Merge remote-tracking branch 'origin/development' into features/ptm_p…

…ipeline

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: victor.giurcoiu@tum.de
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.7.4
+version: 0.7.8
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.7.4 " # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.7.4 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.7.8 " # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.7.8 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/build_package.yml

@@ -16,7 +16,7 @@ jobs:
               name: Check out source-code repository
 
             - name: Setup Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: ${{ matrix.python }}
 

.github/workflows/main_master_branch_protection.yml

@@ -40,7 +40,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             - name: Set up Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: "3.9"
             # PRs to the repository master branch are only ok if coming from any patch or release branch

.github/workflows/publish_docs.yml

@@ -11,7 +11,7 @@ jobs:
               name: Check out source-code repository
 
             - name: Setup Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: 3.9
 

.github/workflows/publish_package.yml

@@ -15,7 +15,7 @@ jobs:
                   fetch-depth: 2
 
             - name: Set up Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: "3.9"
 
@@ -29,7 +29,7 @@ jobs:
                   poetry build --ansi
 
             - name: Publish package on PyPI
-              uses: pypa/gh-action-pypi-publish@v1.9.0
+              uses: pypa/gh-action-pypi-publish@v1.10.3
               with:
                   # TODO COOKIETEMPLE: Configure your PyPI Token to enable automatic deployment to PyPi on releases
                   # https://help.github.com/en/actions/configuring-and-managing-workflows/creating-and-storing-encrypted-secrets

.github/workflows/run_cookietemple_lint.yml

@@ -11,7 +11,7 @@ jobs:
               name: Check out source-code repository
 
             - name: Setup Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: 3.9
 

.github/workflows/run_tests.yml

@@ -72,7 +72,7 @@ jobs:
               uses: actions/checkout@v4
 
             - name: Set up Python ${{ matrix.python-version }}
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: ${{ matrix.python-version }}
 
@@ -138,7 +138,7 @@ jobs:
               uses: actions/checkout@v4
 
             - name: Set up Python 3.9
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: 3.9
 
@@ -166,4 +166,4 @@ jobs:
               run: nox --force-color --session=coverage -- xml -i
 
             - name: Upload coverage report
-              uses: codecov/codecov-action@v4.5.0
+              uses: codecov/codecov-action@v4.6.0

.github/workflows/sync_project.yml

@@ -10,7 +10,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             - name: Setup Python
-              uses: actions/setup-python@v5.1.1
+              uses: actions/setup-python@v5.2.0
               with:
                   python-version: 3.9
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.7.4
+current_version = 0.7.8
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_fundamentals/__init__.py

docs/conf.py

@@ -52,9 +52,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.7.4"
+version = "0.7.8"
 # The full version, including alpha/beta/rc tags.
-release = "0.7.4"
+release = "0.7.8"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "spectrum_fundamentals"
-version = "0.7.4"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.7.8"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "Fundamental functions, annotation pipeline and constants for oktoberfest"
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"

spectrum_fundamentals/__init__.py

@@ -5,7 +5,7 @@
 __author__ = """The Oktoberfest development team (Wilhelmlab at Technical University of Munich)"""
 __copyright__ = f"Copyright {datetime.now():%Y}, Wilhelmlab at Technical University of Munich"
 __license__ = "MIT"
-__version__ = "0.7.4"
+__version__ = "0.7.8"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.7.4", message=click.style("spectrum_fundamentals Version: 0.7.4"))
+@click.version_option(version="0.7.8", message=click.style("spectrum_fundamentals Version: 0.7.8"))
 def main() -> None:
     """spectrum_fundamentals."""
 

spectrum_fundamentals/constants.py

@@ -555,7 +555,7 @@ class RescoreType(Enum):
 
 CHARGES = [1, 2, 3]  # limited to uint8 (0-255) when array is created
 POSITIONS = [x for x in range(1, 30)]  # fragment numbers 1-29 -- limited to uint8 (0-255) when array is created
-
+POSITIONS_XL = [x for x in range(1, 59)]
 ANNOTATION_FRAGMENT_TYPE = []
 ANNOTATION_FRAGMENT_CHARGE = []
 ANNOTATION_FRAGMENT_NUMBER = []

spectrum_fundamentals/metrics/percolator.py

@@ -62,6 +62,8 @@ def __init__(
         drop_miss_cleavage_flag: Optional[bool] = False,
     ):
         """Initialize a Percolator obj."""
+        super().__init__(pred_intensities, true_intensities, mz, "CROSSLINKER_TYPE" in metadata.columns)
+
         self.metadata = metadata
         self.input_type = input_type
         self.all_features_flag = all_features_flag
@@ -70,7 +72,7 @@ def __init__(
         self.fdr_cutoff = fdr_cutoff
         self.neutral_loss_flag = neutral_loss_flag
         self.drop_miss_cleavage_flag = drop_miss_cleavage_flag
-        self.xl = "CROSSLINKER_TYPE" in self.metadata.columns
+
         self.base_columns = [
             "raw_file",
             "scan_number",
@@ -94,10 +96,9 @@ def __init__(
             "mass_analyzer",
             "mz_range",
             "collision_energy",
+            "proteins",
         ]
 
-        super().__init__(pred_intensities, true_intensities, mz)
-
     @staticmethod
     def sample_balanced_over_bins(retention_time_df: pd.DataFrame, sample_size: int = 5000) -> pd.Index:
         """
@@ -328,19 +329,17 @@ def add_percolator_metadata_columns(self):
         """Add metadata columns needed by percolator, e.g. to identify a PSM."""
         if self.xl:
             spec_id_cols = ["RAW_FILE", "SCAN_NUMBER", "MODIFIED_SEQUENCE_A", "MODIFIED_SEQUENCE_B", "PRECURSOR_CHARGE"]
-            self.metrics_val["Peptide"] = (
-                self.metadata["MODIFIED_SEQUENCE_A"] + "_" + self.metadata["MODIFIED_SEQUENCE_B"]
-            ).apply(lambda x: "_." + x + "._")
-            self.metrics_val["Proteins"] = (
-                self.metadata["MODIFIED_SEQUENCE_A"] + "_" + self.metadata["MODIFIED_SEQUENCE_B"]
+            modified_sequence_a = self.metadata["MODIFIED_SEQUENCE_A"].astype(str)
+            modified_sequence_b = self.metadata["MODIFIED_SEQUENCE_B"].astype(str)
+            self.metrics_val["Peptide"] = (modified_sequence_a + "_" + modified_sequence_b).apply(
+                lambda x: "_." + x + "._"
             )
+            self.metrics_val["Proteins"] = modified_sequence_a + "_" + modified_sequence_b
             self.metrics_val["Label"] = self.target_decoy_labels
         else:
             spec_id_cols = ["RAW_FILE", "SCAN_NUMBER", "MODIFIED_SEQUENCE", "PRECURSOR_CHARGE"]
             self.metrics_val["Peptide"] = self.metadata["MODIFIED_SEQUENCE"].apply(lambda x: "_." + x + "._")
-            self.metrics_val["Proteins"] = self.metadata[
-                "MODIFIED_SEQUENCE"
-            ]  # we don't need the protein ID to get PSM / peptide results, fill with peptide sequence
+            self.metrics_val["Proteins"] = self.metadata["PROTEINS"]
 
         if "SCAN_EVENT_NUMBER" in self.metadata.columns:
             spec_id_cols.append("SCAN_EVENT_NUMBER")
@@ -469,6 +468,11 @@ def calc(self):  # noqa: C901
             if self.neutral_loss_flag:
                 self.metrics_val["ANNOTATED_NL_COUNT"] = self.metadata["ANNOTATED_NL_COUNT"]
                 self.metrics_val["EXPECTED_NL_COUNT"] = self.metadata["EXPECTED_NL_COUNT"]
+                columns_to_remove = []
+                for col in self.metrics_val.columns:
+                    if "vs_predicted" in col:
+                        columns_to_remove.append(col)
+                self.metrics_val.drop(columns=columns_to_remove, inplace=True)
             if self.drop_miss_cleavage_flag:
                 self.metrics_val.drop(columns=["missedCleavages", "KR"], inplace=True)
             if self.xl:

spectrum_fundamentals/metrics/similarity.py

@@ -481,9 +481,6 @@ def _calc_additional_metrics(
             true_intensities, pred_intensities, "max"
         )
         self.metrics_val[f"mse{key_suffix}"] = SimilarityMetrics.abs_diff(true_intensities, pred_intensities, "mse")
-        self.metrics_val[f"modified_cosine{key_suffix}"] = SimilarityMetrics.modified_cosine(
-            true_intensities, pred_intensities, self.mz, self.mz
-        )
 
         col_names_spectral_angle = [
             f"spectral_angle_{amount}_charge{key_suffix}" for amount in ["single", "double", "triple"]
@@ -539,3 +536,7 @@ def _calc_additional_metrics(
                 self.metrics_val[col_name_spearman_corr] = SimilarityMetrics.correlation(
                     true_intensities, pred_intensities, i + 1, "spearman"
                 )
+
+            self.metrics_val[f"modified_cosine{key_suffix}"] = SimilarityMetrics.modified_cosine(
+                true_intensities, pred_intensities, self.mz, self.mz
+            )

tests/unit_tests/data/perc_input.csv

@@ -1,9 +1,9 @@
-,RAW_FILE,SCAN_NUMBER,MODIFIED_SEQUENCE,SEQUENCE,PRECURSOR_CHARGE,MASS,CALCULATED_MASS,SCORE,REVERSE,FRAGMENTATION,MASS_ANALYZER,SCAN_EVENT_NUMBER,RETENTION_TIME,PREDICTED_IRT,COLLISION_ENERGY
-0,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,7978,AAIGEATRL,AAIGEATRL,2,900.50345678,900.50288029264,60.43600000000001,False,HCD,FTMS,1,0.5000000183883155,0.5000000323590892,30.0
-1,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12304,AAVPRAAFL,AAVPRAAFL,2,914.53379,914.53379,34.006,True,HCD,FTMS,2,1.000000038995633,1.5000000246189773,30.0
-2,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12398,AAYFGVYDTAK,AAYFGVYDTAK,2,1204.5764,1204.5764,39.97399999999999,True,HCD,FTMS,3,1.5000000993570157,2.500000056694346,30.0
-3,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,11716,AAYYHPSYL,AAYYHPSYL,2,1083.5025,1083.5025,99.919,False,HCD,FTMS,4,2.0000000098074193,3.5000000203256407,30.0
-4,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,87.802,False,HCD,FTMS,5,2.500000083793533,4.5000000747038005,30.0
-5,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,62.802,False,HCD,FTMS,6,3.0000000338727677,5.5000000960095505,30.0
-6,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,False,HCD,FTMS,7,3.500000001673834,6.5000000134594345,30.0
-7,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,False,HCD,FTMS,8,4.000000066050141,7.500000085284446,30.0
+,RAW_FILE,SCAN_NUMBER,MODIFIED_SEQUENCE,SEQUENCE,PRECURSOR_CHARGE,MASS,CALCULATED_MASS,SCORE,REVERSE,FRAGMENTATION,MASS_ANALYZER,SCAN_EVENT_NUMBER,RETENTION_TIME,PREDICTED_IRT,COLLISION_ENERGY,PROTEINS
+0,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,7978,AAIGEATRL,AAIGEATRL,2,900.5034568,900.5028803,60.436,FALSE,HCD,FTMS,1,0.500000018,0.500000032,30,sp|O23523|RGGA_ARATH
+1,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12304,AAVPRAAFL,AAVPRAAFL,2,914.53379,914.53379,34.006,TRUE,HCD,FTMS,2,1.000000039,1.500000025,30,sp|O23523|RGGA_ARATH
+2,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12398,AAYFGVYDTAK,AAYFGVYDTAK,2,1204.5764,1204.5764,39.974,TRUE,HCD,FTMS,3,1.500000099,2.500000057,30,sp|O23523|RGGA_ARATH
+3,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,11716,AAYYHPSYL,AAYYHPSYL,2,1083.5025,1083.5025,99.919,FALSE,HCD,FTMS,4,2.00000001,3.50000002,30,sp|O23523|RGGA_ARATH
+4,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,87.802,FALSE,HCD,FTMS,5,2.500000084,4.500000075,30,sp|O23523|RGGA_ARATH
+5,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,62.802,FALSE,HCD,FTMS,6,3.000000034,5.500000096,30,sp|O23523|RGGA_ARATH
+6,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,FALSE,HCD,FTMS,7,3.500000002,6.500000013,30,sp|O23523|RGGA_ARATH
+7,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,FALSE,HCD,FTMS,8,4.000000066,7.500000085,30,sp|O23523|RGGA_ARATH

tests/unit_tests/test_percolator.py

@@ -395,7 +395,7 @@ def test_calc(self):
         # np.testing.assert_almost_equal(percolator.metrics_val['ExpMass'][0], 900.50345678)
         np.testing.assert_string_equal(percolator.metrics_val["Peptide"][0], "_.AAIGEATRL._")
         np.testing.assert_string_equal(
-            percolator.metrics_val["Proteins"][0], "AAIGEATRL"
+            percolator.metrics_val["Proteins"][0], "sp|O23523|RGGA_ARATH"
         )  # we don't need the protein ID to get PSM / peptide results
 
         # features