis (55 characters)", + "4. CAGI challenges utilize participants' shared sequence data (57 characters)", + "5. Participants make data public for CAGI challenge analysis (59 characters)" + ] + }, + { + "id": 245, + "slug": "cagi4-pgp", + "name": "CAGI4: PGP", + "headline": "CAGI Challenges Utilizing Public Genomic and Phenotypic Data Resources", + "headline_alternatives": [] + }, + { + "id": 246, + "slug": "cagi4-pyruvate-kinase", + "name": "CAGI4: Pyruvate kinase", + "headline": "Predicting mutation impacts on pyruvate kinase activity and regulation", + "headline_alternatives": [] + }, + { + "id": 247, + "slug": "cagi2-rad50", + "name": "CAGI2: RAD50", + "headline": "Assessing RAD50 variants for breast cancer risk", + "headline_alternatives": [ + "1. Identifying RAD50 variants associated with breast cancer risk (54 characters)", + "2. Assessing RAD50 variants for breast cancer susceptibility (59 characters)", + "3. Evaluating RAD50 gene variants in breast cancer cases and controls (71 characters) ", + "4. Determining if RAD50 variants confer intermediate breast cancer risk (79 characters)", + "5. Can RAD50 gene variants help predict breast cancer susceptibility? (76 characters)" + ] + }, + { + "id": 248, + "slug": "cagi2-risksnps", + "name": "CAGI2: riskSNPs", + "headline": "Exploring molecular mechanisms linking SNPs to disease risk", + "headline_alternatives": [] + }, + { + "id": 249, + "slug": "cagi3-risksnps", + "name": "CAGI3: riskSNPs", + "headline": "Exploring molecular mechanisms linking SNPs to disease risk", + "headline_alternatives": [] + }, + { + "id": 250, + "slug": "cagi2-nav1-5", + "name": "CAGI2: SCN5A", + "headline": "Predictors are asked to submit predictions on the effect of the mutants on t...", + "headline_alternatives": [] + }, + { + "id": 251, + "slug": "cagi2-mr-1", + "name": "CAGI2: Shewanella oneidensis strain MR-1", + "headline": "Shewanella oneidensis strain MR-1 (formerly known as S. putrefaciens) is a m...", + "headline_alternatives": [] + }, + { + "id": 252, + "slug": "cagi3-mr-1", + "name": "CAGI3: Shewanella oneidensis strain MR-1", + "headline": "Shewanella oneidensis strain MR-1 (formerly known as S. putrefaciens) is a m...", + "headline_alternatives": [] + }, + { + "id": 253, + "slug": "cagi4-sickkids", + "name": "CAGI4: SickKids", + "headline": "The challenge presented here is to use computational methods to match each g...", + "headline_alternatives": [ + "1. Predict phenotypes from genome sequences of kids with disorders (79 characters)", + "2. Match genome sequences to clinical descriptions for 25 children (77 characters) ", + "3. Identify variants predicting genetic disorders from sequences (76 characters)", + "4. Infer phenotypes and disease risk from genomic data (74 characters)", + "5. Predict traits and disease predispositions from genomes (78 characters)" + ] + }, + { + "id": 254, + "slug": "cagi4-sumo-ligase", + "name": "CAGI4: SUMO ligase", + "headline": "Participants are asked to submit predictions of the effect of the variants o...", + "headline_alternatives": [] + }, + { + "id": 255, + "slug": "cagi3-splicing", + "name": "CAGI3: TP53 splicing", + "headline": "With the provided data, determine which disease-causing mutations in the TP5...", + "headline_alternatives": [] + }, + { + "id": 256, + "slug": "cagi4-warfarin", + "name": "CAGI4: Warfarin exomes", + "headline": "With the provided exome data and clinical covariates, predict the therapeuti...", + "headline_alternatives": [ + "1. Improve warfarin dosing to reduce adverse events", + "2. Seek better warfarin dosing for fewer patient hospitalizations", + "3. Find optimal warfarin doses despite high variability ", + "4. Reduce warfarin's adverse events via personalized dosing", + "5. Develop improved warfarin dosing given high usage" + ] + }, + { + "id": 257, + "slug": "cagi6-calmodulin", + "name": "CAGI6: Calmodulin", + "headline": "Participants were asked to submit predictions for the competitive growth sco...", + "headline_alternatives": [] + }, + { + "id": 258, + "slug": "cagi2-splicing", + "name": "CAGI2: splicing", + "headline": "Predictors are asked to compare exons from wild type and disease-associated ...", + "headline_alternatives": [ + "1. Developing methods to improve accuracy of pre-mRNA splicing", + "2. Improving understanding of spliceosome assembly for splicing regulation ", + "3. Elucidating mechanisms regulating spliceosome assembly on pre-mRNAs", + "4. Characterizing spliceosome dynamics during pre-mRNA splicing", + "5. Analyzing spliceosome assembly on nascent pre-mRNA introns" + ] + }, + { + "id": 259, + "slug": "cagi6-lc-arsa", + "name": "CAGI6: ARSA", + "headline": "Predicting the effect of naturally occurring missense mutations on enzymatic...", + "headline_alternatives": [] + }, + { + "id": 260, + "slug": "predict-hits-for-the-wdr-domain-of-lrrk2", + "name": "CACHE1: Predict Hits for The WDR Domain of LRRK2", + "headline": "Finding ligands targeting the central cavity of the WD-40 repeat (WDR) domai...", + "headline_alternatives": [ + "1. Find hits targeting LRRK2 WD40 domain for Parkinson's (56 characters)", + "2. Discover compounds binding LRRK2 WDR to treat Parkinson's (64 characters) ", + "3. Seek ligands for LRRK2 WD40 to modulate Parkinson's risk (65 characters)", + "4. Target LRRK2 WD40 repeats to impact Parkinson's pathogenesis (79 characters) ", + "5. Identify small molecules binding LRRK2 WDR domain for Parkinson's (76 characters)" + ] + }, + { + "id": 261, + "slug": "finding-ligands-targeting-the-conserved-rna-binding-site-of-sars-cov-2-nsp13", + "name": "CACHE2: Finding Ligands Targeting The Conserved RNA Binding Site of SARS-CoV-2 NSP13", + "headline": "Finding ligands targeting the conserved RNA binding site of SARS-CoV-2 NSP13...", + "headline_alternatives": [] + }, + { + "id": 262, + "slug": "finding-ligands-targeting-the-macrodomain-of-sars-cov-2-nsp3", + "name": "CACHE3: Finding ligands targeting the macrodomain of SARS-CoV-2 Nsp3", + "headline": "Studying the macrodomain of Severe acute respiratory syndrome coronavirus 2 ...", + "headline_alternatives": [] + }, + { + "id": 263, + "slug": "finding-ligands-targeting-the-tkb-domain-of-cblb", + "name": "CACHE4: Finding ligands targeting the TKB domain of CBLB", + "headline": "Investigating the TKB domain of CBLB, a protein involved in cancer and immun...", + "headline_alternatives": [ + "1. Predict novel compounds binding CBLB TKB domain (76 characters)", + "2. Discover new chemical templates binding CBLB protein (69 characters)", + "3. Find compounds binding CBLB below 30 micromolar KD (63 characters) ", + "4. Model binding of novel ligands to CBLB TKB domain (65 characters)", + "5. Predict tight-binding compounds for closed CBLB conformation (79 characters)" + ] + }, + { + "id": 264, + "slug": "rare-disease-ai-hackathon", + "name": "Rare Disease AI Hackathon", + "headline": "Researchers and medical experts are invited to collaborate on our patient ca...", + "headline_alternatives": [] + }, + { + "id": 265, + "slug": "cometh-benchmark", + "name": "COMETH Benchmark", + "headline": "Quantify tumor heterogeneity\u2014how many cell types are present and in which pr...", + "headline_alternatives": [] + }, + { + "id": 266, + "slug": "the-miccai-2014-machine-learning-challenge", + "name": "The MICCAI 2014 Machine Learning Challenge", + "headline": "Predicting Binary and Continuous Phenotypes from Structural Brain MRI Data i...", + "headline_alternatives": [] + }, + { + "id": 267, + "slug": "cagi6-annotate-all-missense", + "name": "CAGI6: Annotate All Missense", + "headline": "Predictors are asked to predict the functional effect of every coding single...", + "headline_alternatives": [] + }, + { + "id": 268, + "slug": "cagi6-hmbs", + "name": "CAGI6: HMBS", + "headline": "Participants are asked to submit predictions of the fitness score for each o...", + "headline_alternatives": [] + }, + { + "id": 269, + "slug": "cagi6-id-panel", + "name": "CAGI6: Intellectual Disability Panel", + "headline": "In this challenge, predictors are asked to analyze the sequence data for the...", + "headline_alternatives": [] + }, + { + "id": 270, + "slug": "cagi6-mapk1", + "name": "CAGI6: MAPK1", + "headline": "For each variant, participants are asked to predict the \u0394\u0394G(H2O) value for t...", + "headline_alternatives": [] + }, + { + "id": 271, + "slug": "cagi6-mapk3", + "name": "CAGI6: MAPK3", + "headline": "For each variant, participants are asked to predict the \u0394\u0394G(H2O) value for t...", + "headline_alternatives": [] + }, + { + "id": 272, + "slug": "cagi6-mthfr", + "name": "CAGI6: MTHFR", + "headline": "Participants are asked to submit predictions of the fitness score for each m...", + "headline_alternatives": [] + }, + { + "id": 273, + "slug": "cagi6-prs", + "name": "CAGI6: Polygenic Risk Scores", + "headline": "Participants will be expected to provide a fully trained prediction model th...", + "headline_alternatives": [] + }, + { + "id": 274, + "slug": "cagi6-rgp", + "name": "CAGI6: Rare Genomes Project", + "headline": "The prediction challenge involves approximately 30 families. The prediction ...", + "headline_alternatives": [] + }, + { + "id": 275, + "slug": "cagi6-invitae", + "name": "CAGI6: Sherloc clinical classification", + "headline": "Over 122,000 coding (missense, silent, frameshift, stop gained, in-frame cod...", + "headline_alternatives": [ + "1. Predict pathogenicity of 122,000 variants for submission to ClinVar by Invitae (79 characters)", + "2. Classify 122,000 variants by predicted pathogenicity before submission to ClinVar (79 characters) ", + "3. Assess clinical utility of 122,000 variant interpretations before ClinVar submission (78 characters)", + "4. Interpret pathogenicity of 122,000 variants spanning clinical effects for ClinVar (79 characters)", + "5. Predict effects of 122,000 uncharacterized variants for Invitae's ClinVar submission (80 characters)" + ] + }, + { + "id": 276, + "slug": "cagi6-splicing-vus", + "name": "CAGI6: Splicing VUS", + "headline": "Predict whether the experimentally validated variants of unknown significanc...", + "headline_alternatives": [] + }, + { + "id": 277, + "slug": "cagi6-stk11", + "name": "CAGI6: STK11", + "headline": "Participants are asked to submit predictions on the impact of the variants l...", + "headline_alternatives": [] + }, + { + "id": 278, + "slug": "qbi-hackathon", + "name": "QBI hackathon", + "headline": "A 48-hour event connecting the Bay Area developer community with scientists ...", + "headline_alternatives": [] + }, + { + "id": 279, + "slug": "niddk-central-repository-data-centric-challenge", + "name": "NIDDK Central Repository Data-Centric Challenge", + "headline": "Enhancing NIDDK datasets for future Artificial Intelligence (AI) application...", + "headline_alternatives": [] + }, + { + "id": 280, + "slug": "stanford-ribonanza-rna-folding", + "name": "Stanford Ribonanza RNA Folding", + "headline": "Pioneering RNA Science: A Path to Programmable Medicine and Scientific Break...", + "headline_alternatives": [ + "1. Harnessing RNA to cure disease and fight climate change", + "2. Understanding RNA structure to enable programmable medicine ", + "3. Data science key to unraveling RNA for new medicines", + "4. Decoding RNA structure for disease cures and biotech advances", + "5. RNA manipulation through data science for medicine and biotech" + ] + }, + { + "id": 281, + "slug": "uls23", + "name": "Universal Lesion Segmentation '23 Challenge", + "headline": "Revolutionizing Lesion Segmentation: Advancements, Challenges, and a Univers...", + "headline_alternatives": [] } ] \ No newline at end of file diff --git a/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py index 0430fa9914..43916c9433 100644 --- a/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py +++ b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py @@ -121,7 +121,7 @@ def process_challenge(challenge): return obj -challenge_headlines = list(map(process_challenge, challenges[:5])) +challenge_headlines = list(map(process_challenge, challenges)) # SAVE OUTPUT TO FILE From a4bdc801c45cd9dff7e4a1fc59c341e1ab9f4d44 Mon Sep 17 00:00:00 2001 From: Thomas Schaffter Date: Tue, 14 Nov 2023 16:19:03 -0800 Subject: [PATCH 4/4] Update apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py Co-authored-by: Verena Chung <9377970+vpchung@users.noreply.github.com> --- .../src/challenge_headline/generate_challenge_headlines.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py index 43916c9433..e28f524bb5 100644 --- a/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py +++ b/apps/openchallenges/notebook/src/challenge_headline/generate_challenge_headlines.py @@ -84,7 +84,7 @@ def generate_challenge_headlines(text, num_headlines): "following challenge description. " "The headlines must summarize the goal of the challenge. " # "The headlines must not include the name of the challenge. " - "The headlines must reads naturally. " + "The headlines must read naturally. " f"Description: \n{text}" ) response = Bedrock(