almost there, but abbreviations might be wrong

data/chromosome1.contig

@@ -34754,7 +34754,7 @@ FT                   db_xref=PMID:30566651"
 FT   CDS             join(2167206..2167245,2167302..2168683)
 FT                   /colour=7
 FT                   /product="mitochondrial inner membrane protein involved in
-FT                   translation Mdm28 (predicted)"
+FT                   translation Mdm38 (predicted)"
 FT                   /systematic_id="SPAC23C11.17"
 FT                   /db_xref="SPD:24/24E06"
 FT                   /controlled_curation="term=sequence feature, transmembrane
@@ -34777,7 +34777,8 @@ FT                   /controlled_curation="term=human LETM1 ortholog;
 FT                   date=20100614"
 FT                   /controlled_curation="term=warning, gene structure
 FT                   updated; date=20220825"
-FT                   /primary_name="mdm28"
+FT                   /synonym="mdm28"
+FT                   /primary_name="mdm38"
 FT   intron          2167246..2167301
 FT                   /controlled_curation="term=misc, confirmed intron"
 FT                   /systematic_id="SPAC23C11.17"

data/chromosome2.contig

@@ -60868,8 +60868,8 @@ FT                   /feature_source="evidence=ECO:0000309; source=SO:0001238;
 FT                   condition=FYECO:0000126; during=GO:0072690;
 FT                   score=5.463740; db_xref=PMID:30566651"
 FT   CDS             join(3734792..3735902,3735949..3736232,3736288..3736725,3736788..3736904)
-FT                   /colour=7
-FT                   /product="ER protein folding protein (predicted)"
+FT                   /colour=10
+FT                   /product="ER membrane protein"
 FT                   /db_xref="SPD:27/27H12"
 FT                   /systematic_id="SPBC13G1.05"
 FT                   /controlled_curation="term=sequence feature, transmembrane

protein_modification_qc.py

@@ -59,8 +59,17 @@ def check_func(row, genome, allowed_mod_dict):
         type='dummy',
         rule_name='dummy',
         regex=f'(?<!{aa})({aa})(\d+){aa}?',
+        apply_syntax=lambda x: f'{x[0]}{x[1]}',
     )
-    result = replace_allele_features_with_syntax_rules([dummy_rule], [row['sequence_position']], [], gene)
+    # Special abbreviations for CTD modifications
+    ctd_rule = SyntaxRule(
+        type='ctd_abbreviations',
+        rule_name='ctd_abbreviations',
+        regex='(CTD_S2|CTD_T4|CTD_S5|CTD_S7)',
+        apply_syntax=lambda x: x[0]
+    )
+
+    result = replace_allele_features_with_syntax_rules([dummy_rule, ctd_rule], [row['sequence_position']], [], gene)
 
     # Extract the matched and unmatched elements
     match_groups: list[tuple[re.Match, SyntaxRule]] = list(filter(lambda x: type(x) != str, result))
@@ -70,21 +79,38 @@ def check_func(row, genome, allowed_mod_dict):
     if len(unmatched):
         return 'pattern_error', ''
 
-    correct_name = ','.join(''.join(match_group[0].groups()) for match_group in match_groups)
+    correct_name_list = list()
+    for match_group in match_groups:
+        groups_from_match = match_group[0].groups()
+        syntax_rule = match_group[1]
+        correct_name_list.append(syntax_rule.apply_syntax(groups_from_match))
+
+    correct_name = ','.join(correct_name_list)
 
     change_sequence_position_to = ''
     if correct_name != row['sequence_position']:
         change_sequence_position_to = correct_name
 
-    errors = [check_sequence_single_pos(match_group[0].groups(), gene, 'peptide') for match_group in match_groups]
+    # Error handling ommitted for CTD
+    errors = list()
+    for match_group in match_groups:
+        if match_group[1].rule_name == 'ctd_abbreviations':
+            if systematic_id == 'SPBC28F2.12':
+                continue
+            else:
+                errors.append('no_ctd')
+        else:
+            errors.append(check_sequence_single_pos(match_group[0].groups(), gene, 'peptide'))
 
     if any(errors):
         return '|'.join(errors), change_sequence_position_to
 
     # If there are restriction for this particular MOD, check for those
     if allowed_mod_dict[row['modification']]:
         # Get all letters in the sequence_position
-        residues = set(x for x in re.findall('[a-zA-Z]', row['sequence_position']))
+        # We use ([A-Za-z])(?=\d) instead of [A-Za-z] so that CTD abbreviations such as CTD_S2
+        # are also supported
+        residues = set(x for x in re.findall('([A-Za-z])(?=\d)', row['sequence_position']))
         if any(residue not in allowed_mod_dict[row['modification']] for residue in residues):
             return 'residue_not_allowed', change_sequence_position_to
 

protein_modification_transvar.py

@@ -15,6 +15,19 @@
 tqdm.pandas()
 
 
+def expand_CTD_abbreviations(sequence_position: str) -> str:
+    """Expand CTD abbreviations to all positions"""
+    abbreviations = {
+        "CTD_S2": "S1579,S1586,S1593,S1600,S1607,S1614,S1621,S1628,S1635,S1642,S1649,S1656,S1663,S1670,S1677,S1684,S1691,S1698,S1705,S1712,S1719,S1726,S1733,S1740,S1747",
+        "CTD_T4": "T1584,T1591,T1598,T1605,T1612,T1619,T1626,T1615,T1640,T1647,T1654,T1661,T1663,T1675,T1682,T1689,T1696,T1703,T1710,T1717,T1723,T1731,T1738,T1745,T1752",
+        "CTD_S5": "T1582,T1589,T1596,T1603,T1610,T1617,T1624,T1613,T1638,T1645,T1652,T1659,T1666,T1673,T1680,T1687,T1694,T1701,T1708,T1715,T1722,T1729,T1736,T1743,T1750",
+        "CTD_S7": "S1584,S1591,S1598,S1605,S1612,S1619,S1626,S1615,S1640,S1647,S1654,S1661,S1668,S1675,S1682 S1689,S1696,S1703,S1710,S1717,S1724,S1731,S1738,S1745,S1752"
+    }
+    for key in abbreviations:
+        sequence_position = sequence_position.replace(key, abbreviations[key])
+    return sequence_position
+
+
 def format_for_transvar(row, genome):
 
     # Transvar uses only gene_ids, while the pipeline uses a mix to handle multi-transcripts
@@ -42,6 +55,7 @@ def get_transvar_coordinates(row, db, genome, exclude_transcripts):
     # print(row['systematic_id'], '<<<>>>', row['transvar_input'])
     qc_id = process_systematic_id(row['systematic_id'], genome, 'first')
     transcript_id = None if (qc_id == row['systematic_id']) else qc_id
+    print(row['transvar_input'])
     try:
         transvar_annotation_list = parse_transvar_string(get_transvar_str_annotation('panno', row['transvar_input'], db))
         return get_transvar_annotation_coordinates(transvar_annotation_list, row['systematic_id'], transcript_id)
@@ -69,6 +83,9 @@ def main(genome_file, protein_modification_results_file, exclude_transcripts_fil
     data['exploded_sequence_position'] = data['sequence_position']
     data.loc[data['change_sequence_position_to'] != '', 'exploded_sequence_position'] = data['change_sequence_position_to']
 
+    # Expand CTD abbreviations
+    data['exploded_sequence_position'] = data['sequence_position'].apply(expand_CTD_abbreviations)
+
     # Explode the sequence_position and the rules_applied
     data_exploded = data[['systematic_id', 'sequence_position', 'exploded_sequence_position']].copy()
     data_exploded.drop_duplicates(inplace=True)

results/protein_modification_cannot_fix_other_errors.tsv

@@ -1,11 +1 @@
 systematic_id	primary_name	modification	evidence	sequence_position	annotation_extension	reference	taxon	date	error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2009-07-12	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPAC2F3.15)	PMID:19328067	4896	2009-07-12	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPAC2F3.15)	PMID:19328067	4896	2024-03-05	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2024-03-05	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC19F8.07)	PMID:19328067	4896	2009-07-12	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2009-07-12	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPAC24B11.06c)	PMID:33410907	4896	2021-01-12	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	removed_by(PomBase:SPAC3G9.04)	PMID:33410907	4896	2021-01-22	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC19F8.07)	PMID:19328067	4896	2024-03-05	pattern_error
-SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2024-03-05	pattern_error

results/protein_modification_cannot_fix_sequence_errors.tsv

@@ -163,9 +163,9 @@ SPCC1739.11c	cdc11	MOD:00046	Inferred from Direct Assay	S12		PMID:22419817	4896
 SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8654750	4896	2011-10-10	L23
 SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8654750	4896	2011-10-10	L23
 SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8654750	4896	2011-10-10	L23
-SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:9191272	4896	2011-10-10	L23
-SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8736868	4896	2011-10-10	L23
 SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8861202	4896	2011-10-19	L23
+SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:8736868	4896	2011-10-10	L23
+SPCC1795.06	map2	MOD:01641	Inferred from Direct Assay	L23	removed_by(PomBase:SPAC1296.03c)	PMID:9191272	4896	2011-10-10	L23
 SPCC18B5.11c	cds1	MOD:00696	Inferred from Direct Assay	T121		PMID:24663817	4896	2020-03-09	T121
 SPCC18B5.11c	cds1	MOD:00047	Inferred from Direct Assay	T334	added_by(PomBase:SPCC18B5.11c)	PMID:19357077	4896	2014-02-04	T334
 SPCC18B5.11c	cds1	MOD:00047	Inferred from Direct Assay	T379	added_by(PomBase:SPCC18B5.11c)	PMID:19357077	4896	2014-02-04	T379

rpb_only.tsv

@@ -0,0 +1,11 @@
+systematic_id	primary_name	modification	evidence	sequence_position	annotation_extension	reference	taxon	date	sequence_error	change_sequence_position_to
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2009-07-12		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPAC2F3.15)	PMID:19328067	4896	2009-07-12		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPAC2F3.15)	PMID:19328067	4896	2024-03-05		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S2	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2024-03-05		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC19F8.07)	PMID:19328067	4896	2009-07-12		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2009-07-12		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	removed_by(PomBase:SPAC3G9.04)	PMID:33410907	4896	2021-01-22		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPAC24B11.06c)	PMID:33410907	4896	2021-01-12		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC19F8.07)	PMID:19328067	4896	2024-03-05		
+SPBC28F2.12	rpb1	MOD:00046	Inferred from Direct Assay	CTD_S5	added_by(PomBase:SPBC32H8.10)	PMID:19328067	4896	2024-03-05