cleaned up masterlocalization parsing to remove unnecessary insertion of...

cleaned up masterlocalization parsing to remove unnecessary insertion of tuples to the localization list instead of simply appending them

main.py

@@ -23,16 +23,18 @@ def main():
     input_data: List[FileTuple] = ingestfiledata(files=input_files)
     protein_seqrecords: List[SeqRecord] = getproteinsequences(protein_fasta_files)
     data = [genrawsequences(ftuple) for ftuple in input_data]
-    localization_col_titles = []
-    localized_data = []
+
+    localization_col_titles: List[Tuple[str, str]] = []  # list of tuples containing (fileID, column title)
+    localized_data: List[FileTuple] = []
 
     # localized_data += [parsemasterlocalizations(ftuple) for ftuple in data]
     # localization_col_titles += ['master_localized_mods']
     for ftuple in data:
         if use_mod_in_master_prot:
-            file_headers_tuple = parsemasterlocalizations(ftuple)
+            file_headers_tuple: Tuple[FileTuple, List[Tuple[str, str]]] = parsemasterlocalizations(ftuple)
         else:
-            file_headers_tuple = parseprotlocalizations(ftuple, protein_seqrecords)
+            file_headers_tuple: Tuple[FileTuple, List[Tuple[str, str]]] = parseprotlocalizations(ftuple,
+                                                                                                 protein_seqrecords)
         localized_data += file_headers_tuple[0]  # add the filetuple to the list of localized filetuples
         localization_col_titles += file_headers_tuple[1]  # add the list of (fileid, column title) tuples
 
@@ -79,14 +81,15 @@ def genrawsequences(ftuple: FileTuple) -> FileTuple:
 def parsemasterlocalizations(ftuple: FileTuple) -> Tuple[FileTuple, List[Tuple[str, str]]]:
     # todo: other PTMs
     # todo: file specified regex string
+    # NOTE: does not work on files with multiple master proteins
     # matches serine, threonine, tyrosine and 0 or more digits
     # this provides support for unlocalized PTM where only the amino acid is present and not the localization
     # regex = eval(r"r'[STY]([\d]{0,})'") can use this syntax to read in regex string regex
-    regex = r'[STY]([\d]{0,})'
+
+    regex = r'[STY]([\d]{0,})'  # specific to serine, threonine, tyrosine phosphorylation
     file_data = ftuple.FileData
     localizations = []
-    # matches = re.finditer(regex, test_str, re.MULTILINE)
-    # print(list(matches))
+
     for row in file_data.itertuples():
         mod_string = row.modifications_in_master_proteins
         # example modstring "P10636-8 2xPhospho [S383; S]"
@@ -95,11 +98,11 @@ def parsemasterlocalizations(ftuple: FileTuple) -> Tuple[FileTuple, List[Tuple[s
         if not str(mod_string) == "nan":
             matches = re.finditer(regex, mod_string)
             matched_strs = []
-            for matchobj in matches:
-                matched_strs.append(matchobj.groups())
+            for match_obj in matches:
+                matched_strs.extend(match_obj.groups())
             localizations.append(matched_strs)
         else:
-            localizations.append([()])
+            localizations.append([])
 
     file_data.insert(file_data.shape[1], "master_localized_mods", localizations)
     return FileTuple(ftuple.FileName, file_data), [(file_data['master_protein_accessions'][1], "master_localized_mods")]