Merge branch 'development' of github.com:wilhelm-lab/spectrum_fundame…

…ntals into development

spectrum_fundamentals/metrics/percolator.py

@@ -1,8 +1,5 @@
 import enum
-import hashlib
 import logging
-import re
-import subprocess
 from typing import Optional, Tuple, Union
 
 import numpy as np
@@ -60,26 +57,15 @@ def __init__(
         all_features_flag: bool = False,
         regression_method: str = "lowess",
         fdr_cutoff: float = 0.01,
-        percolator_version: Optional[float] = 3.05,
     ):
         """Initialize a Percolator obj."""
         self.metadata = metadata
         self.input_type = input_type
         self.all_features_flag = all_features_flag
         self.regression_method = regression_method
         self.fdr_cutoff = fdr_cutoff
-
-        self._resolve_percolator_compatibility(percolator_version)
         super().__init__(pred_intensities, true_intensities, mz)
 
-    def _resolve_percolator_compatibility(self, percolator_version: Optional[float] = None):
-        if percolator_version is None:
-            result = subprocess.run(["percolator", "-h"], capture_output=True, text=True)
-            version_line = result.stderr.splitlines()[0].strip()
-            version = version_line.split("version ")[1]
-            percolator_version = float(re.sub(r"\.[^.]+$", "", version))
-        self.prot_col_name = "Proteins" if percolator_version >= 3.06 else "Protein"
-
     @staticmethod
     def sample_balanced_over_bins(retention_time_df: pd.DataFrame, sample_size: int = 5000) -> pd.Index:
         """
@@ -170,18 +156,6 @@ def get_aligned_predicted_retention_times(
 
         return aligned_rts_predicted
 
-    @staticmethod
-    def get_scannr(metadata_subset: Union[pd.Series, Tuple[str, int]]) -> int:
-        """
-        Creates a hash of the raw_file and scan number to use as a unique scan number in percolator.
-
-        :param metadata_subset: tuple of (raw_file, scan_number)
-        :return: hashed unique id
-        """
-        raw_file, scan_number = metadata_subset
-        s = f"{raw_file}{scan_number}".encode()
-        return int(hashlib.sha224(s).hexdigest()[:6], 16)
-
     @staticmethod
     def get_delta_score(scores_df: pd.DataFrame, scoring_feature: str) -> np.ndarray:
         """
@@ -296,11 +270,11 @@ def add_percolator_metadata_columns(self):
             spec_id_cols.append("SCAN_EVENT_NUMBER")
         self.metrics_val["SpecId"] = self.metadata[spec_id_cols].apply(Percolator.get_specid, axis=1)
         self.metrics_val["Label"] = self.target_decoy_labels
-        self.metrics_val["ScanNr"] = self.metadata[["RAW_FILE", "SCAN_NUMBER"]].apply(Percolator.get_scannr, axis=1)
-
+        self.metrics_val["ScanNr"] = self.metadata["SCAN_NUMBER"]
+        self.metrics_val["filename"] = self.metadata["RAW_FILE"]
         self.metrics_val["Peptide"] = self.metadata["MODIFIED_SEQUENCE"].apply(lambda x: "_." + x + "._")
 
-        self.metrics_val[self.prot_col_name] = self.metadata[
+        self.metrics_val["Proteins"] = self.metadata[
             "MODIFIED_SEQUENCE"
         ]  # we don't need the protein ID to get PSM / peptide results, fill with peptide sequence
 
@@ -397,8 +371,8 @@ def fdrs_to_qvals(fdrs: np.ndarray) -> np.ndarray:
 
     def _reorder_columns_for_percolator(self):
         all_columns = self.metrics_val.columns
-        first_columns = ["SpecId", "Label", "ScanNr"]
-        last_columns = ["Peptide", "Protein"] if "Protein" in all_columns else ["Peptide", "Proteins"]
+        first_columns = ["SpecId", "Label", "ScanNr", "filename"]
+        last_columns = ["Peptide", "Proteins"]
         mid_columns = list(set(all_columns) - set(first_columns) - set(last_columns))
         new_columns = first_columns + sorted(mid_columns) + last_columns
         self.metrics_val = self.metrics_val[new_columns]

tests/unit_tests/data/perc_output.csv

@@ -1,4 +1,4 @@
-,SpecId,Label,ScanNr,CID,Charge1,Charge2,Charge3,Charge4,Charge5,Charge6,HCD,KR,Mass,RT,UnknownFragmentationMethod,abs_rt_diff,collision_energy_aligned,count_not_observed_and_not_predicted,count_not_observed_and_not_predicted_b,count_not_observed_and_not_predicted_y,count_not_observed_but_predicted,count_not_observed_but_predicted_b,count_not_observed_but_predicted_y,count_observed,count_observed_and_predicted,count_observed_and_predicted_b,count_observed_and_predicted_y,count_observed_b,count_observed_but_not_predicted,count_observed_but_not_predicted_b,count_observed_but_not_predicted_y,count_observed_y,count_predicted,count_predicted_b,count_predicted_y,fraction_not_observed_and_not_predicted,fraction_not_observed_and_not_predicted_b,fraction_not_observed_and_not_predicted_b_vs_predicted_b,fraction_not_observed_and_not_predicted_vs_predicted,fraction_not_observed_and_not_predicted_y,fraction_not_observed_and_not_predicted_y_vs_predicted_y,fraction_not_observed_but_predicted,fraction_not_observed_but_predicted_b,fraction_not_observed_but_predicted_b_vs_predicted,fraction_not_observed_but_predicted_vs_predicted,fraction_not_observed_but_predicted_y,fraction_not_observed_but_predicted_y_vs_predicted,fraction_observed,fraction_observed_and_predicted,fraction_observed_and_predicted_b,fraction_observed_and_predicted_b_vs_predicted_b,fraction_observed_and_predicted_vs_predicted,fraction_observed_and_predicted_y,fraction_observed_and_predicted_y_vs_predicted_y,fraction_observed_b,fraction_observed_but_not_predicted,fraction_observed_but_not_predicted_b,fraction_observed_but_not_predicted_b_vs_predicted_b,fraction_observed_but_not_predicted_vs_predicted,fraction_observed_but_not_predicted_y,fraction_observed_but_not_predicted_y_vs_predicted_y,fraction_observed_y,fraction_predicted,fraction_predicted_b,fraction_predicted_y,iRT,lda_scores,missedCleavages,modified_cosine,pearson_corr,pred_RT,sequence_length,spectral_angle,Peptide,Protein
+,SpecId,Label,ScanNr,CID,Charge1,Charge2,Charge3,Charge4,Charge5,Charge6,HCD,KR,Mass,RT,UnknownFragmentationMethod,abs_rt_diff,collision_energy_aligned,count_not_observed_and_not_predicted,count_not_observed_and_not_predicted_b,count_not_observed_and_not_predicted_y,count_not_observed_but_predicted,count_not_observed_but_predicted_b,count_not_observed_but_predicted_y,count_observed,count_observed_and_predicted,count_observed_and_predicted_b,count_observed_and_predicted_y,count_observed_b,count_observed_but_not_predicted,count_observed_but_not_predicted_b,count_observed_but_not_predicted_y,count_observed_y,count_predicted,count_predicted_b,count_predicted_y,fraction_not_observed_and_not_predicted,fraction_not_observed_and_not_predicted_b,fraction_not_observed_and_not_predicted_b_vs_predicted_b,fraction_not_observed_and_not_predicted_vs_predicted,fraction_not_observed_and_not_predicted_y,fraction_not_observed_and_not_predicted_y_vs_predicted_y,fraction_not_observed_but_predicted,fraction_not_observed_but_predicted_b,fraction_not_observed_but_predicted_b_vs_predicted,fraction_not_observed_but_predicted_vs_predicted,fraction_not_observed_but_predicted_y,fraction_not_observed_but_predicted_y_vs_predicted,fraction_observed,fraction_observed_and_predicted,fraction_observed_and_predicted_b,fraction_observed_and_predicted_b_vs_predicted_b,fraction_observed_and_predicted_vs_predicted,fraction_observed_and_predicted_y,fraction_observed_and_predicted_y_vs_predicted_y,fraction_observed_b,fraction_observed_but_not_predicted,fraction_observed_but_not_predicted_b,fraction_observed_but_not_predicted_b_vs_predicted_b,fraction_observed_but_not_predicted_vs_predicted,fraction_observed_but_not_predicted_y,fraction_observed_but_not_predicted_y_vs_predicted_y,fraction_observed_y,fraction_predicted,fraction_predicted_b,fraction_predicted_y,iRT,lda_scores,missedCleavages,modified_cosine,pearson_corr,pred_RT,sequence_length,spectral_angle,Peptide,Proteins
 0,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02-7978-AAIGEATRL-2-1,1,10203379,0,0,1,0,0,0,0,1,1,900.50288029264,0.5000000183883155,0,0.0,0.3,2.0,1,1,2.0,1,1,4.0,2.0,1,1,1,2.0,0,2,3,4.0,2,2,0.25,0.3333333333333333,0.5,0.5,0.2,0.5,0.25,0.3333333333333333,0.5,0.5,0.2,0.5,0.5,0.25,0.3333333333333333,0.5,0.5,0.2,0.5,0.3333333333333333,0.25,0.0,0.0,0.5,0.4,1.0,0.6,0.5,0.6666666666666666,0.4,0.5000000183883155,1.7027402478448157e+30,1,0.8959462788501606,0.8831116463997931,0.5000000323590892,9,0.7449534694193893,_.AAIGEATRL._,AAIGEATRL
 1,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02-12304-AAVPRAAFL-2-2,-1,5831230,0,0,1,0,0,0,0,1,1,914.53379,1.000000038995633,0,2.533209730870567e-08,0.3,1.0,0,1,1.0,0,1,2.0,1.0,0,1,1,1.0,1,0,1,2.0,0,2,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,0.5,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,1.0,0.25,1.0,1.0,0.5,0.0,0.0,0.3333333333333333,0.5,0.0,0.6666666666666666,1.0000000136635356,-1.7027402478448157e+30,1,1.0,0.0,1.5000000246189773,9,0.5903344918223923,_.AAVPRAAFL._,AAVPRAAFL
 2,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02-12398-AAYFGVYDTAK-2-3,-1,16059765,0,0,1,0,0,0,0,1,1,1204.5764,1.5000000993570155,0,1.0185683851915428e-07,0.3,1.0,0,1,1.0,0,1,2.0,1.0,0,1,1,1.0,1,0,1,2.0,0,2,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,0.5,0.25,0.0,0.0,0.5,0.3333333333333333,0.5,1.0,0.25,1.0,1.0,0.5,0.0,0.0,0.3333333333333333,0.5,0.0,0.6666666666666666,1.499999997500177,-1.7027402478448157e+30,0,1.0,0.0,2.500000056694346,11,0.5903344918223923,_.AAYFGVYDTAK._,AAYFGVYDTAK

tests/unit_tests/test_percolator.py

@@ -274,12 +274,6 @@ def _create_noisy_logistic_data():
 class TestPercolator:
     """Class to test percolator."""
 
-    def test_get_scannr(self):
-        """Test get_scannr."""
-        np.testing.assert_equal(
-            perc.Percolator.get_scannr(("20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02", 7978)), 10203379
-        )
-
     def test_get_specid(self):
         """Test get_specid."""
         np.testing.assert_string_equal(
@@ -361,11 +355,12 @@ def test_calc(self):
             percolator.metrics_val["SpecId"][0], "20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02-7978-AAIGEATRL-2-1"
         )
         np.testing.assert_equal(percolator.metrics_val["Label"][0], 1)
-        np.testing.assert_equal(percolator.metrics_val["ScanNr"][0], 10203379)
+        np.testing.assert_equal(percolator.metrics_val["ScanNr"][0], 7978)
+        np.testing.assert_equal(percolator.metrics_val["filename"][0], "20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02")
         # 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["Protein"][0], "AAIGEATRL"
+            percolator.metrics_val["Proteins"][0], "AAIGEATRL"
         )  # we don't need the protein ID to get PSM / peptide results
 
         # features