Linting iii

alphabase/psm_reader/alphapept_reader.py

@@ -1,4 +1,4 @@
-import os
+from pathlib import Path
 from typing import Optional
 
 import h5py
@@ -18,7 +18,7 @@
 def parse_ap(precursor):
     """Parser to parse peptide strings."""
     items = precursor.split("_")
-    decoy = 1 if len(items) == 3 else 0
+    decoy = 1 if len(items) == 3 else 0  # noqa: PLR2004 magic value
     modseq = items[0]
     charge = items[-1]
 
@@ -77,7 +77,7 @@ def _load_file(self, filename):
         with h5py.File(filename, "r") as _hdf:
             dataset = _hdf[self.hdf_dataset]
             df = pd.DataFrame({col: dataset[col] for col in dataset})
-            df[PsmDfCols.RAW_NAME] = os.path.basename(filename)[: -len(".ms_data.hdf")]
+            df[PsmDfCols.RAW_NAME] = Path(filename).name[: -len(".ms_data.hdf")]
             df["precursor"] = df["precursor"].str.decode("utf-8")
             # df['naked_sequence'] = df['naked_sequence'].str.decode('utf-8')
             if "scan_no" in df.columns:

alphabase/psm_reader/dia_psm_reader.py

@@ -21,7 +21,7 @@ class SpectronautReader(MaxQuantReader):
 
     """
 
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,
@@ -66,7 +66,7 @@ def _load_file(self, filename):
 
 
 class SwathReader(SpectronautReader):
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,
@@ -90,7 +90,7 @@ def __init__(
 
 
 class DiannReader(SpectronautReader):
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,
@@ -144,7 +144,7 @@ class SpectronautReportReader(MaxQuantReader):
 
     """
 
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,

alphabase/psm_reader/maxquant_reader.py

@@ -18,8 +18,8 @@
 warnings.filterwarnings("always")
 
 mod_to_unimod_dict = {}
-for mod_name, unimod_id in MOD_DF[["mod_name", "unimod_id"]].values:
-    unimod_id = int(unimod_id)
+for mod_name, unimod_id_ in MOD_DF[["mod_name", "unimod_id"]].to_numpy():
+    unimod_id = int(unimod_id_)
     if unimod_id in (-1, "-1"):
         continue
     if mod_name[-2] == "@":
@@ -81,14 +81,14 @@ def parse_mod_seq(
         0 for N-term; -1 for C-term; 1 to N for normal modifications.
 
     """
-    PeptideModSeq = modseq
+    peptide_mod_seq = modseq
     underscore_for_ncterm = modseq[0] == "_"
     mod_list = []
     site_list = []
-    site = PeptideModSeq.find(mod_sep[0])
+    site = peptide_mod_seq.find(mod_sep[0])
     while site != -1:
-        site_end = PeptideModSeq.find(mod_sep[1], site + 1) + 1
-        if site_end < len(PeptideModSeq) and PeptideModSeq[site_end] == mod_sep[1]:
+        site_end = peptide_mod_seq.find(mod_sep[1], site + 1) + 1
+        if site_end < len(peptide_mod_seq) and peptide_mod_seq[site_end] == mod_sep[1]:
             site_end += 1
         if underscore_for_ncterm:
             site_list.append(site - 1)
@@ -97,42 +97,42 @@ def parse_mod_seq(
         start_mod = site
         if start_mod > 0:
             start_mod -= 1
-        mod_list.append(PeptideModSeq[start_mod:site_end])
-        PeptideModSeq = PeptideModSeq[:site] + PeptideModSeq[site_end:]
-        site = PeptideModSeq.find(mod_sep[0], site)
+        mod_list.append(peptide_mod_seq[start_mod:site_end])
+        peptide_mod_seq = peptide_mod_seq[:site] + peptide_mod_seq[site_end:]
+        site = peptide_mod_seq.find(mod_sep[0], site)
 
     # patch for phos. How many other modification formats does MQ have?
-    site = PeptideModSeq.find("p")
+    site = peptide_mod_seq.find("p")
     while site != -1:
-        mod_list.append(PeptideModSeq[site : site + 2])
+        mod_list.append(peptide_mod_seq[site : site + 2])
         site_list = [i - 1 if i > site else i for i in site_list]
         if underscore_for_ncterm:
             site_list.append(site)
         else:
             site_list.append(site + 1)
-        PeptideModSeq = PeptideModSeq[:site] + PeptideModSeq[site + 1 :]
-        site = PeptideModSeq.find("p", site)
+        peptide_mod_seq = peptide_mod_seq[:site] + peptide_mod_seq[site + 1 :]
+        site = peptide_mod_seq.find("p", site)
 
     if fixed_C57:
-        site = PeptideModSeq.find("C")
+        site = peptide_mod_seq.find("C")
         while site != -1:
             if underscore_for_ncterm:
                 site_list.append(site)
             else:
                 site_list.append(site + 1)
             mod_list.append("C" + "Carbamidomethyl (C)".join(mod_sep))
-            site = PeptideModSeq.find("C", site + 1)
-    sequence = PeptideModSeq.strip("_")
-    nAA = len(sequence)
+            site = peptide_mod_seq.find("C", site + 1)
+    sequence = peptide_mod_seq.strip("_")
+    n_aa = len(sequence)
     return (
         sequence,
         ";".join(mod_list),
-        ";".join([str(i) if i <= nAA else "-1" for i in site_list]),
+        ";".join([str(i) if i <= n_aa else "-1" for i in site_list]),
     )
 
 
 class MaxQuantReader(PSMReaderBase):
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,

alphabase/psm_reader/msfragger_reader.py

@@ -23,7 +23,7 @@ def _is_fragger_decoy(proteins):
 mod_mass_tol = psm_reader_yaml["msfragger_pepxml"]["mod_mass_tol"]
 
 
-def _get_mods_from_masses(sequence, msf_aa_mods):
+def _get_mods_from_masses(sequence, msf_aa_mods):  # noqa: PLR0912, C901 many branches, too complex TODO: refactor
     mods = []
     mod_sites = []
     aa_mass_diffs = []
@@ -78,7 +78,7 @@ def _get_mods_from_masses(sequence, msf_aa_mods):
     )
 
 
-class MSFragger_PSM_TSV_Reader(PSMReaderBase):
+class MSFragger_PSM_TSV_Reader(PSMReaderBase):  # noqa: N801 name should use CapWords convention TODO: refactor
     def __init__(
         self,
         *,
@@ -93,7 +93,7 @@ def __init__(
 
 
 class MSFraggerPepXML(PSMReaderBase):
-    def __init__(
+    def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
         column_mapping: Optional[dict] = None,
@@ -129,7 +129,7 @@ def _load_file(self, filename):
         msf_df[PsmDfCols.RAW_NAME] = (
             msf_df["spectrum"].str.split(".").apply(lambda x: x[0])
         )
-        msf_df["to_remove"] = 0  # TODO revisit
+        msf_df["to_remove"] = 0  # TODO: revisit
         self.column_mapping[PsmDfCols.TO_REMOVE] = "to_remove"
         return msf_df
 

alphabase/psm_reader/pfind_reader.py

@@ -12,7 +12,7 @@
 )
 
 
-def convert_one_pFind_mod(mod):
+def _convert_one_pfind_mod(mod: str) -> Optional[str]:  # noqa:  C901 too complex (11 > 10) TODO: refactor
     if mod[-1] == ")":
         mod = mod[: (mod.find("(") - 1)]
         idx = mod.rfind("[")
@@ -22,40 +22,44 @@ def convert_one_pFind_mod(mod):
         idx = mod.rfind("[")
         name = mod[:idx]
         site = mod[(idx + 1) : -1]
+
     if len(site) == 1:
-        return name + "@" + site
-    if site == "AnyN-term":
-        return name + "@" + "Any_N-term"
-    if site == "ProteinN-term":
-        return name + "@" + "Protein_N-term"
-    if site.startswith("AnyN-term"):
-        return name + "@" + site[-1] + "^Any_N-term"
-    if site.startswith("ProteinN-term"):
-        return name + "@" + site[-1] + "^Protein_N-term"
-    if site == "AnyC-term":
-        return name + "@" + "Any_C-term"
-    if site == "ProteinC-term":
-        return name + "@" + "Protein_C-term"
-    if site.startswith("AnyC-term"):
-        return name + "@" + site[-1] + "^Any_C-term"
-    if site.startswith("ProteinC-term"):
-        return name + "@" + site[-1] + "^Protein_C-term"
-    return None
-
-
-def translate_pFind_mod(mod_str):
+        return_value = name + "@" + site
+    elif site == "AnyN-term":
+        return_value = name + "@" + "Any_N-term"
+    elif site == "ProteinN-term":
+        return_value = name + "@" + "Protein_N-term"
+    elif site.startswith("AnyN-term"):
+        return_value = name + "@" + site[-1] + "^Any_N-term"
+    elif site.startswith("ProteinN-term"):
+        return_value = name + "@" + site[-1] + "^Protein_N-term"
+    elif site == "AnyC-term":
+        return_value = name + "@" + "Any_C-term"
+    elif site == "ProteinC-term":
+        return_value = name + "@" + "Protein_C-term"
+    elif site.startswith("AnyC-term"):
+        return_value = name + "@" + site[-1] + "^Any_C-term"
+    elif site.startswith("ProteinC-term"):
+        return_value = name + "@" + site[-1] + "^Protein_C-term"
+    else:
+        return_value = None
+
+    return return_value
+
+
+def translate_pFind_mod(mod_str):  # noqa: N802 name `get_pFind_mods` should be lowercase TODO: used by peptdeep
     if not mod_str:
         return ""
     ret_mods = []
-    for mod in mod_str.split(";"):
-        mod = convert_one_pFind_mod(mod)
+    for mod_ in mod_str.split(";"):
+        mod = _convert_one_pfind_mod(mod_)
         if not mod or mod not in ap_mod.MOD_INFO_DICT:
             return pd.NA
         ret_mods.append(mod)
     return ";".join(ret_mods)
 
 
-def get_pFind_mods(pfind_mod_str):
+def get_pFind_mods(pfind_mod_str):  # noqa: N802 name `get_pFind_mods` should be lowercase TODO: used by peptdeep
     pfind_mod_str = pfind_mod_str.strip(";")
     if not pfind_mod_str:
         return "", ""
@@ -84,7 +88,7 @@ def parse_pfind_protein(protein, keep_reverse=True):
     )
 
 
-class pFindReader(PSMReaderBase):
+class pFindReader(PSMReaderBase):  # noqa: N801 name `pFindReader` should use CapWords convention TODO: used by peptdeep, alpharaw
     def __init__(
         self,
         *,

alphabase/psm_reader/psm_reader.py

@@ -1,6 +1,6 @@
 import copy
-import os
 import warnings
+from pathlib import Path
 from typing import NoReturn, Optional
 
 import numpy as np
@@ -77,7 +77,7 @@ def _keep_modifications(mod_str: str, mod_set: set) -> str:
 
 
 #: See `psm_reader.yaml <https://github.com/MannLabs/alphabase/blob/main/alphabase/constants/const_files/psm_reader.yaml>`_
-psm_reader_yaml = load_yaml(os.path.join(CONST_FILE_FOLDER, "psm_reader.yaml"))
+psm_reader_yaml = load_yaml(Path(CONST_FILE_FOLDER) / "psm_reader.yaml")
 
 
 class PSMReaderBase:
@@ -268,9 +268,7 @@ def load(self, _file) -> pd.DataFrame:
         return self.import_file(_file)
 
     def import_files(self, file_list: list):
-        df_list = []
-        for _file in file_list:
-            df_list.append(self.import_file(_file))
+        df_list = [self.import_file(file) for file in file_list]
         self._psm_df = pd.concat(df_list, ignore_index=True)
         return self._psm_df