Merge pull request #51 from jyaacoub/development

Development

.gitignore

@@ -207,5 +207,6 @@ lib/mgltools_x86_64Linux2_1.5.7/MGLToolsPckgs/AutoDockTools/Utilities24/*
 lib/mgltools_x86_64Linux2_1.5.7p1.tar.gz
 
 log_test/
-slurm_tests/
+slurm_out_DDP/
 /*.sh
+results/model_checkpoints/ours/*.model*

docs/req.txt

@@ -0,0 +1,122 @@
+absl-py==1.4.0
+aiosignal==1.3.1
+astor==0.8.1
+asttokens==2.2.1
+attrs==23.1.0
+autograd==1.5
+autograd-gamma==0.5.0
+backcall==0.2.0
+biopython==1.79
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.7
+cloudpickle==2.2.1
+cmake==3.26.4
+comm==0.1.3
+contourpy==1.0.7
+cycler==0.11.0
+debugpy==1.6.7
+decorator==5.1.1
+dm-tree==0.1.8
+executing==1.2.0
+fastjsonschema==2.17.1
+filelock==3.12.2
+flake8==6.1.0
+fonttools==4.39.4
+formulaic==0.6.1
+frozenlist==1.4.0
+fsspec==2023.6.0
+future==0.18.3
+grpcio==1.57.0
+huggingface-hub==0.16.4
+idna==3.4
+interface-meta==1.3.0
+ipykernel==6.23.1
+ipython==8.13.2
+jedi==0.18.2
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.17.3
+jupyter_client==8.2.0
+jupyter_core==5.3.0
+kiwisolver==1.4.4
+lifelines==0.27.7
+lit==16.0.5
+MarkupSafe==2.1.3
+matplotlib==3.7.1
+matplotlib-inline==0.1.6
+mccabe==0.7.0
+mpmath==1.3.0
+msgpack==1.0.5
+nbformat==5.9.0
+nest-asyncio==1.5.6
+networkx==3.1
+numpy==1.23.5
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+packaging==23.1
+pandas==1.5.3
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.5.0
+platformdirs==3.5.1
+plotly==5.14.1
+ProDy==2.4.1
+prompt-toolkit==3.0.38
+protobuf==4.24.1
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==12.0.1
+pycodestyle==2.11.0
+pyflakes==3.1.0
+Pygments==2.15.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+pytz==2023.3
+PyYAML==6.0.1
+pyzmq==25.1.0
+rapidfuzz==3.3.0
+ray==2.6.3
+rdkit==2023.3.1
+regex==2023.6.3
+requests==2.31.0
+safetensors==0.3.1
+scikit-learn==1.2.2
+scipy==1.10.1
+seaborn==0.11.2
+six==1.16.0
+stack-data==0.6.2
+statannotations==0.6.0
+submitit==1.4.5
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.2
+tensorboardX==2.6.2.2
+thefuzz==0.20.0
+threadpoolctl==3.1.0
+tokenizers==0.13.3
+torch==2.0.1
+torch-geometric==2.3.1
+torchsummary==1.5.1
+tornado==6.3.2
+tqdm==4.65.0
+traitlets==5.9.0
+transformers==4.31.0
+triton==2.0.0
+typing_extensions==4.6.3
+tzdata==2023.3
+urllib3==2.0.2
+wcwidth==0.2.6
+wrapt==1.15.0

docs/requirements.txt

@@ -1,29 +1,29 @@
-numpy
-pandas
-tqdm
-rdkit
-scipy
+numpy==1.23.5
+pandas==1.5.3
+tqdm==4.65.0
+rdkit==2023.3.1
+scipy==1.10.1
 
 # for generating figures:
-matplotlib
-seaborn
-statannotations
+matplotlib==3.7.1
+seaborn==0.11.2
+statannotations==0.6.0
 
-lifelines # used for concordance index calc
+lifelines==0.27.7 # used for concordance index calc
 #biopython # used for cmap
 
 # model building
-torch
-torch_geometric
-transformers # huggingface needed for esm
+torch==2.0.1
+torch-geometric==2.3.1
+transformers==4.31.0 # huggingface needed for esm
 
 # optional:
-torchsummary 
-tabulate # for torch_geometric.nn.summary
-ipykernel
-plotly
-requests
+torchsummary==1.5.1
+tabulate==0.9.0 # for torch_geometric.nn.summary
+ipykernel==6.23.1
+plotly==5.14.1
+requests==2.31.0
 #ray[tune]
 
-submitit
-ProDy
+submitit==1.4.5
+ProDy==2.4.1

playground.py

@@ -1,8 +1,31 @@
-# %%
-from src.data_analysis.figures import prepare_df, fig3_edge_feat
-df = prepare_df('results/model_media/model_stats.csv')
+#%%
+from src.data_processing.datasets import PDBbindDataset
+from src.utils import config as cfg
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# d0 = pd.read_csv(f'{cfg.DATA_ROOT}/DavisKibaDataset/davis/nomsa_anm/full/XY.csv', index_col=0)
+d0 = pd.read_csv(f'{cfg.DATA_ROOT}/PDBbindDataset/nomsa_anm/full/XY.csv', index_col=0)
+
+d0['len'] = d0.prot_seq.str.len()
 
 # %%
-fig3_edge_feat(df, show=True, exclude=[])
+n, bins, patches = plt.hist(d0['len'], bins=20)
+# Set labels and title
+plt.xlabel('Protein Sequence length')
+plt.ylabel('Frequency')
+plt.title('Histogram of Protein Sequence length (davis)')
+
+# Add counts to each bin
+for count, x, patch in zip(n, bins, patches):
+    plt.text(x + 0.5, count, str(int(count)), ha='center', va='bottom')
+
+cutoff= 1500
+print(f"Eliminating codes above {cutoff} length would reduce the dataset by: {len(d0[d0['len'] > cutoff])}")
+print(f"\t - Eliminates {len(d0[d0['len'] > cutoff].index.unique())} unique proteins")
+
+# %% -d PDBbind -f nomsa -e anm
+from src.utils.loader import Loader
+d1 = Loader.load_dataset('PDBbind', 'nomsa', 'anm')
 
 # %%