From 85c243c9efbec4c7e78c88adf99d674affaeba99 Mon Sep 17 00:00:00 2001
From: mschwoerer <82171591+mschwoer@users.noreply.github.com>
Date: Fri, 15 Nov 2024 16:06:37 +0100
Subject: [PATCH 1/4] fix some docstrings

---
 alphabase/psm_reader/dia_psm_reader.py  |  4 +-
 alphabase/psm_reader/keys.py            |  1 +
 alphabase/psm_reader/maxquant_reader.py |  7 +++-
 alphabase/psm_reader/psm_reader.py      | 56 +++++++++++++++----------
 alphabase/psm_reader/sage_reader.py     |  9 ++++
 alphabase/spectral_library/reader.py    | 15 +++----
 ruff-lint-psm-readers.toml              |  4 +-
 7 files changed, 60 insertions(+), 36 deletions(-)

diff --git a/alphabase/psm_reader/dia_psm_reader.py b/alphabase/psm_reader/dia_psm_reader.py
index 09dace3f..71da89c2 100644
--- a/alphabase/psm_reader/dia_psm_reader.py
+++ b/alphabase/psm_reader/dia_psm_reader.py
@@ -107,9 +107,7 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
         rt_unit: str = "minute",
         **kwargs,
     ):
-        """Also similar to `MaxQuantReader`,
-        but different in column_mapping and modification_mapping.
-        """
+        """Similar to `SpectronautReader` but different in column_mapping and modification_mapping."""
         super().__init__(
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,
diff --git a/alphabase/psm_reader/keys.py b/alphabase/psm_reader/keys.py
index cee93ea8..388afeb8 100644
--- a/alphabase/psm_reader/keys.py
+++ b/alphabase/psm_reader/keys.py
@@ -5,6 +5,7 @@ class ConstantsClass(type):
     """A metaclass for classes that should only contain string constants."""
 
     def __setattr__(cls, name: Any, value: Any) -> NoReturn:  # noqa: ANN401
+        """Raise an error when trying to set an attribute."""
         raise TypeError("Constants class cannot be modified")
 
     def get_values(cls) -> List[str]:
diff --git a/alphabase/psm_reader/maxquant_reader.py b/alphabase/psm_reader/maxquant_reader.py
index 298668ce..a4b7bac6 100644
--- a/alphabase/psm_reader/maxquant_reader.py
+++ b/alphabase/psm_reader/maxquant_reader.py
@@ -66,9 +66,9 @@ def parse_mod_seq(
         separator to indicate the modification section.
         Defaults to '()'
 
-    fixed_C : bool
+    fixed_C57 : bool
         If Carbamidomethyl@C is a fixed modification
-        and not displayed in the sequence. Defaults to True for MaxQuant.
+        and not displayed in the sequence. Defaults to True.
 
     Returns
     -------
@@ -172,6 +172,9 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
             The columns to find modified sequences,
             by default ['Modified sequence']
 
+        **kwargs : dict
+            deprecated
+
         """
         if mod_seq_columns is None:
             mod_seq_columns = [
diff --git a/alphabase/psm_reader/psm_reader.py b/alphabase/psm_reader/psm_reader.py
index 2c2becaf..9b4dc97e 100644
--- a/alphabase/psm_reader/psm_reader.py
+++ b/alphabase/psm_reader/psm_reader.py
@@ -15,18 +15,17 @@
 
 
 def translate_other_modification(mod_str: str, mod_dict: dict) -> str:
-    """Translate modifications of `mod_str` to the AlphaBase
-    format mapped by mod_dict.
+    """Translate modifications of `mod_str` to the AlphaBase format mapped by mod_dict.
 
     Parameters
     ----------
-        mod_str : str
-            mod list in str format, seperated by ';',
-            e.g. ModA;ModB
-        mod_dict : dict
-            translate mod dict from others to AlphaBase,
-            e.g. for pFind, key=['Phospho[S]','Oxidation[M]'],
-            value=['Phospho@S','Oxidation@M']
+    mod_str : str
+        mod list in str format, seperated by ';',
+        e.g. ModA;ModB
+    mod_dict : dict
+        translate mod dict from others to AlphaBase,
+        e.g. for pFind, key=['Phospho[S]','Oxidation[M]'],
+        value=['Phospho@S','Oxidation@M']
 
     Returns
     -------
@@ -91,7 +90,9 @@ def __init__(
         rt_unit: str = "minute",
         **kwargs,
     ):
-        """The Base class for all PSMReaders. The key of the sub-classes for different
+        """The Base class for all PSMReaders.
+
+        The key of the sub-classes for different
         search engine format is to re-define `column_mapping` and `modification_mapping`.
 
         Parameters
@@ -112,6 +113,7 @@ def __init__(
             }
             ```
             Defaults to None.
+
         modification_mapping : dict, optional
             A dict that maps alphabase's modifications to other engine's.
             If it is None, this dict will be init by
@@ -126,12 +128,21 @@ def __init__(
             }
             ```
             Defaults to None.
+
         fdr : float, optional
             FDR level to keep PSMs.
             Defaults to 0.01.
+
         keep_decoy : bool, optional
             If keep decoy PSMs in self.psm_df.
-            Defautls to False.
+            Defaults to False.
+
+        rt_unit : str, optional
+            The unit of RT in the search engine result.
+            Defaults to 'minute'.
+
+        **kwargs: dict
+            deprecated
 
         Attributes
         ----------
@@ -140,10 +151,8 @@ def __init__(
         modification_mapping : dict
             Dict structure same as modification_mapping in Args.
             We must use self.set_modification_mapping(new_mapping) to update it.
-        _psm_df : pd.DataFrame
-            the PSM DataFrame after loading from search engines.
         psm_df : pd.DataFrame
-            the getter of self._psm_df
+            the PSM DataFrame after loading from search engines.
         keep_fdr : float
             The only PSMs with FDR<=keep_fdr were returned in self._psm_df.
         keep_decoy : bool
@@ -280,8 +289,9 @@ def import_files(self, file_list: List[str]) -> pd.DataFrame:
         return self._psm_df
 
     def import_file(self, _file: str) -> pd.DataFrame:
-        """This is the main entry function of PSM readers,
-        it imports the file with following steps:
+        """Main entry function of PSM readers.
+
+        Imports a file with following steps:
         ```
         origin_df = self._load_file(_file)
         self._translate_columns(origin_df)
@@ -364,6 +374,7 @@ def normalize_rt_by_raw_name(self) -> None:
 
     def _load_file(self, filename: str) -> pd.DataFrame:
         """Load original dataframe from PSM filename.
+
         Different search engines may store PSMs in different ways:
         tsv, csv, HDF, XML, ...
 
@@ -399,8 +410,7 @@ def _find_mapped_columns(self, origin_df: pd.DataFrame) -> Dict[str, str]:
         return mapped_columns
 
     def _translate_columns(self, origin_df: pd.DataFrame) -> None:
-        """Translate the dataframe from other search engines
-        to AlphaBase format.
+        """Translate the dataframe from other search engines to AlphaBase format.
 
         Parameters
         ----------
@@ -426,6 +436,7 @@ def _translate_columns(self, origin_df: pd.DataFrame) -> None:
 
     def _transform_table(self) -> None:
         """Transform the dataframe format if needed.
+
         Usually only needed in combination with spectral libraries.
 
         Parameters
@@ -442,7 +453,8 @@ def _transform_table(self) -> None:
 
     def _load_modifications(self, origin_df: pd.DataFrame) -> NoReturn:
         """Read modification information from 'origin_df'.
-        Some of search engines use modified_sequence, some of them
+
+        Some search engines use modified_sequence, some of them
         use additional columns to store modifications and the sites.
 
         Parameters
@@ -483,9 +495,9 @@ def _translate_modifications(self) -> None:
             )
 
     def _post_process(self) -> None:
-        """Set 'nAA' columns, remove unknown modifications
-        and perform other post processings,
-        e.g. get 'rt_norm', remove decoys, filter FDR...
+        """Set 'nAA' columns, remove unknown modifications and perform other post processings.
+
+        E.g. get 'rt_norm', remove decoys, filter FDR...
 
         """
         self._psm_df[PsmDfCols.NAA] = self._psm_df[PsmDfCols.SEQUENCE].str.len()
diff --git a/alphabase/psm_reader/sage_reader.py b/alphabase/psm_reader/sage_reader.py
index 090d0845..7f1dfcb0 100644
--- a/alphabase/psm_reader/sage_reader.py
+++ b/alphabase/psm_reader/sage_reader.py
@@ -25,6 +25,7 @@ def __init__(
         mp_process_num: int = 10,
     ):
         """Translate Sage style modifications to alphabase style modifications.
+
         A modified sequence like VM[+15.9949]QENSSSFSDLSER will be translated to mods: Oxidation@M, mod_sites: 2.
         By default, the translation is done by matching the observed mass and location to the UniMod database.
         If a custom translation dataframe is provided, the translation will be done based on the custom translation dataframe first.
@@ -57,6 +58,7 @@ def __init__(
 
     def __call__(self, psm_df: pd.DataFrame) -> pd.DataFrame:
         """Translate modifications in the PSMs to alphabase style modifications.
+
         1. Discover all modifications in the PSMs.
         2. Annotate modifications from custom translation df, if provided.
         3. Annotate all remaining modifications from UniMod.
@@ -107,6 +109,7 @@ def _annotate_from_custom_translation(
         self, discovered_modifications_df: pd.DataFrame, translation_df: pd.DataFrame
     ) -> Tuple[pd.DataFrame, pd.DataFrame]:
         """Annotate modifications from custom translation df, if provided.
+
         Discovered modifications are first matched using the custom translation dataframe.
         If no match is found, the modifications are returned for matching using UniMod.
 
@@ -153,6 +156,7 @@ def _annotate_from_unimod(
         self, discovered_modifications_df: pd.DataFrame, translation_df: pd.DataFrame
     ) -> pd.DataFrame:
         """Annotate all remaining modifications from UniMod.
+
         UniMod modification are used from the global MOD_DF.
 
         Parameters
@@ -476,6 +480,9 @@ def _apply_translate_modifications_mp(
     mp_process_num : int
         The number of parallel processes
 
+    progress_bar : bool, optional
+        Whether to show a progress bar. Defaults to True
+
     """
     df_list = []
     with mp.get_context("spawn").Pool(mp_process_num) as p:
@@ -497,6 +504,7 @@ def _apply_translate_modifications_mp(
 
 def _get_annotated_mod_df() -> pd.DataFrame:
     """Annotates the modification dataframe for annotation of sage output.
+
     Due to the modified sequence based notation,
     C-Terminal and sidechain modifications on the last AA could be confused.
 
@@ -526,6 +534,7 @@ def _get_annotated_mod_df() -> pd.DataFrame:
 
 def _sage_spec_idx_from_scan_nr(scan_indicator_str: str) -> int:
     """Extract the spectrum index from the scan_nr field in Sage output.
+
     Sage uses 1-based indexing for spectra, so we need to subtract 1 to convert to 0-based indexing.
 
     Parameters
diff --git a/alphabase/spectral_library/reader.py b/alphabase/spectral_library/reader.py
index 1da44991..d0c04173 100644
--- a/alphabase/spectral_library/reader.py
+++ b/alphabase/spectral_library/reader.py
@@ -57,6 +57,8 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
             default is 0.01
 
         fixed_C57: bool
+            If true, the search engine will not show `Carbamidomethyl` in the modified sequences.
+            By default False
 
         mod_seq_columns: list of str
             List of column names in the csv file containing the modified sequence.
@@ -76,8 +78,10 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
             Decoy type for the spectral library.
             Can be either `pseudo_reverse` or `diann`
 
-        """
+        **kwargs: dict
+            deprecated
 
+        """
         if mod_seq_columns is None:
             mod_seq_columns = psm_reader_yaml["library_reader_base"]["mod_seq_columns"]
 
@@ -138,6 +142,7 @@ def _find_key_columns(self, lib_df: pd.DataFrame) -> None:
 
     def _get_fragment_intensity(self, lib_df: pd.DataFrame) -> pd.DataFrame:  # noqa: PLR0912, C901 too many branches, too complex TODO: refactor
         """Create the self._fragment_intensity dataframe from a given spectral library.
+
         In the process, the input dataframe is converted from long format to a precursor dataframe and returned.
 
         Parameters
@@ -244,9 +249,7 @@ def _get_fragment_intensity(self, lib_df: pd.DataFrame) -> pd.DataFrame:  # noqa
         return df
 
     def _load_file(self, filename: str) -> pd.DataFrame:
-        """Load the spectral library from a csv file.
-        Reimplementation of `PSMReaderBase._translate_columns`.
-        """
+        """Load the spectral library from a csv file."""
         csv_sep = self._get_table_delimiter(filename)
 
         df = pd.read_csv(
@@ -281,9 +284,7 @@ def _load_file(self, filename: str) -> pd.DataFrame:
     def _post_process(
         self,
     ) -> None:
-        """Process the spectral library and create the `fragment_intensity`, `fragment_mz`dataframe.
-        Reimplementation of `PSMReaderBase._post_process`.
-        """
+        """Process the spectral library and create the `fragment_intensity`, `fragment_mz` dataframe."""
         # identify unknown modifications
         len_before = len(self._psm_df)
         self._psm_df = self._psm_df[~self._psm_df[PsmDfCols.MODS].isna()]
diff --git a/ruff-lint-psm-readers.toml b/ruff-lint-psm-readers.toml
index 3c6dc61a..eb234586 100644
--- a/ruff-lint-psm-readers.toml
+++ b/ruff-lint-psm-readers.toml
@@ -32,8 +32,8 @@ ignore = [
     #
     "PD002", #pandas-use-of-inplace-argument # TODO revisit
 
-    # these still need to be resolved:
-    "D",
+#    # these still need to be resolved:
+    "D101", "D100", "D103", "D107", "D102",
 
     # reader-specific
     "FA100", # Add `from __future__ import annotations` to simplify `typing.Optional`

From f291f2c3dbdc0084c8479708c0c191eec2378e48 Mon Sep 17 00:00:00 2001
From: mschwoerer <82171591+mschwoer@users.noreply.github.com>
Date: Fri, 15 Nov 2024 16:09:44 +0100
Subject: [PATCH 2/4] fix some docstrings

---
 alphabase/psm_reader/alphapept_reader.py | 2 ++
 alphabase/psm_reader/dia_psm_reader.py   | 2 ++
 alphabase/psm_reader/keys.py             | 2 ++
 alphabase/psm_reader/maxquant_reader.py  | 2 ++
 alphabase/psm_reader/msfragger_reader.py | 2 ++
 alphabase/psm_reader/pfind_reader.py     | 2 ++
 alphabase/psm_reader/psm_reader.py       | 2 ++
 alphabase/psm_reader/sage_reader.py      | 2 ++
 alphabase/spectral_library/reader.py     | 2 ++
 ruff-lint-psm-readers.toml               | 5 ++++-
 10 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/alphabase/psm_reader/alphapept_reader.py b/alphabase/psm_reader/alphapept_reader.py
index 6475f912..614c7c00 100644
--- a/alphabase/psm_reader/alphapept_reader.py
+++ b/alphabase/psm_reader/alphapept_reader.py
@@ -1,3 +1,5 @@
+"""Reader for AlphaPept's *.ms_data.hdf files."""
+
 from pathlib import Path
 from typing import Optional, Tuple
 
diff --git a/alphabase/psm_reader/dia_psm_reader.py b/alphabase/psm_reader/dia_psm_reader.py
index 71da89c2..5351c438 100644
--- a/alphabase/psm_reader/dia_psm_reader.py
+++ b/alphabase/psm_reader/dia_psm_reader.py
@@ -1,3 +1,5 @@
+"""Readers for Spectronaut's output library and reports, Swath data and DIANN data."""
+
 from typing import List, Optional
 
 import numpy as np
diff --git a/alphabase/psm_reader/keys.py b/alphabase/psm_reader/keys.py
index 388afeb8..3f4badba 100644
--- a/alphabase/psm_reader/keys.py
+++ b/alphabase/psm_reader/keys.py
@@ -1,3 +1,5 @@
+"""Constants for accessing the columns of a PSM dataframe."""
+
 from typing import Any, List, NoReturn
 
 
diff --git a/alphabase/psm_reader/maxquant_reader.py b/alphabase/psm_reader/maxquant_reader.py
index a4b7bac6..c92b4bc9 100644
--- a/alphabase/psm_reader/maxquant_reader.py
+++ b/alphabase/psm_reader/maxquant_reader.py
@@ -1,3 +1,5 @@
+"""Reader for MaxQuant data."""
+
 import copy
 import warnings
 from typing import List, Optional
diff --git a/alphabase/psm_reader/msfragger_reader.py b/alphabase/psm_reader/msfragger_reader.py
index 0fc68b00..70cdc01c 100644
--- a/alphabase/psm_reader/msfragger_reader.py
+++ b/alphabase/psm_reader/msfragger_reader.py
@@ -1,3 +1,5 @@
+"""MSFragger reader."""
+
 from typing import List, Optional, Tuple
 
 import numpy as np
diff --git a/alphabase/psm_reader/pfind_reader.py b/alphabase/psm_reader/pfind_reader.py
index 36dc0604..dcba1071 100644
--- a/alphabase/psm_reader/pfind_reader.py
+++ b/alphabase/psm_reader/pfind_reader.py
@@ -1,3 +1,5 @@
+"""pFind reader."""
+
 from typing import Optional, Tuple, Union
 
 import numpy as np
diff --git a/alphabase/psm_reader/psm_reader.py b/alphabase/psm_reader/psm_reader.py
index 9b4dc97e..58bf9fec 100644
--- a/alphabase/psm_reader/psm_reader.py
+++ b/alphabase/psm_reader/psm_reader.py
@@ -1,3 +1,5 @@
+"""The base class for all PSM readers and the provider for all readers."""
+
 import copy
 import warnings
 from pathlib import Path
diff --git a/alphabase/psm_reader/sage_reader.py b/alphabase/psm_reader/sage_reader.py
index 7f1dfcb0..90272a06 100644
--- a/alphabase/psm_reader/sage_reader.py
+++ b/alphabase/psm_reader/sage_reader.py
@@ -1,3 +1,5 @@
+"""SageReader for reading Sage output files."""
+
 import logging
 import multiprocessing as mp
 import re
diff --git a/alphabase/spectral_library/reader.py b/alphabase/spectral_library/reader.py
index d0c04173..5f50ebd3 100644
--- a/alphabase/spectral_library/reader.py
+++ b/alphabase/spectral_library/reader.py
@@ -1,3 +1,5 @@
+"""Module for reading spectral libraries."""
+
 import warnings
 from typing import List, Optional
 
diff --git a/ruff-lint-psm-readers.toml b/ruff-lint-psm-readers.toml
index eb234586..5d8694f5 100644
--- a/ruff-lint-psm-readers.toml
+++ b/ruff-lint-psm-readers.toml
@@ -33,7 +33,10 @@ ignore = [
     "PD002", #pandas-use-of-inplace-argument # TODO revisit
 
 #    # these still need to be resolved:
-    "D101", "D100", "D103", "D107", "D102",
+    "D101",
+    "D103",
+    "D107",
+    "D102",
 
     # reader-specific
     "FA100", # Add `from __future__ import annotations` to simplify `typing.Optional`

From 9cc23f33b2d866a4078f61a0b495405f2af10fbf Mon Sep 17 00:00:00 2001
From: mschwoerer <82171591+mschwoer@users.noreply.github.com>
Date: Fri, 15 Nov 2024 16:12:20 +0100
Subject: [PATCH 3/4] fix some docstrings

---
 alphabase/psm_reader/alphapept_reader.py | 2 ++
 alphabase/psm_reader/dia_psm_reader.py   | 4 ++++
 alphabase/psm_reader/maxquant_reader.py  | 2 ++
 alphabase/psm_reader/msfragger_reader.py | 5 +++++
 alphabase/psm_reader/pfind_reader.py     | 3 +++
 alphabase/psm_reader/psm_reader.py       | 4 ++++
 alphabase/psm_reader/sage_reader.py      | 8 ++++++++
 alphabase/spectral_library/reader.py     | 2 ++
 ruff-lint-psm-readers.toml               | 2 +-
 9 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/alphabase/psm_reader/alphapept_reader.py b/alphabase/psm_reader/alphapept_reader.py
index 614c7c00..a398fe5c 100644
--- a/alphabase/psm_reader/alphapept_reader.py
+++ b/alphabase/psm_reader/alphapept_reader.py
@@ -50,6 +50,8 @@ def parse_ap(precursor: str) -> Tuple[str, str, str, str, int]:
 
 
 class AlphaPeptReader(PSMReaderBase):
+    """Reader for AlphaPept's *.ms_data.hdf files."""
+
     def __init__(
         self,
         *,
diff --git a/alphabase/psm_reader/dia_psm_reader.py b/alphabase/psm_reader/dia_psm_reader.py
index 5351c438..b9a2e75b 100644
--- a/alphabase/psm_reader/dia_psm_reader.py
+++ b/alphabase/psm_reader/dia_psm_reader.py
@@ -71,6 +71,8 @@ def _load_file(self, filename: str) -> pd.DataFrame:
 
 
 class SwathReader(SpectronautReader):
+    """Reader for SWATH or OpenSWATH library TSV/CSV."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
@@ -98,6 +100,8 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
 
 
 class DiannReader(SpectronautReader):
+    """Reader for DIANN data."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
diff --git a/alphabase/psm_reader/maxquant_reader.py b/alphabase/psm_reader/maxquant_reader.py
index c92b4bc9..5ec5b3fc 100644
--- a/alphabase/psm_reader/maxquant_reader.py
+++ b/alphabase/psm_reader/maxquant_reader.py
@@ -134,6 +134,8 @@ def parse_mod_seq(
 
 
 class MaxQuantReader(PSMReaderBase):
+    """Reader for MaxQuant data."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
diff --git a/alphabase/psm_reader/msfragger_reader.py b/alphabase/psm_reader/msfragger_reader.py
index 70cdc01c..08306b1d 100644
--- a/alphabase/psm_reader/msfragger_reader.py
+++ b/alphabase/psm_reader/msfragger_reader.py
@@ -83,14 +83,19 @@ def _get_mods_from_masses(  # noqa: PLR0912, C901 too many branches, too complex
 
 
 class MSFragger_PSM_TSV_Reader(PSMReaderBase):  # noqa: N801 name should use CapWords convention TODO: refactor
+    """Reader for MSFragger's psm.tsv file."""
+
     def __init__(
         self,
         **kwargs,
     ):
+        """Constructor."""
         raise NotImplementedError("MSFragger_PSM_TSV_Reader for psm.tsv")
 
 
 class MSFraggerPepXML(PSMReaderBase):
+    """Reader for MSFragger's pep.xml file."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
diff --git a/alphabase/psm_reader/pfind_reader.py b/alphabase/psm_reader/pfind_reader.py
index dcba1071..95704afd 100644
--- a/alphabase/psm_reader/pfind_reader.py
+++ b/alphabase/psm_reader/pfind_reader.py
@@ -92,6 +92,8 @@ def parse_pfind_protein(protein: str, *, keep_reverse: bool = True) -> str:
 
 
 class pFindReader(PSMReaderBase):  # noqa: N801 name `pFindReader` should use CapWords convention TODO: used by peptdeep, alpharaw
+    """Reader for pFind's *.txt files."""
+
     def __init__(
         self,
         *,
@@ -101,6 +103,7 @@ def __init__(
         keep_decoy: bool = False,
         **kwargs,
     ):
+        """Reading PSMs from pFind's *.txt."""
         super().__init__(
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,
diff --git a/alphabase/psm_reader/psm_reader.py b/alphabase/psm_reader/psm_reader.py
index 58bf9fec..a70d5039 100644
--- a/alphabase/psm_reader/psm_reader.py
+++ b/alphabase/psm_reader/psm_reader.py
@@ -82,6 +82,8 @@ def _keep_modifications(mod_str: str, mod_set: set) -> str:
 
 
 class PSMReaderBase:
+    """The Base class for all PSMReaders."""
+
     def __init__(
         self,
         *,
@@ -558,6 +560,8 @@ def filter_psm_by_modifications(
 
 
 class PSMReaderProvider:
+    """A factory class to register and get readers for different PSM types."""
+
     def __init__(self):
         self.reader_dict = {}
 
diff --git a/alphabase/psm_reader/sage_reader.py b/alphabase/psm_reader/sage_reader.py
index 90272a06..87663a78 100644
--- a/alphabase/psm_reader/sage_reader.py
+++ b/alphabase/psm_reader/sage_reader.py
@@ -20,6 +20,8 @@
 
 
 class SageModificationTranslation:
+    """Translate Sage style modifications to alphabase style modifications."""
+
     def __init__(
         self,
         custom_translation_df: pd.DataFrame = None,
@@ -560,6 +562,8 @@ def _sage_spec_idx_from_scan_nr(scan_indicator_str: str) -> int:
 
 
 class SageReaderBase(PSMReaderBase):
+    """Base class for SageReader."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         *,
@@ -628,6 +632,8 @@ def _translate_modifications(self) -> None:
 
 
 class SageReaderTSV(SageReaderBase):
+    """Reader for Sage output files in TSV format."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
@@ -636,6 +642,8 @@ def _load_file(self, filename: str) -> pd.DataFrame:
 
 
 class SageReaderParquet(SageReaderBase):
+    """Reader for Sage output files in parquet format."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
diff --git a/alphabase/spectral_library/reader.py b/alphabase/spectral_library/reader.py
index 5f50ebd3..6134994a 100644
--- a/alphabase/spectral_library/reader.py
+++ b/alphabase/spectral_library/reader.py
@@ -16,6 +16,8 @@
 
 
 class LibraryReaderBase(MaxQuantReader, SpecLibBase):
+    """Base class for reading spectral libraries."""
+
     def __init__(  # noqa: PLR0913 many arguments in function definition
         self,
         charged_frag_types: List[str] = [
diff --git a/ruff-lint-psm-readers.toml b/ruff-lint-psm-readers.toml
index 5d8694f5..a1f310c1 100644
--- a/ruff-lint-psm-readers.toml
+++ b/ruff-lint-psm-readers.toml
@@ -33,7 +33,7 @@ ignore = [
     "PD002", #pandas-use-of-inplace-argument # TODO revisit
 
 #    # these still need to be resolved:
-    "D101",
+#    "D101",
     "D103",
     "D107",
     "D102",

From 5645032b67c5c57e4dba696ee89577da82b9c398 Mon Sep 17 00:00:00 2001
From: mschwoerer <82171591+mschwoer@users.noreply.github.com>
Date: Fri, 15 Nov 2024 16:16:51 +0100
Subject: [PATCH 4/4] fix some docstrings

---
 alphabase/psm_reader/alphapept_reader.py | 1 +
 alphabase/psm_reader/dia_psm_reader.py   | 3 +++
 alphabase/psm_reader/maxquant_reader.py  | 3 +++
 alphabase/psm_reader/msfragger_reader.py | 1 +
 alphabase/psm_reader/pfind_reader.py     | 4 ++++
 alphabase/psm_reader/psm_reader.py       | 9 +++++++++
 alphabase/psm_reader/sage_reader.py      | 4 ++++
 ruff-lint-psm-readers.toml               | 8 +-------
 8 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/alphabase/psm_reader/alphapept_reader.py b/alphabase/psm_reader/alphapept_reader.py
index a398fe5c..b3dfbd8f 100644
--- a/alphabase/psm_reader/alphapept_reader.py
+++ b/alphabase/psm_reader/alphapept_reader.py
@@ -109,4 +109,5 @@ def _load_modifications(self, df: pd.DataFrame) -> None:
 
 
 def register_readers() -> None:
+    """Register readers for AlphaPept's *.ms_data.hdf files."""
     psm_reader_provider.register_reader("alphapept", AlphaPeptReader)
diff --git a/alphabase/psm_reader/dia_psm_reader.py b/alphabase/psm_reader/dia_psm_reader.py
index b9a2e75b..172e8a7b 100644
--- a/alphabase/psm_reader/dia_psm_reader.py
+++ b/alphabase/psm_reader/dia_psm_reader.py
@@ -35,6 +35,7 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
         rt_unit: str = "minute",
         **kwargs,
     ):
+        """Initialize SpectronautReader."""
         if mod_seq_columns is None:
             mod_seq_columns = psm_reader_yaml["spectronaut"]["mod_seq_columns"]
 
@@ -165,6 +166,7 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
         rt_unit: str = "minute",
         **kwargs,
     ):
+        """Initialize SpectronautReportReader."""
         super().__init__(
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,
@@ -194,6 +196,7 @@ def _load_file(self, filename: str) -> pd.DataFrame:
 
 
 def register_readers() -> None:
+    """Register readers for Spectronaut's output library and reports, Swath data and DIANN data."""
     psm_reader_provider.register_reader("spectronaut", SpectronautReader)
     psm_reader_provider.register_reader("speclib_tsv", SpectronautReader)
     psm_reader_provider.register_reader("openswath", SwathReader)
diff --git a/alphabase/psm_reader/maxquant_reader.py b/alphabase/psm_reader/maxquant_reader.py
index 5ec5b3fc..ae00441b 100644
--- a/alphabase/psm_reader/maxquant_reader.py
+++ b/alphabase/psm_reader/maxquant_reader.py
@@ -34,6 +34,7 @@
 def replace_parentheses_with_brackets(
     modseq: str,
 ) -> str:
+    """Replace parentheses with brackets in the modified sequence."""
     mod_depth = 0
     for i, aa in enumerate(modseq):
         if aa == "(":
@@ -212,6 +213,7 @@ def _init_modification_mapping(self) -> None:
     def set_modification_mapping(
         self, modification_mapping: Optional[dict] = None
     ) -> None:
+        """Set modification mapping."""
         super().set_modification_mapping(modification_mapping)
         self._add_all_unimod()
         self._extend_mod_brackets()
@@ -307,4 +309,5 @@ def _load_modifications(self, origin_df: pd.DataFrame) -> None:
 
 
 def register_readers() -> None:
+    """Register MaxQuant reader."""
     psm_reader_provider.register_reader("maxquant", MaxQuantReader)
diff --git a/alphabase/psm_reader/msfragger_reader.py b/alphabase/psm_reader/msfragger_reader.py
index 08306b1d..efebddf5 100644
--- a/alphabase/psm_reader/msfragger_reader.py
+++ b/alphabase/psm_reader/msfragger_reader.py
@@ -189,6 +189,7 @@ def _post_process(self) -> None:
 
 
 def register_readers() -> None:
+    """Register MSFragger readers."""
     psm_reader_provider.register_reader("msfragger_psm_tsv", MSFragger_PSM_TSV_Reader)
     psm_reader_provider.register_reader("msfragger", MSFragger_PSM_TSV_Reader)
     psm_reader_provider.register_reader("msfragger_pepxml", MSFraggerPepXML)
diff --git a/alphabase/psm_reader/pfind_reader.py b/alphabase/psm_reader/pfind_reader.py
index 95704afd..9517279c 100644
--- a/alphabase/psm_reader/pfind_reader.py
+++ b/alphabase/psm_reader/pfind_reader.py
@@ -51,6 +51,7 @@ def _convert_one_pfind_mod(mod: str) -> Optional[str]:  # noqa:  C901 too comple
 
 
 def translate_pFind_mod(mod_str: str) -> Union[str, NAType]:  # noqa: N802 name `get_pFind_mods` should be lowercase TODO: used by peptdeep
+    """Translate pFind modification string."""
     if not mod_str:
         return ""
     ret_mods = []
@@ -63,6 +64,7 @@ def translate_pFind_mod(mod_str: str) -> Union[str, NAType]:  # noqa: N802 name
 
 
 def get_pFind_mods(pfind_mod_str: str) -> Tuple[str, str]:  # noqa: N802 name `get_pFind_mods` should be lowercase TODO: used by peptdeep
+    """Parse pFind modification string."""
     pfind_mod_str = pfind_mod_str.strip(";")
     if not pfind_mod_str:
         return "", ""
@@ -81,6 +83,7 @@ def get_pFind_mods(pfind_mod_str: str) -> Tuple[str, str]:  # noqa: N802 name `g
 
 
 def parse_pfind_protein(protein: str, *, keep_reverse: bool = True) -> str:
+    """Parse pFind protein string."""
     proteins = protein.strip("/").split("/")
     return ";".join(
         [
@@ -156,5 +159,6 @@ def _load_modifications(self, pfind_df: pd.DataFrame) -> None:
 
 
 def register_readers() -> None:
+    """Register pFind readers."""
     psm_reader_provider.register_reader("pfind", pFindReader)
     psm_reader_provider.register_reader("pfind3", pFindReader)
diff --git a/alphabase/psm_reader/psm_reader.py b/alphabase/psm_reader/psm_reader.py
index a70d5039..65598d52 100644
--- a/alphabase/psm_reader/psm_reader.py
+++ b/alphabase/psm_reader/psm_reader.py
@@ -196,6 +196,7 @@ def __init__(
 
     @property
     def psm_df(self) -> pd.DataFrame:
+        """Get the PSM DataFrame."""
         return self._psm_df
 
     def add_modification_mapping(self, modification_mapping: dict) -> None:
@@ -237,6 +238,7 @@ def add_modification_mapping(self, modification_mapping: dict) -> None:
     def set_modification_mapping(
         self, modification_mapping: Optional[dict] = None
     ) -> None:
+        """Set the modification mapping."""
         if modification_mapping is None:
             self._init_modification_mapping()
         elif isinstance(modification_mapping, str):
@@ -288,6 +290,7 @@ def load(self, _file: Union[List[str], str]) -> pd.DataFrame:
         return self.import_file(_file)
 
     def import_files(self, file_list: List[str]) -> pd.DataFrame:
+        """Import multiple files."""
         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
@@ -365,10 +368,12 @@ def _normalize_rt(self) -> None:
             ).clip(0, 1)
 
     def normalize_rt_by_raw_name(self) -> None:
+        """Normalize RT by raw name."""
         if PsmDfCols.RT not in self._psm_df.columns:
             return
         if PsmDfCols.RT_NORM not in self._psm_df.columns:
             self._normalize_rt()
+
         if PsmDfCols.RAW_NAME not in self._psm_df.columns:
             return
         for _, df_group in self._psm_df.groupby(PsmDfCols.RAW_NAME):
@@ -563,11 +568,13 @@ class PSMReaderProvider:
     """A factory class to register and get readers for different PSM types."""
 
     def __init__(self):
+        """Initialize PSMReaderProvider."""
         self.reader_dict = {}
 
     def register_reader(
         self, reader_type: str, reader_class: Type[PSMReaderBase]
     ) -> None:
+        """Register a reader by reader_type."""
         self.reader_dict[reader_type.lower()] = reader_class
 
     def get_reader(
@@ -580,6 +587,7 @@ def get_reader(
         keep_decoy: bool = False,
         **kwargs,
     ) -> PSMReaderBase:
+        """Get a reader by reader_type."""
         return self.reader_dict[reader_type.lower()](
             column_mapping=column_mapping,
             modification_mapping=modification_mapping,
@@ -592,6 +600,7 @@ def get_reader_by_yaml(
         self,
         yaml_dict: dict,
     ) -> PSMReaderBase:
+        """Get a reader by a yaml dict."""
         return self.get_reader(**copy.deepcopy(yaml_dict))
 
 
diff --git a/alphabase/psm_reader/sage_reader.py b/alphabase/psm_reader/sage_reader.py
index 87663a78..5c4c8543 100644
--- a/alphabase/psm_reader/sage_reader.py
+++ b/alphabase/psm_reader/sage_reader.py
@@ -576,6 +576,7 @@ def __init__(  # noqa: PLR0913 many arguments in function definition
         mp_process_num: int = 10,
         **kwargs,
     ):
+        """Initialize SageReaderBase."""
         self.custom_translation_df = custom_translation_df
         self.mp_process_num = mp_process_num
 
@@ -635,6 +636,7 @@ class SageReaderTSV(SageReaderBase):
     """Reader for Sage output files in TSV format."""
 
     def __init__(self, *args, **kwargs):
+        """Initialize SageReaderTSV."""
         super().__init__(*args, **kwargs)
 
     def _load_file(self, filename: str) -> pd.DataFrame:
@@ -645,6 +647,7 @@ class SageReaderParquet(SageReaderBase):
     """Reader for Sage output files in parquet format."""
 
     def __init__(self, *args, **kwargs):
+        """Initialize SageReaderParquet."""
         super().__init__(*args, **kwargs)
 
     def _load_file(self, filename: str) -> pd.DataFrame:
@@ -652,5 +655,6 @@ def _load_file(self, filename: str) -> pd.DataFrame:
 
 
 def register_readers() -> None:
+    """Register Sage readers."""
     psm_reader_provider.register_reader("sage_tsv", SageReaderTSV)
     psm_reader_provider.register_reader("sage_parquet", SageReaderParquet)
diff --git a/ruff-lint-psm-readers.toml b/ruff-lint-psm-readers.toml
index a1f310c1..9d38be38 100644
--- a/ruff-lint-psm-readers.toml
+++ b/ruff-lint-psm-readers.toml
@@ -32,13 +32,7 @@ ignore = [
     #
     "PD002", #pandas-use-of-inplace-argument # TODO revisit
 
-#    # these still need to be resolved:
-#    "D101",
-    "D103",
-    "D107",
-    "D102",
-
-    # reader-specific
+    # psm_reader-specific
     "FA100", # Add `from __future__ import annotations` to simplify `typing.Optional`
 
     # same as pyproject.toml