Fix/xl percolator gen features

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: [email protected]
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.7.7
+version: 0.7.8
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.7.7 " # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.7.7 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.7.8 " # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.7.8 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.7.7
+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 = "0.7.7"
+version = "0.7.8"
 # The full version, including alpha/beta/rc tags.
-release = "0.7.7"
+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 = "0.7.7"  # <<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__ = "0.7.7"
+__version__ = "0.7.8"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.7.7", message=click.style("spectrum_fundamentals Version: 0.7.7"))
+@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

@@ -510,7 +510,7 @@ 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",
@@ -97,8 +99,6 @@ def __init__(
             "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:
         """
@@ -327,12 +327,12 @@ 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"]

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
+            )