Merge pull request #80 from sanjaynagi/results-book-21-07-23

Implement rna-seq-pop results book
sanjaynagi · Jul 25, 2023 · 509199a · 509199a
2 parents 60b0aec + 731939d
commit 509199a
Show file tree

Hide file tree

Showing 63 changed files with 9,211 additions and 72 deletions.
diff --git a/.github/workflows/github-action-rna-seq-pop-paired-end.yml b/.github/workflows/github-action-rna-seq-pop-paired-end.yml
@@ -15,7 +15,13 @@ jobs:
         uses: actions/checkout@v2
         with:
           submodules: recursive
-
+
+      - name: cp results book yamls 
+        run: cp docs/rna-seq-pop-results/_toc.yml docs/rna-seq-pop-results/_config.yml .test/docs/rna-seq-pop-results
+
+      - name: cp landing page
+        run: cp docs/rna-seq-pop-results/landing-page.md .test/docs/rna-seq-pop-results
+
       - name: Test workflow paired-end
         uses: snakemake/[email protected]
         with:

diff --git a/.github/workflows/github-action-rna-seq-pop-single-end.yml b/.github/workflows/github-action-rna-seq-pop-single-end.yml
@@ -16,6 +16,12 @@ jobs:
         with:
           submodules: recursive
 
+      - name: cp results book yamls 
+        run: cp docs/rna-seq-pop-results/_toc.yml docs/rna-seq-pop-results/_config.yml .test/docs/rna-seq-pop-results
+
+      - name: cp landing page
+        run: cp docs/rna-seq-pop-results/landing-page.md .test/docs/rna-seq-pop-results
+
       - name: Test workflow single-end
         uses: snakemake/[email protected]
         with:

diff --git a/.gitignore b/.gitignore
@@ -21,8 +21,6 @@ config/config.yaml
 config/samples.tsv
 *snpEff_summary.html
 workflow/scripts/misc
-workflow/notebooks
 .test/workflow/scripts/
 .ipynb_checkpoints
-workflow/scripts/snpEff
-workflow/scripts/*ipynb*
+workflow/scripts/snpEff
diff --git a/.test/config/config_paired_end.yaml b/.test/config/config_paired_end.yaml
@@ -3,6 +3,9 @@ metadata: config/samples.tsv
 # Dataset name
 dataset: 'Test-GithubActionsCI'
 
+jupyter-book:
+      activate: True
+
 fastq: 
       auto: True # set auto if your files follow 
       paired: True
@@ -78,9 +81,8 @@ VariantAnalysis:
             missingness: 0.5
             # Do we want to run pbs (Needs three conditions, two more closely related and a slight outgroup)
             pbs:
-                  activate: True
-                  contrasts: 
-                        - 'PiriTia_ContTia_Kisumu'
+                  activate: False
+                  contrasts: ['PiriTia_ContTia_Kisumu']
 
       # For Anopheles gambiae s.l only - run Ancestry Informative Marker analysis.
       ancestry:
@@ -108,12 +110,12 @@ VariantAnalysis:
 miscellaneous:
 # If activate:True, creates allele balance .xlsx reports on IR mutations of choice
       VariantsOfInterest: 
-            activate: False
+            activate: True
             path: "resources/test-IRmutations.tsv"
 
       GeneFamiliesHeatmap:
             activate: False
-            eggnog: resources/Anogam_long.pep_eggnog_diamond.emapper.annotations.tsv.gz.GO
+            eggnog: resources/Anogam_long.pep_eggnog_diamond.emapper.annotations.tsv.gz
             pfam: resources/Anogam_long.pep_Pfamscan.seqs.gz
 
       sweeps:

diff --git a/.test/config/config_single_end.yaml b/.test/config/config_single_end.yaml
@@ -3,6 +3,9 @@ metadata: config/samples.tsv
 # Dataset name
 dataset: 'Test-GithubActionsCI'
 
+jupyter-book:
+      activate: True
+
 fastq: 
       table: config/fastq.tsv
       auto: True # set auto if your files follow 
@@ -113,7 +116,7 @@ VariantAnalysis:
 miscellaneous:
 # If activate:True, creates allele balance .xlsx reports on IR mutations of choice
       VariantsOfInterest: 
-            activate: False
+            activate: True
             path: "resources/test-IRmutations.tsv"
 
       GeneFamiliesHeatmap:

diff --git a/.test/docs/rna-seq-pop-results/_config.yml b/.test/docs/rna-seq-pop-results/_config.yml
@@ -0,0 +1,44 @@
+# Book settings
+# Learn more at https://jupyterbook.org/customize/config.html
+
+title: 
+author: Sanjay Curtis Nagi
+copyright: "2023"
+logo: logo.png
+
+# Force re-execution of notebooks on each build.
+# See https://jupyterbook.org/content/execute.html
+execute:
+  execute_notebooks: "off"
+
+# Information about where the book exists on the web
+repository:
+  url: https://github.com/sanjaynagi/rna-seq-pop  # Online location of your book
+  path_to_book: docs/rna-seq-pop-results  # Optional path to your book, relative to the repository root
+  branch: master  # Which branch of the repository should be used when creating links (optional)
+
+# Add GitHub buttons to your book
+# See https://jupyterbook.org/customize/config.html#add-a-link-to-your-repository
+html:
+  favicon : favicon.ico
+  use_issues_button: true
+  use_repository_button: true
+  comments:
+    utterances:
+      repo: "sanjaynagi/rna-seq-pop"
+      issue-term: "pathname"
+      label: "comment"
+      theme: "github-light" 
+
+
+sphinx:
+    extra_extensions:
+        - 'sphinx.ext.autodoc'
+        - 'sphinx.ext.napoleon'
+    config:
+        myst_enable_extensions:
+            - substitution
+            - dollarmath
+        html_js_files:
+            - https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js
+        suppress_warnings: ["mystnb.unknown_mime_type"]
diff --git a/.test/docs/rna-seq-pop-results/_toc.yml b/.test/docs/rna-seq-pop-results/_toc.yml
@@ -0,0 +1,19 @@
+format: jb-book
+root: landing-page
+parts:
+- caption: Quality Control
+  chapters:
+        - file: notebooks/quality-control
+        - file: notebooks/counts-qc
+- caption: Differential expression
+  chapters:
+        - file: notebooks/differential-expression
+        - file: notebooks/gene-families-heatmap
+        - file: notebooks/gene-set-enrichment-analysis
+- caption: Variant analysis
+  chapters:
+        - file: notebooks/principal-components-analysis
+        - file: notebooks/genetic-diversity
+        - file: notebooks/variants-of-interest
+        - file: notebooks/windowed-selection
+        - file: notebooks/karyotyping
diff --git a/.test/resources/multiqc.yaml b/.test/resources/multiqc.yaml
@@ -0,0 +1,18 @@
+table_columns_visible:
+  QualiMap:
+    general_error_rate: True
+    median_insert_size: False
+sp:
+  fastp:
+    fn: "*.json"
+  qualimap/bamqc/genome_results:
+    fn: genome_results.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: coverage_histogram.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: insert_size_histogram.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: genome_fraction_coverage.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: mapped_reads_gc-content_distribution.txt
+
diff --git a/config/exampleconfig.yaml b/config/exampleconfig.yaml
@@ -41,10 +41,8 @@ contrasts:
 
 
 QualityControl:
-      trim-reads:
+      fastp-trim:
             activate: False
-      fastqc:
-            activate: True
       mosdepth:
             activate: True
       multiqc:

diff --git a/docs/rna-seq-pop-book/_config.yml → docs/rna-seq-pop-docs/_config.yml b/docs/rna-seq-pop-book/_config.yml → docs/rna-seq-pop-docs/_config.yml
diff --git a/docs/rna-seq-pop-book/_toc.yml → docs/rna-seq-pop-docs/_toc.yml b/docs/rna-seq-pop-book/_toc.yml → docs/rna-seq-pop-docs/_toc.yml
diff --git a/docs/rna-seq-pop-book/landing-page.md → docs/rna-seq-pop-docs/landing-page.md b/docs/rna-seq-pop-book/landing-page.md → docs/rna-seq-pop-docs/landing-page.md
diff --git a/docs/rna-seq-pop-book/logo.png → docs/rna-seq-pop-docs/logo.png b/docs/rna-seq-pop-book/logo.png → docs/rna-seq-pop-docs/logo.png
diff --git a/...ebooks/ancestry_informative_markers.ipynb → ...ebooks/ancestry_informative_markers.ipynb b/...ebooks/ancestry_informative_markers.ipynb → ...ebooks/ancestry_informative_markers.ipynb
diff --git a/.../notebooks/configuring_the_workflow.ipynb → .../notebooks/configuring_the_workflow.ipynb b/.../notebooks/configuring_the_workflow.ipynb → .../notebooks/configuring_the_workflow.ipynb
diff --git a/...seq-pop-book/notebooks/contributing.ipynb → ...seq-pop-docs/notebooks/contributing.ipynb b/...seq-pop-book/notebooks/contributing.ipynb → ...seq-pop-docs/notebooks/contributing.ipynb
diff --git a/...k/notebooks/differential_expression.ipynb → ...s/notebooks/differential_expression.ipynb b/...k/notebooks/differential_expression.ipynb → ...s/notebooks/differential_expression.ipynb
diff --git a/...eq-pop-book/notebooks/gene_families.ipynb → ...eq-pop-docs/notebooks/gene_families.ipynb b/...eq-pop-book/notebooks/gene_families.ipynb → ...eq-pop-docs/notebooks/gene_families.ipynb
diff --git a/...op-book/notebooks/genetic_diversity.ipynb → ...op-docs/notebooks/genetic_diversity.ipynb b/...op-book/notebooks/genetic_diversity.ipynb → ...op-docs/notebooks/genetic_diversity.ipynb
diff --git a/docs/rna-seq-pop-book/notebooks/gsea.ipynb → docs/rna-seq-pop-docs/notebooks/gsea.ipynb b/docs/rna-seq-pop-book/notebooks/gsea.ipynb → docs/rna-seq-pop-docs/notebooks/gsea.ipynb
diff --git a/...a-seq-pop-book/notebooks/input_data.ipynb → ...a-seq-pop-docs/notebooks/input_data.ipynb b/...a-seq-pop-book/notebooks/input_data.ipynb → ...a-seq-pop-docs/notebooks/input_data.ipynb
diff --git a/...seq-pop-book/notebooks/installation.ipynb → ...seq-pop-docs/notebooks/installation.ipynb b/...seq-pop-book/notebooks/installation.ipynb → ...seq-pop-docs/notebooks/installation.ipynb
@@ -42,6 +42,12 @@
     "\n",
     "When we run RNA-Seq-Pop, it is important to use the `--use-conda` directive - this will automatically install all necessary packages into isolated software environments, so we do not have to install any other dependencies.\n",
     "\n",
+    "Please also ensure your conda has channel priorities set to 'flexible', otherwise, conda may throw up errors when installing packages. You can do this with the following command:\n",
+    "\n",
+    "```\n",
+    "conda config --set channel_priority flexible\n",
+    "```\n",
+    "\n",
     "#### Testing the setup\n",
     "\n",
     "To test whether RNA-Seq-Pop is configured correctly, from the root directory you can perform a dry-run on the test dataset, with the following command:\n",

diff --git a/...-seq-pop-book/notebooks/karyotyping.ipynb → ...-seq-pop-docs/notebooks/karyotyping.ipynb b/...-seq-pop-book/notebooks/karyotyping.ipynb → ...-seq-pop-docs/notebooks/karyotyping.ipynb
diff --git a/...-pop-book/notebooks/quality_control.ipynb → ...-pop-docs/notebooks/quality_control.ipynb b/...-pop-book/notebooks/quality_control.ipynb → ...-pop-docs/notebooks/quality_control.ipynb
diff --git a/...-seq-pop-book/notebooks/read_counts.ipynb → ...-seq-pop-docs/notebooks/read_counts.ipynb b/...-seq-pop-book/notebooks/read_counts.ipynb → ...-seq-pop-docs/notebooks/read_counts.ipynb
diff --git a/...-seq-pop-book/notebooks/rna-seq-pop.ipynb → ...-seq-pop-docs/notebooks/rna-seq-pop.ipynb b/...-seq-pop-book/notebooks/rna-seq-pop.ipynb → ...-seq-pop-docs/notebooks/rna-seq-pop.ipynb
diff --git a/...book/notebooks/running_the_workflow.ipynb → ...docs/notebooks/running_the_workflow.ipynb b/...book/notebooks/running_the_workflow.ipynb → ...docs/notebooks/running_the_workflow.ipynb
diff --git a/...na-seq-pop-book/notebooks/selection.ipynb → ...na-seq-pop-docs/notebooks/selection.ipynb b/...na-seq-pop-book/notebooks/selection.ipynb → ...na-seq-pop-docs/notebooks/selection.ipynb
diff --git a/...na-seq-pop-book/notebooks/snakemake.ipynb → ...na-seq-pop-docs/notebooks/snakemake.ipynb b/...na-seq-pop-book/notebooks/snakemake.ipynb → ...na-seq-pop-docs/notebooks/snakemake.ipynb
diff --git a/...-pop-book/notebooks/troubleshooting.ipynb → ...-pop-docs/notebooks/troubleshooting.ipynb b/...-pop-book/notebooks/troubleshooting.ipynb → ...-pop-docs/notebooks/troubleshooting.ipynb
diff --git a/...-pop-book/notebooks/variant_calling.ipynb → ...-pop-docs/notebooks/variant_calling.ipynb b/...-pop-book/notebooks/variant_calling.ipynb → ...-pop-docs/notebooks/variant_calling.ipynb
diff --git a/...book/notebooks/variants_of_interest.ipynb → ...docs/notebooks/variants_of_interest.ipynb b/...book/notebooks/variants_of_interest.ipynb → ...docs/notebooks/variants_of_interest.ipynb
diff --git a/docs/rna-seq-pop-book/references.bib → docs/rna-seq-pop-docs/references.bib b/docs/rna-seq-pop-book/references.bib → docs/rna-seq-pop-docs/references.bib
diff --git a/docs/rna-seq-pop-book/requirements.txt → docs/rna-seq-pop-docs/requirements.txt b/docs/rna-seq-pop-book/requirements.txt → docs/rna-seq-pop-docs/requirements.txt
diff --git a/docs/rna-seq-pop-results/_config.yml b/docs/rna-seq-pop-results/_config.yml
@@ -0,0 +1,44 @@
+# Book settings
+# Learn more at https://jupyterbook.org/customize/config.html
+
+title: 
+author: Sanjay Curtis Nagi
+copyright: "2023"
+logo: logo.png
+
+# Force re-execution of notebooks on each build.
+# See https://jupyterbook.org/content/execute.html
+execute:
+  execute_notebooks: "off"
+
+# Information about where the book exists on the web
+repository:
+  url: https://github.com/sanjaynagi/rna-seq-pop  # Online location of your book
+  path_to_book: docs/rna-seq-pop-results  # Optional path to your book, relative to the repository root
+  branch: master  # Which branch of the repository should be used when creating links (optional)
+
+# Add GitHub buttons to your book
+# See https://jupyterbook.org/customize/config.html#add-a-link-to-your-repository
+html:
+  favicon : favicon.ico
+  use_issues_button: true
+  use_repository_button: true
+  comments:
+    utterances:
+      repo: "sanjaynagi/rna-seq-pop"
+      issue-term: "pathname"
+      label: "comment"
+      theme: "github-light" 
+
+
+sphinx:
+    extra_extensions:
+        - 'sphinx.ext.autodoc'
+        - 'sphinx.ext.napoleon'
+    config:
+        myst_enable_extensions:
+            - substitution
+            - dollarmath
+        html_js_files:
+            - https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js
+        suppress_warnings: ["mystnb.unknown_mime_type"]
diff --git a/docs/rna-seq-pop-results/_toc.yml b/docs/rna-seq-pop-results/_toc.yml
@@ -0,0 +1,19 @@
+format: jb-book
+root: landing-page
+parts:
+- caption: Quality Control
+  chapters:
+        - file: notebooks/quality-control
+        - file: notebooks/counts-qc
+- caption: Differential expression
+  chapters:
+        - file: notebooks/differential-expression
+        - file: notebooks/gene-families-heatmap
+        - file: notebooks/gene-set-enrichment-analysis
+- caption: Variant analysis
+  chapters:
+        - file: notebooks/principal-components-analysis
+        - file: notebooks/genetic-diversity
+        - file: notebooks/variants-of-interest
+        - file: notebooks/windowed-selection
+        - file: notebooks/karyotyping
diff --git a/docs/rna-seq-pop-results/favicon.ico b/docs/rna-seq-pop-results/favicon.ico
diff --git a/docs/rna-seq-pop-results/landing-page.md b/docs/rna-seq-pop-results/landing-page.md
@@ -0,0 +1,19 @@
+# RNA-Seq-Pop
+
+Welcome to your [RNA-Seq-Pop](https://github.com/sanjaynagi/rna-seq-pop/) results book. Not all analyses have been ported to this book yet, other results can be found in the `results/` directory.
+
+---
+
+Sanjay C Nagi, Ambrose Oruni, David Weetman, Martin J Donnelly (2022). **RNA-Seq-Pop: Exploiting the sequence in RNA-Seq - a Snakemake workflow reveals patterns of insecticide resistance in the malaria vector Anopheles gambiae**. bioRxiv 2022.06.17.493894; doi: https://doi.org/10.1101/2022.06.17.493894
+
+---
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/5QQe7DLHO4M" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+
+---
+
+```{tableofcontents}
+```
+
+---  
+
diff --git a/docs/rna-seq-pop-results/logo.png b/docs/rna-seq-pop-results/logo.png
diff --git a/resources/multiqc.yaml b/resources/multiqc.yaml
@@ -0,0 +1,18 @@
+table_columns_visible:
+  QualiMap:
+    general_error_rate: True
+    median_insert_size: False
+sp:
+  fastp:
+    fn: "*.json"
+  qualimap/bamqc/genome_results:
+    fn: genome_results.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: coverage_histogram.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: insert_size_histogram.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: genome_fraction_coverage.txt
+  qualimap/bamqc/raw_data_qualimapReport:
+    fn: mapped_reads_gc-content_distribution.txt
+