Merge branch 'main' into ionbot_parser

compomics · Sep 15, 2023 · 0b96576 · 0b96576
2 parents c6b0679 + e2cb5d4
commit 0b96576
Show file tree

Hide file tree

Showing 28 changed files with 1,356 additions and 473 deletions.
diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
@@ -8,24 +8,24 @@ jobs:
   publish:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.8'
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
 
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip flit
-        pip install --editable .[dev]
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip flit
+          pip install --editable .[dev]
 
-    - name: Test package
-      run: |
-        pytest
+      - name: Test package
+        run: |
+          pytest
 
-    - name: Build and publish to PyPI
-      env:
-        FLIT_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        FLIT_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-      run: flit publish
+      - name: Build and publish to PyPI
+        env:
+          FLIT_USERNAME: ${{ secrets.PYPI_USERNAME }}
+          FLIT_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        run: flit publish
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -10,64 +10,63 @@ jobs:
   test-with-codecov:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-    - name: Set up Python 3.8
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.8'
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
 
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flit flake8
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flit flake8
 
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+      - name: Lint with flake8
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
-    - name: Install with Flit
-      run: flit install --deps all
+      - name: Install with Flit
+        run: flit install --deps all
 
-    - name: Test with pytest and codecov
-      run: |
-        pytest --cov=psm_utils tests
-
-    - name: Upload coverage reports to Codecov
-      uses: codecov/codecov-action@v3
+      - name: Test with pytest and codecov
+        run: |
+          pytest --cov=psm_utils tests
 
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v3
 
   test-platforms:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11']
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
-    - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
 
-    - name: Install package and its dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flit flake8
+      - name: Install package and its dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flit flake8
 
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+      - name: Lint with flake8
+        run: |
+          # stop the build if there are Python syntax errors or undefined names
+          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
-    - name: Install with Flit
-      run: flit install --deps all
+      - name: Install with Flit
+        run: flit install --deps all
 
-    - name: Test with pytest
-      run: |
-        pytest
+      - name: Test with pytest
+        run: |
+          pytest
diff --git a/.gitignore b/.gitignore
@@ -1,3 +1,6 @@
+# Ruff
+.ruff_cache/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -103,7 +106,8 @@ celerybeat.pid
 
 # Environments
 .env
-.venv
+.venv/
+.venv*/
 env/
 venv/
 ENV/
@@ -127,3 +131,4 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+.vscode/settings.json
diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -1,7 +1,11 @@
 version: 2
 
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
 python:
-  version: '3.8'
   install:
     - method: pip
       path: .

diff --git a/README.rst b/README.rst
@@ -86,19 +86,20 @@ Goals and non-goals
 Supported file formats
 **********************
 
-===================================================================================================================== =============== =============== ===============
- File format                                                                                                           psm_utils tag   Read support    Write support
-===================================================================================================================== =============== =============== ===============
- `OpenMS idXML <https://www.openms.de/>`_                                                                              ``idxml``       ✅              ❌
- `MaxQuant msms.txt <https://www.maxquant.org/>`_                                                                      ``msms``        ✅              ❌
- `MS Amanda CSV <https://ms.imp.ac.at/?goto=msamanda>`_                                                                ``msamanda``    ✅              ❌
- `mzIdentML <https://psidev.info/mzidentml>`_                                                                          ``mzid``        ✅              ✅
- `Peptide Record <https://psm-utils.readthedocs.io/en/stable/api/psm_utils.io/#module-psm_utils.io.peptide_record>`_   ``peprec``      ✅              ✅
- `Percolator tab <https://github.com/percolator/percolator/wiki/Interface>`_                                           ``percolator``  ✅              ✅
- `Sage <https://github.com/lazear/sage/blob/v0.12.0/DOCS.md#interpreting-sage-output>`_                                ``sage``        ✅              ❌
- `TSV <https://psm-utils.readthedocs.io/en/stable/api/psm_utils.io/#module-psm_utils.io.tsv>`_                         ``tsv``         ✅              ✅
- `X!Tandem XML <https://www.thegpm.org/tandem/>`_                                                                      ``xtandem``     ✅              ❌
-===================================================================================================================== =============== =============== ===============
+===================================================================================================================== ======================== =============== ===============
+ File format                                                                                                           psm_utils tag            Read support    Write support
+===================================================================================================================== ======================== =============== ===============
+ `OpenMS idXML <https://www.openms.de/>`_                                                                              ``idxml``                ✅              ❌
+ `MaxQuant msms.txt <https://www.maxquant.org/>`_                                                                      ``msms``                 ✅              ❌
+ `MS Amanda CSV <https://ms.imp.ac.at/?goto=msamanda>`_                                                                ``msamanda``             ✅              ❌
+ `mzIdentML <https://psidev.info/mzidentml>`_                                                                          ``mzid``                 ✅              ✅
+ `Peptide Record <https://psm-utils.readthedocs.io/en/stable/api/psm_utils.io/#module-psm_utils.io.peptide_record>`_   ``peprec``               ✅              ✅
+ `Percolator tab <https://github.com/percolator/percolator/wiki/Interface>`_                                           ``percolator``           ✅              ✅
+ Proteome Discoverer MSF                                                                                               ``proteome_discoverer``  ✅              ❌
+ `Sage <https://github.com/lazear/sage/blob/v0.12.0/DOCS.md#interpreting-sage-output>`_                                ``sage``                 ✅              ❌
+ `TSV <https://psm-utils.readthedocs.io/en/stable/api/psm_utils.io/#module-psm_utils.io.tsv>`_                         ``tsv``                  ✅              ✅
+ `X!Tandem XML <https://www.thegpm.org/tandem/>`_                                                                      ``xtandem``              ✅              ❌
+===================================================================================================================== ======================== =============== ===============
 
 Legend: ✅ Supported, ❌ Unsupported
 

diff --git a/docs/source/api/psm_utils.io.rst b/docs/source/api/psm_utils.io.rst
@@ -8,7 +8,7 @@ psm_utils.io
 
 
 psm_utils.io.idxml
-#####################
+##################
 
 .. automodule:: psm_utils.io.idxml
    :members:
@@ -25,7 +25,7 @@ psm_utils.io.maxquant
 
 
 psm_utils.io.msamanda
-##########################
+#####################
 
 .. automodule:: psm_utils.io.msamanda
    :members:
@@ -34,7 +34,7 @@ psm_utils.io.msamanda
 
 
 psm_utils.io.mzid
-#####################
+#################
 
 .. automodule:: psm_utils.io.mzid
    :members:
@@ -52,16 +52,24 @@ psm_utils.io.peptide_record
 
 
 psm_utils.io.percolator
-###########################
+#######################
 
 .. automodule:: psm_utils.io.percolator
    :members:
    :inherited-members:
 
 
 
+psm_utils.io.proteome_discoverer
+################################
+.. automodule:: psm_utils.io.proteome_discoverer
+   :members:
+   :inherited-members:
+
+
+
 psm_utils.io.sage
-###########################
+#################
 
 .. automodule:: psm_utils.io.sage
    :members:
@@ -70,7 +78,7 @@ psm_utils.io.sage
 
 
 psm_utils.io.tsv
-##########################
+################
 
 .. automodule:: psm_utils.io.tsv
    :members:
@@ -79,7 +87,7 @@ psm_utils.io.tsv
 
 
 psm_utils.io.xtandem
-##########################
+####################
 
 .. automodule:: psm_utils.io.xtandem
    :members:

diff --git a/online/pages/1_PSM_file_statistics.py b/online/pages/1_PSM_file_statistics.py
@@ -92,14 +92,14 @@ def _input_form(self):
                     "Score type: order",
                     options=[True, False],
                     format_func=lambda x: "Higher score is better"
-                    if x == True
+                    if x
                     else "Lower score is better",
                 )
                 self.state["log_scale"] = row[1].radio(
                     "Score type: scale",
                     options=[False, True],
                     format_func=lambda x: "Logarithmic scale (e.g., e-value)"
-                    if x == True
+                    if x
                     else "Linear scale (e.g., Andromeda score)",
                     help=(
                         """
@@ -142,9 +142,7 @@ def _read_file(self):
                 # Write file to disk for psm_utils; then read
                 with NamedTemporaryFile(mode="wb", delete=False) as tmp_file:
                     if self.state["input_file"].name.lower().endswith(".gz"):
-                        tmp_file.write(
-                            gzip.decompress(self.state["input_file"].getvalue())
-                        )
+                        tmp_file.write(gzip.decompress(self.state["input_file"].getvalue()))
                     else:
                         tmp_file.write(self.state["input_file"].getvalue())
                     tmp_file.flush()
@@ -179,7 +177,7 @@ def _prepare_psms(self):
             )
 
         # If no q-values, try to calculate
-        if (psm_list["qvalue"] == None).any():
+        if (psm_list["qvalue"] == None).any():  # noqa: E711
             # If no decoys, display error
             if percent_decoys == 0.0:
                 st.error(
@@ -231,13 +229,9 @@ def _show_results(self):
 
         n_collections = psm_df["collection"].unique().shape[0]
         n_runs = psm_df[["run", "collection"]].drop_duplicates().shape[0]
-        n_spectra = (
-            psm_df[["spectrum_id", "run", "collection"]].drop_duplicates().shape[0]
-        )
+        n_spectra = psm_df[["spectrum_id", "run", "collection"]].drop_duplicates().shape[0]
         n_psms = psm_df.shape[0]
-        n_peptidoforms = (
-            psm_df["peptidoform"].apply(lambda x: x.proforma).unique().shape[0]
-        )
+        n_peptidoforms = psm_df["peptidoform"].apply(lambda x: x.proforma).unique().shape[0]
         percent_decoys = np.count_nonzero(psm_list["is_decoy"]) / len(psm_list)
 
         row_1 = st.columns(3)
@@ -262,19 +256,12 @@ def _show_results(self):
         else:
             psm_df_filtered = psm_df[psm_df["qvalue"] <= self.state["fdr_threshold"]]
             n_spectra = (
-                psm_df_filtered[["spectrum_id", "run", "collection"]]
-                .drop_duplicates()
-                .shape[0]
+                psm_df_filtered[["spectrum_id", "run", "collection"]].drop_duplicates().shape[0]
             )
             n_psms = psm_df_filtered.shape[0]
-            n_peptides = (
-                psm_df["peptidoform"].apply(lambda x: x.sequence).unique().shape[0]
-            )
+            n_peptides = psm_df["peptidoform"].apply(lambda x: x.sequence).unique().shape[0]
             n_peptidoforms = (
-                psm_df_filtered["peptidoform"]
-                .apply(lambda x: x.proforma)
-                .unique()
-                .shape[0]
+                psm_df_filtered["peptidoform"].apply(lambda x: x.proforma).unique().shape[0]
             )
 
             row_3 = st.columns(4)

diff --git a/psm_utils/io/__init__.py b/psm_utils/io/__init__.py
@@ -14,6 +14,7 @@
 import psm_utils.io.mzid as mzid
 import psm_utils.io.peptide_record as peptide_record
 import psm_utils.io.percolator as percolator
+import psm_utils.io.proteome_discoverer as proteome_discoverer
 import psm_utils.io.sage as sage
 import psm_utils.io.tsv as tsv
 import psm_utils.io.xtandem as xtandem
@@ -54,6 +55,12 @@
         "extension": ".percolator.txt",
         "filename_pattern": r"^.*\.(?:(?:pin)|(?:pout))$",
     },
+    "proteome_discoverer": {
+        "reader": proteome_discoverer.MSFReader,
+        "writer": None,
+        "extension": ".msf",
+        "filename_pattern": r"^.*\.msf$",
+    },
     "tsv": {
         "reader": tsv.TSVReader,
         "writer": tsv.TSVWriter,