Fix generatemutfasta FASTA headers for netMHCpan compatibility

.github/workflows/gitbook-sync.yml

@@ -47,8 +47,31 @@ jobs:
           fetch-depth: 2 # To retrieve the preceding commit.
 
       - name: Combine all tags.yml files
-        id: get_tags
-        run: find . -name "tags.yml" -not -path "./.github/*" -exec cat {} + > .github/tags.yml
+        run: |
+          echo "{}" > .github/tags.yml
+
+          for f in $(find . -name "tags.yml" -not -path "./.github/*"); do
+            if [[ "$f" == *"/modules/"* ]]; then
+              PREFIX="modules"
+            elif [[ "$f" == *"/subworkflows/"* ]]; then
+              PREFIX="subworkflows"
+            else
+              echo "Unknown feature type for $f"
+              exit 1
+            fi
+
+            yq eval "
+              with_entries(
+                .key = \"${PREFIX}/\" + .key
+              )
+            " "$f" > /tmp/tags.prefixed.yml
+
+            yq eval-all '. as $item ireduce ({}; . *+ $item)' \
+              .github/tags.yml /tmp/tags.prefixed.yml > /tmp/tags.merged.yml
+
+            mv /tmp/tags.merged.yml .github/tags.yml
+          done
+
 
       - name: debug
         run: cat .github/tags.yml
@@ -67,6 +90,7 @@ jobs:
     needs: [pytest-changes, nf-test-changes]
     strategy:
       fail-fast: false
+      max-parallel: 1
       matrix:
         tags:
           [
@@ -85,28 +109,52 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: "3.10" # install the python version needed
+      - name: Install yq
+        run: sudo apt-get update && sudo apt-get install -y yq
       - uses: actions/checkout@v4
         with:
           ref: docs
       - name: Update name of ${{ matrix.tags }}
         run: |
           MATRIX_FRAGMENT="${{ matrix.tags }}"
           TEMP_NAME=$(echo $MATRIX_FRAGMENT | sed 's/subworkflows\///g')
-          SW_NAME=$(echo $TEMP_NAME | sed 's/modules\///g')
+          SW_NAME=$(echo $TEMP_NAME | sed 's/modules\///g' | sed 's/\//\//')
           echo "SW_NAME=$SW_NAME" >> $GITHUB_ENV
       - name: Rename md file
         id: replace_slash
         run: |
           FRAGMENT="${{ env.SW_NAME }}"
-          MD_NAME=$(echo $FRAGMENT | sed 's/\//_/g')
+          if [[ "$FRAGMENT" == *"/"* ]]; then
+            DIR="$(dirname "$FRAGMENT")"
+            BASE="$(basename "$FRAGMENT")"
+            MD_PATH="${DIR}/${DIR}_${BASE}"
+          else
+            MD_PATH="$FRAGMENT"
+          fi
+
+          echo "MD_PATH=$MD_PATH" >> $GITHUB_ENV
+          MD_NAME="${FRAGMENT}"
+
+          echo "MD_PATH=$MD_PATH" >> $GITHUB_ENV
           echo "MD_NAME=$MD_NAME" >> $GITHUB_ENV
-          echo "${MD_NAME}"
       - uses: EndBug/add-and-commit@v9
         with:
           default_author: github_actions
           message: "pull changes before adding doc for ${{ matrix.tags }}"
           pull: "--rebase"
           cwd: "./"
+      - name: Ensure output folder exists and debug
+        run: |
+          echo "MD_PATH=${MD_PATH}"
+          echo "Creating folder: ./modules/$(dirname ${MD_PATH})"
+          mkdir -p ./modules/$(dirname ${MD_PATH})
+          ls -la ./modules
+      - name: Ensure parent README exists
+        run: |
+          DIR="$(dirname "$MD_PATH")"
+          if [ ! -f "./modules/$DIR/README.md" ]; then
+            echo "# $DIR" > "./modules/$DIR/README.md"
+          fi
       - name: Download convertor from yml to md
         run: |
           curl -o ${{ github.workspace }}/yaml_to_md.py https://raw.githubusercontent.com/mskcc-omics-workflows/yaml_to_md/0.0.3/yaml_to_md.py
@@ -152,24 +200,33 @@ jobs:
           echo "FEATURE_TYPE=$FEATURE_TYPE" >> $GITHUB_ENV
           echo "SUMMARY_TYPE=$SUMMARY_TYPE" >> $GITHUB_ENV
           echo "SUBWORKFLOW=$SUBWORKFLOW" >> $GITHUB_ENV
+
       - name: Run convertor to generate md file for new module
         run: |
           echo ${{ matrix.tags }}
-          python ${{ github.workspace }}/yaml_to_md.py all --yaml-file ${{ github.workspace }}/temp.yml --output-file ./${{ env.FEATURE_TYPE }}/${{ env.MD_NAME }}.md --schema-url https://raw.githubusercontent.com/mskcc-omics-workflows/yaml_to_md/0.0.3/nextflow_schema/${{ env.FEATURE_TYPE }}/meta-schema.json ${{ env.SUBWORKFLOW }}
-      - name: Check file existence for modules
-        id: check_files
-        uses: andstor/file-existence-action@v1
-        with:
-          branch: docs
-          files: ${{ env.FEATURE_TYPE}}/${{ env.MD_NAME }}.md
+          mkdir -p ./${{ env.FEATURE_TYPE }}/$(dirname $MD_PATH)
+          python ${{ github.workspace }}/yaml_to_md.py all \
+            --yaml-file ${{ github.workspace }}/temp.yml \
+            --output-file ./${{ env.FEATURE_TYPE }}/${{ env.MD_PATH }}.md \
+            --schema-url https://raw.githubusercontent.com/mskcc-omics-workflows/yaml_to_md/0.0.3/nextflow_schema/${{ env.FEATURE_TYPE }}/meta-schema.json \
+            ${{ env.SUBWORKFLOW }}
       - name: Add to SUMMARY for new features
         run: |
-          curl -o ${{ github.workspace }}/update_summary.py https://raw.githubusercontent.com/mskcc-omics-workflows/modules/develop/.github/workflows/update_summary.py
-          python ${{ github.workspace }}/update_summary.py SUMMARY.md "* [${{ env.MD_NAME }}](${{ env.FEATURE_TYPE }}/${{ env.MD_NAME }}.md)" ${{ env.SUMMARY_TYPE }} > tmp_summary.md
+          curl -o ${{ github.workspace }}/update_summary.py https://raw.githubusercontent.com/mskcc-omics-workflows/modules/release/0.2.4/.github/workflows/update_summary.py
+          python ${{ github.workspace }}/update_summary.py SUMMARY.md "${{ env.SW_NAME }}" ${{ env.SUMMARY_TYPE }} > tmp_summary.md
           mv tmp_summary.md SUMMARY.md
+      - name: Check for changes
+        run: |
+          if git diff --quiet; then
+            echo "NO_CHANGES=true" >> $GITHUB_ENV
+          fi
+      - name: Stage new files
+        run: |
+          git add "./${{ env.FEATURE_TYPE }}/${{ env.MD_PATH }}.md"
+          git add SUMMARY.md
       - uses: EndBug/add-and-commit@v9
         with:
           default_author: github_actions
           message: "add doc for ${{ matrix.tags }}"
-          add: '["*/*.md --force", "SUMMARY.md --force"]'
           cwd: "./"
+          push: --force

.github/workflows/update_summary.py

@@ -1,81 +1,78 @@
 import sys
 from collections import defaultdict
 
-
-def update_summary_old(origin: str, new_feature: str, feature_type: str):
-    out_summary = ""
-    with open(origin, 'r') as f:
-        for line in f.readlines():
-            if feature_type == "module" and line.startswith("## Subworkflows") and new_feature not in out_summary:
-                out_summary += new_feature + '\n\n'
-            if line.strip():
-                out_summary += line
-    if feature_type == "subworkflow" and new_feature not in out_summary:
-        out_summary += new_feature
-    return out_summary
-
+def build_module_entry(module_id: str):
+    if "/" in module_id:
+        namespace, name = module_id.split("/", 1)
+        display = f"{namespace}_{name}"
+        path = f"modules/{namespace}/{namespace}_{name}.md"
+        parent = namespace
+    else:
+        display = module_id
+        path = f"modules/{module_id}.md"
+        parent = None
+    entry = f"* [{display}]({path})"
+    return entry, parent
 
 def load_summary_file(origin: str):
-    # Read the summary file to dict
-    # keys, "Table of contents", "Modules", "Subworkflows"
-    # values are list of lines
     sections = defaultdict(list)
     current_section = None
-    with open(origin, "r") as file_read:
-        for row in file_read:
+    with open(origin, "r") as f:
+        for row in f:
             if row.startswith("#"):
                 current_section = row.replace("#", "").strip()
                 continue
             if row.strip():
-                sections[current_section].append(row)
+                sections[current_section].append(row.rstrip("\n"))
     return sections
 
-
 def add_new_feature(sections: dict, new_feature: str, feature_type: str):
-    new_list = []
-    found = False
     if feature_type == "module":
-        # Check if the new feature is already in current summary file
-        if new_feature.replace("\\", "") in [line.strip().replace("\\", "") for line in sections["Modules"]]:
+        entry, parent = build_module_entry(new_feature)
+        module_lines = sections["Modules"]
+
+        # Check if entry already exists
+        existing_entries = [line.strip() for line in module_lines]
+        if entry in existing_entries or f"  {entry}" in existing_entries:
             return sections
-        # Get module name from [] and remove the _ part.
-        # Check if the first part of the module name exists
-        new_feature_category = new_feature.split("]")[0].split("_")[0].replace("* [", "").replace("\\", "").strip()
-        for line in sections["Modules"]:
-            new_list.append(line)
-            if f"[{new_feature_category}]" in line:
-                found = True
-                new_list.append(f"  {new_feature}\n")
-        if not found:
-            # If not found, put the new feature to the last
-            new_list.append(new_feature + "\n\n")
-        sections["Modules"] = new_list
 
-    if feature_type == "subworkflow" and new_feature not in sections["Subworkflows"]:
-        # There is no subset of subworkflow, so put the new feature to the last
-        sections["Subworkflows"].append(new_feature + "\n")
-    return sections
+        if parent:
+            # Check if parent already exists
+            parent_line = f"* [{parent}](modules/{parent}/README.md)"
+            parent_indices = [i for i, line in enumerate(module_lines) if line.strip() == parent_line]
+            if parent_indices:
+                # Insert under existing parent
+                index = parent_indices[-1] + 1
+                module_lines.insert(index, f"  {entry}")
+            else:
+                # Add parent at end if missing, then child
+                module_lines.append(parent_line)
+                module_lines.append(f"  {entry}")
+        else:
+            module_lines.append(entry)
+
+        sections["Modules"] = module_lines
 
+    elif feature_type == "subworkflow":
+        if new_feature not in sections["Subworkflows"]:
+            sections["Subworkflows"].append(new_feature)
+    return sections
 
 def rebuild_summary(origin: str, new_feature: str, feature_type: str):
-    # Load current summary file to dictionary
-    sections = load_summary_file(origin=origin)
-    # Add the new feature to summary file dict
-    updated_sections = add_new_feature(
-        sections=sections, new_feature=new_feature, feature_type=feature_type)
-    # Output the updated summary file to string
+    sections = load_summary_file(origin)
+    sections = add_new_feature(sections, new_feature, feature_type)
+
     out_summary = "# Table of contents\n\n"
-    for line in updated_sections["Table of contents"]:
-        out_summary += line
+    for line in sections["Table of contents"]:
+        out_summary += f"{line}\n"
     out_summary += "\n## Modules\n\n"
-    for line in updated_sections["Modules"]:
-        out_summary += line
+    for line in sections["Modules"]:
+        out_summary += f"{line}\n"
     out_summary += "\n## Subworkflows\n\n"
-    for line in updated_sections["Subworkflows"]:
-        out_summary += line
+    for line in sections["Subworkflows"]:
+        out_summary += f"{line}\n"
     return out_summary
 
-
 if __name__ == "__main__":
     origin_summary = sys.argv[1]
     new_feature = sys.argv[2]

modules/msk/calculatenoise/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "YOUR-TOOL-HERE"
+  - "YOUR-TOOL=HERE"

modules/msk/calculatenoise/meta.yml

@@ -10,9 +10,9 @@ tools:
       homepage: "https://github.com/msk-access/sequence_qc"
       documentation: "https://github.com/msk-access/sequence_qc"
       tool_dev_url: "https://github.com/msk-access/sequence_qc"
-      doi: ""
+      doi: "no DOI available"
       licence: ["MIT"]
-      identifier: null
+      identifier: ""
 
 input:
   - - meta:
@@ -141,4 +141,4 @@ output:
 authors:
   - "@mikefeixu"
 maintainers:
-  - "@mikefeixu"
+  - "@mikefeixu"

modules/msk/fgbio/collectduplexseqmetrics/meta.yml

@@ -8,10 +8,10 @@ keywords:
 tools:
   - "fgbio":
       description: "A set of tools for working with genomic and high throughput sequencing data, including UMIs"
-      homepage: "None"
-      documentation: "None"
-      tool_dev_url: "None"
-      doi: ""
+      homepage: "https://github.com/fulcrumgenomics/fgbio"
+      documentation: "https://github.com/fulcrumgenomics/fgbio"
+      tool_dev_url: "https://github.com/fulcrumgenomics/fgbio"
+      doi: "no DOI available"
       licence: ["MIT"]
       identifier: biotools:fgbio
 

modules/msk/generatemutfasta/1.2/resources/usr/bin/generateMutFasta.py

@@ -118,22 +118,9 @@ def main():
                 n_missing_tx_id += 1
 
             if len(mut.mt_altered_aa) > 5:
-                id_string = (
-                    str(mut.maf_row["Transcript_ID"])
-                    + " Variant "
-                    + str(mut.maf_row["Chromosome"])
-                    + ":"
-                    + str(mut.maf_row["Start_Position"])
-                    + "-"
-                    + str(mut.maf_row["End_Position"])
-                    + " Ref:"
-                    + str(mut.maf_row["Reference_Allele"])
-                    + " Alt:"
-                    + str(mut.maf_row["Tumor_Seq_Allele2"])
-                )
-                out_fa.write(">" + id_string + "\n")
+                out_fa.write(">" + mut.identifier_key + "_M\n")
                 out_fa.write(mut.mt_altered_aa + "\n")
-                out_WT_fa.write(">" + id_string + "\n")
+                out_WT_fa.write(">" + mut.identifier_key + "_W\n")
                 out_WT_fa.write(mut.wt_altered_aa + "\n")
 
                 ### write out WT/MT CDS + AA for debugging purposes

modules/msk/generatemutfasta/1.2/tests/main.nf.test.snap

@@ -10,7 +10,7 @@
                         "id": "test",
                         "single_end": false
                     },
-                    "test.MUT.sequences.fa:md5,dff338ec438ac75aa674b64ea8e26544"
+                    "test.MUT.sequences.fa:md5,3d2ff66590a4329f9a24e03bdf84e0ab"
                 ]
             ],
             [
@@ -19,16 +19,16 @@
                         "id": "test",
                         "single_end": false
                     },
-                    "test.WT.sequences.fa:md5,51415a40a725a16eaa8f5c51fa43799e"
+                    "test.WT.sequences.fa:md5,4bfcfc4d29d01ddc4108f39350936228"
                 ]
             ],
             "test_generate_mut_fasta.log"
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "25.10.2"
+            "nextflow": "24.10.5"
         },
-        "timestamp": "2026-01-28T15:30:02.572804474"
+        "timestamp": "2026-02-09T15:03:37.884362"
     },
     "generatemutfasta_1.2 - maf - fasta - stub": {
         "content": [
@@ -96,9 +96,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.3",
-            "nextflow": "25.10.2"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.5"
         },
-        "timestamp": "2025-12-18T16:08:27.448965"
+        "timestamp": "2026-02-09T15:03:51.569621"
     }
 }