Merge pull request #233 from MannLabs/linting_I

Linting i

.pre-commit-config.yaml

@@ -11,8 +11,18 @@ repos:
   rev: v0.4.0
   hooks:
     - id: ruff-format
+    # running ruff with rules in pyproject.toml (all files, limited rules)
     - id: ruff
       args:
         - "--fix"
 
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.7.3 # newer version -> stricter
+  hooks:
+    - id: ruff
+      # running ruff again with rules in ruff-lint-psm-readers.toml (specific files, all rules)
+      args:
+        - "--config"
+        - "ruff-lint-psm-readers.toml"
+        - "--fix"
 exclude: .bumpversion.cfg

alphabase/psm_reader/alphapept_reader.py

@@ -15,9 +15,7 @@
 
 @numba.njit
 def parse_ap(precursor):
-    """
-    Parser to parse peptide strings
-    """
+    """Parser to parse peptide strings"""
     items = precursor.split("_")
     decoy = 1 if len(items) == 3 else 0
     modseq = items[0]
@@ -58,9 +56,7 @@ def __init__(
         keep_decoy=False,
         **kwargs,
     ):
-        """
-        Reading PSMs from alphapept's *.ms_data.hdf
-        """
+        """Reading PSMs from alphapept's *.ms_data.hdf"""
         super().__init__(
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,

alphabase/psm_reader/dia_psm_reader.py

@@ -16,6 +16,7 @@ class SpectronautReader(MaxQuantReader):
     ----------
     csv_sep : str, optional
         Delimiter for TSV/CSV, by default '\t'
+
     """
 
     def __init__(
@@ -74,9 +75,7 @@ def __init__(
         mod_seq_columns=psm_reader_yaml["spectronaut"]["mod_seq_columns"],
         **kwargs,
     ):
-        """
-        SWATH or OpenSWATH library, similar to `SpectronautReader`
-        """
+        """SWATH or OpenSWATH library, similar to `SpectronautReader`"""
         super().__init__(
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,
@@ -100,8 +99,7 @@ def __init__(
         rt_unit="minute",
         **kwargs,
     ):
-        """
-        Also similar to `MaxQuantReader`,
+        """Also similar to `MaxQuantReader`,
         but different in column_mapping and modificatin_mapping
         """
         super().__init__(
@@ -143,6 +141,7 @@ class SpectronautReportReader(MaxQuantReader):
     ----------
     csv_sep : str, optional
         Delimiter for TSV/CSV, by default ','
+
     """
 
     def __init__(

alphabase/psm_reader/maxquant_reader.py

@@ -79,6 +79,7 @@ def parse_mod_seq(
 
         str: modification sites, separated by ';'.
         0 for N-term; -1 for C-term; 1 to N for normal modifications.
+
     """
     PeptideModSeq = modseq
     underscore_for_ncterm = modseq[0] == "_"
@@ -170,6 +171,7 @@ def __init__(
         mod_seq_columns : list, optional
             The columns to find modified sequences,
             by default ['Modified sequence']
+
         """
         if mod_seq_columns is None:
             mod_seq_columns = ["Modified sequence"]
@@ -211,8 +213,7 @@ def _add_all_unimod(self):
                 self.modification_mapping[mod_name] = [unimod]
 
     def _extend_mod_brackets(self):
-        """update modification_mapping to include different bracket types."""
-
+        """Update modification_mapping to include different bracket types."""
         for key, mod_list in list(self.modification_mapping.items()):
             mod_set = set(mod_list)
             # extend bracket types of modifications

alphabase/psm_reader/msfragger_reader.py

@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-import pyteomics.pepxml as pepxml
+from pyteomics import pepxml
 
 from alphabase.constants.aa import AA_ASCII_MASS
 from alphabase.constants.atom import MASS_H, MASS_O

alphabase/psm_reader/pfind_reader.py

@@ -22,24 +22,23 @@ def convert_one_pFind_mod(mod):
         site = mod[(idx + 1) : -1]
     if len(site) == 1:
         return name + "@" + site
-    elif site == "AnyN-term":
+    if site == "AnyN-term":
         return name + "@" + "Any_N-term"
-    elif site == "ProteinN-term":
+    if site == "ProteinN-term":
         return name + "@" + "Protein_N-term"
-    elif site.startswith("AnyN-term"):
+    if site.startswith("AnyN-term"):
         return name + "@" + site[-1] + "^Any_N-term"
-    elif site.startswith("ProteinN-term"):
+    if site.startswith("ProteinN-term"):
         return name + "@" + site[-1] + "^Protein_N-term"
-    elif site == "AnyC-term":
+    if site == "AnyC-term":
         return name + "@" + "Any_C-term"
-    elif site == "ProteinC-term":
+    if site == "ProteinC-term":
         return name + "@" + "Protein_C-term"
-    elif site.startswith("AnyC-term"):
+    if site.startswith("AnyC-term"):
         return name + "@" + site[-1] + "^Any_C-term"
-    elif site.startswith("ProteinC-term"):
+    if site.startswith("ProteinC-term"):
         return name + "@" + site[-1] + "^Protein_C-term"
-    else:
-        return None
+    return None
 
 
 def translate_pFind_mod(mod_str):
@@ -50,8 +49,7 @@ def translate_pFind_mod(mod_str):
         mod = convert_one_pFind_mod(mod)
         if not mod or mod not in ap_mod.MOD_INFO_DICT:
             return pd.NA
-        else:
-            ret_mods.append(mod)
+        ret_mods.append(mod)
     return ";".join(ret_mods)