minor cleaning tool.

quantmsutils/diann/diann2mztab.py

@@ -549,6 +549,8 @@ def mztab_mtd(index_ref, dia_params, fasta, charge, missed_cleavages, diann_vers
     :type charge: int
     :param missed_cleavages: Missed cleavages set by Dia-NN
     :type missed_cleavages: int
+    :param diann_version: Version of DIA-NN
+    :type diann_version: str
     :return: MTD sub-table
     :rtype: pandas.core.frame.DataFrame
     """
@@ -1084,15 +1086,15 @@ def __find_info(directory, n):
         # TODO seconds returned from precursor.getRT()
         target.loc[:, "RT"] = target.apply(lambda x: x["RT"] / 60, axis=1)
 
-        RT_matched = pd.merge_asof(group, target, on="RT", direction="nearest")
+        rt_matched = pd.merge_asof(group, target, on="RT", direction="nearest")
         new_target = target
         new_target.columns = [
             "scan_RT",
             "scan_opt_global_spectrum_reference",
             "MS2.Scan",
             "scan_exp_mass_to_charge",
         ]
-        scan_matched = pd.merge(RT_matched, new_target, on="MS2.Scan")
+        scan_matched = pd.merge(rt_matched, new_target, on="MS2.Scan")
 
         #  Cross validation spectrum ID between scan matched and RT matched
         # Keep Scan matched When RT matched and DIA-NN Scan matched are inconsistent in mzML.

quantmsutils/mzml/mzml_statistics.py

@@ -1,7 +1,7 @@
 import re
 import sqlite3
 from pathlib import Path
-from typing import Optional, List
+from typing import Optional, List, Set
 
 import click
 import numpy as np
@@ -198,7 +198,7 @@ def finalize(self):
             self.id_parquet_writer.close()
 
 
-def column_exists(conn, table_name: str) -> List[str]:
+def column_exists(conn, table_name: str) -> Set[str]:
     """
     Fetch the existing columns in the specified SQLite table.
     """

tests/test_commands.py

@@ -42,6 +42,7 @@ def test_extract_sample_from_expdesign_help():
 
     assert result.exit_code == 0
 
+
 def test_sage_feature_file():
     runner = CliRunner()
     result = runner.invoke(
@@ -110,6 +111,7 @@ def test_convert_psm_help():
 
     assert result.exit_code == 0
 
+
 # def test_batch_convert_parquet():
 #     files = ["RD139_Narrow_UPS1_0_1fmol_inj1.mzML",
 #              "RD139_Narrow_UPS1_0_1fmol_inj2.mzML",
@@ -135,6 +137,7 @@ def test_check_samplesheet_help():
 
     assert result.exit_code == 0
 
+
 # test the validation of an SDRF file
 def test_check_samplesheet_sdrf():
     runner = CliRunner()
@@ -187,15 +190,15 @@ def test_mzml_statistics():
 
     table1 = pd.read_parquet("BSA1_F1_ms_info.parquet")
     table2 = pd.read_parquet("tests/test_data/BSA1_F1_ms_info.parquet")
-    table2 = table2.set_index('scan')
-    table1 = table1.set_index('scan')
+    table2 = table2.set_index("scan")
+    table1 = table1.set_index("scan")
 
     assert table1.compare(table2).empty
 
     id_table = pd.read_parquet("BSA1_F1_spectrum_df.parquet")
     id_table2 = pd.read_parquet("tests/test_data/BSA1_F1_spectrum_df.parquet")
-    id_table = id_table.set_index('scan')
-    id_table2 = id_table2.set_index('scan')
+    id_table = id_table.set_index("scan")
+    id_table2 = id_table2.set_index("scan")
 
     assert id_table.shape == id_table2.shape