black applied.

quantmsio/commands/maxquant_command.py

@@ -121,16 +121,20 @@ def convert_maxquant_feature(
     output_path = output_folder + "/" + filename
     if not partitions:
         MQ.write_feature_to_file(
-            evidence_path=evidence_file, sdrf_path=sdrf_file, output_path=output_path, chunksize=chunksize, protein_file=protein_file
+            evidence_path=evidence_file,
+            sdrf_path=sdrf_file,
+            output_path=output_path,
+            chunksize=chunksize,
+            protein_file=protein_file,
         )
     else:
         partitions = partitions.split(",")
         MQ.write_features_to_file(
-            evidence_path=evidence_file, 
+            evidence_path=evidence_file,
             sdrf_path=sdrf_file,
-            output_folder = output_folder,
+            output_folder=output_folder,
             filename=filename,
             partitions=partitions,
             chunksize=chunksize,
-            protein_file=protein_file
-        )
+            protein_file=protein_file,
+        )

quantmsio/core/common.py

@@ -76,8 +76,8 @@
     "Modified sequence": "peptidoform",
     "Raw file": "reference_file_name",
     "Score": "andromeda_score",
-    "Delta score": "andromeda_delta_score",   
-    "PIF": "parent_ion_score"
+    "Delta score": "andromeda_delta_score",
+    "PIF": "parent_ion_score",
 }
 
 MAXQUANT_FEATURE_MAP = {
@@ -92,7 +92,7 @@
     "Raw file": "reference_file_name",
     "Score": "andromeda_score",
     "Delta score": "andromeda_delta_score",
-    "PIF": "parent_ion_score",  
+    "PIF": "parent_ion_score",
     "Reverse": "is_decoy",
     "m/z": "observed_mz",
     "Calibrated retention time": "rt",

quantmsio/core/diann.py

@@ -250,7 +250,7 @@ def write_features_to_file(
         output_folder: str,
         filename: str,
         partitions: list,
-        file_num:int = 50,
+        file_num: int = 50,
         protein_file=None,
     ):
         pqwriters = {}
@@ -261,4 +261,4 @@ def write_features_to_file(
                 feature = Feature.transform_feature(df)
                 pqwriters = save_slice_file(feature, pqwriters, output_folder, key, filename)
         close_file(pqwriters=pqwriters)
-        self.destroy_duckdb_database()
+        self.destroy_duckdb_database()

quantmsio/core/feature.py

@@ -3,7 +3,7 @@
 import pyarrow as pa
 import pyarrow.parquet as pq
 from quantmsio.operate.tools import get_ahocorasick, get_protein_accession
-from quantmsio.utils.file_utils import extract_protein_list,save_slice_file, close_file
+from quantmsio.utils.file_utils import extract_protein_list, save_slice_file, close_file
 from quantmsio.core.mztab import MzTab
 from quantmsio.core.psm import Psm
 from quantmsio.core.sdrf import SDRFHandler

quantmsio/core/maxquant.py

@@ -41,7 +41,7 @@ class MaxQuant:
     def __init__(self):
         pass
 
-    def iter_batch(self, file_path: str, label: str = "feature", chunksize: int = 100000, protein_str:str = None):
+    def iter_batch(self, file_path: str, label: str = "feature", chunksize: int = 100000, protein_str: str = None):
         self.mods_map = self.get_mods_map(file_path)
         self._automaton = get_ahocorasick(self.mods_map)
         col_df = pd.read_csv(file_path, sep="\t", nrows=1)
@@ -252,7 +252,7 @@ def main_operate(self, df: pd.DataFrame):
                 {"score_name": "andromeda_score", "score_value": row["andromeda_score"]},
                 {"score_name": "andromeda_delta_score", "score_value": row["andromeda_delta_score"]},
             ],
-            axis=1
+            axis=1,
         )
         df.loc[:, "cv_params"] = df["parent_ion_score"].apply(
             lambda socre: [{"cv_name": "parent_ion_score", "cv_value": str(socre)}]
@@ -298,7 +298,12 @@ def _init_sdrf(self, sdrf_path: str):
         self._sample_map = Sdrf.get_sample_map_run()
 
     def write_feature_to_file(
-        self, evidence_path: str, sdrf_path: str, output_path: str, chunksize: int = 1000000, protein_file=None,
+        self,
+        evidence_path: str,
+        sdrf_path: str,
+        output_path: str,
+        chunksize: int = 1000000,
+        protein_file=None,
     ):
         self._init_sdrf(sdrf_path)
         pqwriter = None
@@ -313,7 +318,7 @@ def write_feature_to_file(
 
     def write_features_to_file(
         self,
-        evidence_path: str, 
+        evidence_path: str,
         sdrf_path: str,
         output_folder: str,
         filename: str,
@@ -331,4 +336,4 @@ def write_features_to_file(
             for key, df in Feature.slice(report, partitions):
                 feature = Feature.transform_feature(df)
                 pqwriters = save_slice_file(feature, pqwriters, output_folder, key, filename)
-        close_file(pqwriters=pqwriters)
+        close_file(pqwriters=pqwriters)

quantmsio/operate/tools.py

@@ -13,6 +13,7 @@
 from quantmsio.utils.pride_utils import get_unanimous_name
 from quantmsio.utils.file_utils import load_de_or_ae, save_slice_file, save_file, close_file
 
+
 def init_save_info(parquet_path: str):
     pqwriters = {}
     pqwriter_no_part = None

quantmsio/utils/file_utils.py

@@ -83,6 +83,7 @@ def calculate_buffer_size(file_path: str) -> int:
 
     return min(int(total_memory * fraction_of_memory), max_buffer_size, file_size)
 
+
 def save_slice_file(parquet_table, pqwriters, output_folder, partitions, filename):
     folder = [output_folder] + [str(col) for col in partitions]
     folder = os.path.join(*folder)
@@ -95,6 +96,7 @@ def save_slice_file(parquet_table, pqwriters, output_folder, partitions, filenam
     pqwriters[partitions].write_table(parquet_table)
     return pqwriters
 
+
 def save_file(parquet_table, pqwriter, output_folder, filename):
     if not os.path.exists(output_folder):
         os.makedirs(output_folder, exist_ok=True)
@@ -104,9 +106,10 @@ def save_file(parquet_table, pqwriter, output_folder, filename):
     pqwriter.write_table(parquet_table)
     return pqwriter
 
+
 def close_file(pqwriters: dict = None, pqwriter: object = None):
     if pqwriter:
         pqwriter.close()
     else:
         for pqwriter in pqwriters.values():
-            pqwriter.close()
+            pqwriter.close()

tests/test_diann.py

@@ -26,7 +26,7 @@ def test_transform_feature(self, test_data):
             D.add_additional_msg(report)
             Feature.convert_to_parquet_format(report)
             Feature.transform_feature(report)
-    
+
     @data(*test_datas)
     def test_transform_features(self, test_data):
         report_file = datafile(test_data[0])
@@ -36,5 +36,5 @@ def test_transform_features(self, test_data):
         for report in D.main_report_df(0.05, mzml, 2):
             D.add_additional_msg(report)
             Feature.convert_to_parquet_format(report)
-            for _, df in Feature.slice(report, ["reference_file_name","precursor_charge"]):
-                Feature.transform_feature(df)
+            for _, df in Feature.slice(report, ["reference_file_name", "precursor_charge"]):
+                Feature.transform_feature(df)

tests/test_maxquant.py

@@ -51,6 +51,5 @@ def test_transform_features(self, test_data):
         for report in M.iter_batch(evidence_file, chunksize=500000):
             M.transform_feature(report)
             Feature.convert_to_parquet_format(report)
-            for _, df in Feature.slice(report, ["reference_file_name","precursor_charge"]):
+            for _, df in Feature.slice(report, ["reference_file_name", "precursor_charge"]):
                 Feature.transform_feature(df)
-