Merge pull request #37 from lehtiolab/dev

version 3.1
lehtiolab · Feb 3, 2025 · 0e07cb7 · 0e07cb7
2 parents 44dc69f + 6f5abe9
commit 0e07cb7
Show file tree

Hide file tree

Showing 37 changed files with 872 additions and 232 deletions.
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -10,13 +10,21 @@ jobs:
   create-container:
     uses: ./.github/workflows/container.yml
 
-  run-all-tests:
+  run-all-tests-sage:
     needs: create-container
+    env:
+      SEARCH: sage
+    uses: ./.github/workflows/tests_all.yml
+
+  run-all-tests-msgf:
+    needs: create-container
+    env:
+      SEARCH: msgf
     uses: ./.github/workflows/tests_all.yml
 
   create-release:  
     runs-on: ubuntu-latest
-    needs: run-all-tests
+    needs: [run-all-tests-sage, run-all-tests-msgf]
     steps:
       - uses: ncipollo/release-action@v1
         with:

diff --git a/.github/workflows/single_test.yml b/.github/workflows/single_test.yml
@@ -20,4 +20,4 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run single test
-            run: bash run_tests.sh tmt16_fast
+            run: bash run_tests.sh sage tmt16_fast
diff --git a/.github/workflows/tests_all.yml b/.github/workflows/tests_all.yml
@@ -15,7 +15,7 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh tmt16
+            run: bash run_tests.sh $SEARCH tmt16
 
     test-tmt18:
         runs-on: ubuntu-latest
@@ -27,7 +27,7 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh tmt18
+            run: bash run_tests.sh $SEARCH tmt18
 
     test-labelfree:
         runs-on: ubuntu-latest
@@ -39,7 +39,7 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh labelfree
+            run: bash run_tests.sh $SEARCH labelfree
 
     test-lf_phos:
         runs-on: ubuntu-latest
@@ -51,7 +51,7 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh labelfree_phos
+            run: bash run_tests.sh $SEARCH labelfree_phos
 
     test-tims:
         runs-on: ubuntu-latest
@@ -63,7 +63,7 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh tims
+            run: bash run_tests.sh $SEARCH tims
 
     test-mixed-tmt:
         runs-on: ubuntu-latest
@@ -75,4 +75,4 @@ jobs:
             uses: nf-core/setup-nextflow@v2
 
           - name: Run tests
-            run: bash run_tests.sh tmt16_18
+            run: bash run_tests.sh $SEARCH tmt16_18
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,16 @@
 # lehtiolab/ddamsproteomics: Changelog
 
+## Version 3.1 [2025-02-03]
+- Search engine choice of Sage / MSGF
+- QC plots changes in colors, max PSM use in isobaric step, PCA for sets even when sample groups
+- Tables for PSM results in report
+- Possible to remove (e.g. empty) channel for specific set
+- Fixed volcano plots
+- Error early on incorrect totalproteome / remove channel set names
+- Output ExplainedIonCurrentRatio in MSGF PSM table (msstitch to 3.17)
+- OpenMS to 3.2, MSGFPlus to 2024.03.26, Percolator to 3.6.5
+
+
 ## Version 3.0 [2024-09-19]
 - Rewrote in DSL2
 - QC report with plotly

diff --git a/README.md b/README.md
@@ -18,16 +18,16 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
 - run pipeline:
 
 ```
-nextflow run lehtiolab/ddamsproteomics --input /path/to/input_definition.txt --tdb /path/to/proteins.fa --mods 'oxidation;carbamidomethylation' -profile standard,docker
+nextflow run lehtiolab/ddamsproteomics --input /path/to/input_definition.txt --sage --tdb /path/to/proteins.fa --mods 'oxidation;carbamidomethylation' -profile standard,docker
 ```
 
 Or for two sample sets of isobaric data you can:
 
 ```
-nextflow run lehtiolab/ddamsproteomics --input /path/to/input_definition.txt --tdb /path/to/proteins.fa --mods 'oxidation;carbamidomethylation --isobaric 'setA:tmt10plex:126 setB:tmt10plex:127N'
+nextflow run lehtiolab/ddamsproteomics --input /path/to/input_definition.txt --sage --tdb /path/to/proteins.fa --mods 'oxidation;carbamidomethylation --isobaric 'setA:tmt10plex:126 setB:tmt10plex:127N'
 ```
 
-For more elaborate examples covering fractionation, PTMs, and more, the lehtiolab/ddamsproteomics pipeline comes with documentation about the pipeline, found in the `docs/` directory:
+For more elaborate examples covering fractionation, MSGF+, PTMs, and more, the lehtiolab/ddamsproteomics pipeline comes with documentation about the pipeline, found in the `docs/` directory:
 
 - [Running the pipeline](docs/usage.md)
 - [Output and how to interpret the results](docs/output.md)

diff --git a/assets/report.html b/assets/report.html
@@ -28,9 +28,12 @@ <h4 class="subtitle is-4">
           {% if ptmtables.summary %}
           <li id="ptmqctab"> <a> PTMs </a> </li>
           {% endif %}
-          {% if expplots.pca %}
+          {% if expplots.pcagroup %}
           <li id="deqctab"><a>Expression</a> </li>
           {% endif %}
+          {% if expplots.pcaset %}
+          <li id="pcatab"><a>PCA</a> </li>
+          {% endif %}
           <li id="rundatatab"><a>Run data</a></li>
         </ul>
       </div>
@@ -95,6 +98,52 @@ <h5 class="title is-5">{{ ftitle }}</h5>
         {% endfor %}
       </div>
 
+      <h4 class="title is-4">PSMs</h4>
+      <div class="columns">
+        <div class="column">
+          <h5 class="title is-5">IDs</h5>
+          <table class="table is-striped is-narrow is-hoverable is-size-7">
+            <thead>
+              <th>Sample/plate</th>
+              <th>Scans</th>
+              <th>PSMs</th>
+              <th>% ID</th>
+            </thead>
+            <tbody>
+              {% for plate, scans, psms, pc in psmtables.ids %}
+              <tr>
+                <td> {{ plate }} </td>
+                <td> {{ scans }} </td>
+                <td> {{ psms }} </td>
+                <td> {{ pc }} </td>
+              </tr>
+              {% endfor %}
+            </tbody>
+          </table>
+        </div>
+        <div class="column">
+          <h5 class="title is-5">Missed cleavages</h5>
+          <table class="table is-striped is-narrow is-hoverable is-size-7">
+            <thead>
+              <th>Sample/plate</th>
+              <th># missed cleavages</th>
+              <th># PSMs</th>
+              <th>% PSMs</th>
+            </thead>
+            <tbody>
+              {% for plate, mc, psms, pc in psmtables.miscleav %}
+              <tr>
+                <td> {{ plate }} </td>
+                <td> {{ mc }} </td>
+                <td> {{ psms }} </td>
+                <td> {{ pc }} </td>
+              </tr>
+              {% endfor %}
+            </tbody>
+          </table>
+        </div>
+      </div>
+
       {% if ptmtables.summary %}
       <h4 class="title is-4">PTMs</h4>
       <div class="columns">
@@ -360,7 +409,7 @@ <h5 class="title is-5">{{ ftitle }}</h5>
     </div>
     {% endif %}
 
-    {% if expplots.pca %}
+    {% if expplots.pcagroup %}
     <div id="deqcpage" class="mt-5 container">
       {% for plotname, plottitle in expplotnames %}
       <h4 class="title is-4">{{ plottitle }}</h4>
@@ -397,6 +446,24 @@ <h5 class="title is-5">{{ ftitle }}</h5>
     </div>
     {% endif %}
 
+    {% if expplots.pcaset %}
+    <div id="pcapage" class="mt-5 container">
+      {% for plotname, plottitle in pcaplotnames %}
+      <h4 class="title is-4">{{ plottitle }}</h4>
+      <div class="columns">
+        {% for fname, ftitle in featnames %}
+        {% if expplots[plotname][fname] %}
+        <div class="column">
+          <h5 class="title is-5">{{ ftitle }}</h5>
+          {{ expplots[plotname][fname] }}
+        </div>
+        {% endif %}
+        {% endfor %}
+      </div>
+      {% endfor %}
+    </div>
+    {% endif %}
+
     <script type="text/javascript">
       let tabs = [
         ['results', document.getElementById('resultstab'), document.getElementById('resultspage')],
@@ -406,9 +473,12 @@ <h5 class="title is-5">{{ ftitle }}</h5>
         {% if ptmtables.summary %}
         ['ptmqc', document.getElementById('ptmqctab'), document.getElementById('ptmqcpage')],
         {% endif %}
-        {% if expplots.pca %}
+        {% if expplots.pcagroup %}
         ['deqc', document.getElementById('deqctab'), document.getElementById('deqcpage')],
         {% endif %}
+        {% if expplots.pcaset %}
+        ['pca', document.getElementById('pcatab'), document.getElementById('pcapage')],
+        {% endif %}
       ];
       tabs.forEach(t => {
         t[1].addEventListener('click', e => toggleTab(t[0]));

diff --git a/assets/sage.json b/assets/sage.json
@@ -0,0 +1,46 @@
+{
+  "database": {
+    "bucket_size": 8192,
+    "enzyme": {
+      "missed_cleavages": 2,
+      "min_len": 7,
+      "max_len": 50,
+      "cleave_at": "KR",
+      "restrict": "P",
+      "c_terminal": true
+    },
+    "fragment_min_mz": 200.0,
+    "fragment_max_mz": 2000.0,
+    "peptide_min_mass": 500.0,
+    "peptide_max_mass": 5000.0,
+    "ion_kinds": ["a", "b", "y"],
+    "min_ion_index": 2,
+    "static_mods": {
+      "C": 57.0215
+    },
+    "variable_mods": {
+      "M": [15.9949]
+    },
+    "max_variable_mods": 2,
+    "decoy_tag": "decoy_",
+    "generate_decoys": false
+  },
+  "precursor_tol": {
+    "ppm": [-10, 10]
+  },
+  "fragment_tol": {
+    "ppm": [-20, 20]
+  },
+  "precursor_charge": [2, 6],
+  "isotope_errors": [ -1, 2 ],
+  "deisotope": false,
+  "chimera": false,
+  "wide_window": false,
+  "predict_rt": false,
+  "min_peaks": 7,
+  "max_peaks": 150,
+  "min_matched_peaks": 3,
+  "max_fragment_charge": 2,
+  "report_psms": 1,
+  "output_directory": "./"
+}
diff --git a/bin/create_modfile.py b/bin/create_modfile.py
@@ -1,22 +1,29 @@
 #!/usr/bin/env python3
 
 import sys
+import json
 from mods import Mods
 
 
 def main():
     nummods = sys.argv[1]
     modlibfile = sys.argv[2]
-    passed_mods = sys.argv[3].split(';')
+    search_engine = sys.argv[3]
+    passed_mods = sys.argv[4].split(';')
     fixedmods = {}
     varmods = []
     # Parse modifications passed
-    msgfmods = Mods()
-    msgfmods.parse_msgf_modfile(modlibfile, passed_mods)
-    with open('mods.txt', 'w') as fp:
-        fp.write('NumMods={}'.format(nummods))
-        for modline in msgfmods.get_msgf_modlines():
-            fp.write(f'\n{modline}')
+    parsemods = Mods()
+    parsemods.parse_msgf_modfile(modlibfile, passed_mods)
+    modfn = 'mods.txt'
+    if search_engine == 'msgf':
+        with open(modfn, 'w') as fp:
+            fp.write('NumMods={}'.format(nummods))
+            for modline in parsemods.get_msgf_modlines():
+                fp.write(f'\n{modline}')
+    elif search_engine == 'sage':
+        with open(modfn, 'w') as fp:
+            json.dump(parsemods.get_sage_mods(), fp)
 
 
 if __name__ == '__main__':