Skip to content

Commit

Permalink
filled in missing change_name_to
Browse files Browse the repository at this point in the history
  • Loading branch information
@manulera
manulera committed Jul 19, 2023
1 parent 6d6fc84 commit e647532
Show file tree
Hide file tree
Showing 2 changed files with 30 additions and 23 deletions.
9 changes: 8 additions & 1 deletion manual_fixes_pombase/fill_change_name_for_description_in_name.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@
import sys

manual_changes = pandas.read_csv(sys.argv[1], sep="\t", na_filter=False)
original_dataset = manual_changes.copy()
column_order = list(original_dataset.columns)
manual_changes.fillna('', inplace=True)

# only the ones that did not have a value in change_name_to
Expand All @@ -19,4 +21,9 @@ def get_change_name_to(row):

manual_changes['change_name_to'] = manual_changes.apply(get_change_name_to, axis=1)
manual_changes = manual_changes[manual_changes['change_name_to'] != ''].copy()
manual_changes.to_csv('names_that_should_be_fixed.tsv', sep="\t", index=False)
print(original_dataset.shape)
final_dataset = original_dataset.merge(manual_changes[['allele_name', 'change_name_to']], on='allele_name', how='left')
final_dataset.fillna('', inplace=True)
final_dataset['change_name_to'] = final_dataset.apply(lambda row: row['change_name_to_y'] if row['change_name_to_y'] != '' else row['change_name_to_x'], axis=1)
final_dataset.drop(['change_name_to_x', 'change_name_to_y'], axis=1, inplace=True)
final_dataset[column_order].to_csv('names_filled.tsv', sep="\t", index=False)
44 changes: 22 additions & 22 deletions manual_fixes_pombase/manual_cannot_fix_new.tsv
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
systematic_id allele_name allele_description allele_type reference change_description_to change_name_to change_type_to comment_on_change
SPCC188.06c srp54-G408I G408I amino_acid_mutation PMID:10079327 G407I checked primer mutagenesis in silico
SPCC188.06c srp54-G408P G408P amino_acid_mutation PMID:10079327 G407P checked primer mutagenesis in silico
SPCC188.06c srp54-G408I G408I amino_acid_mutation PMID:10079327 G407I srp54-G407I checked primer mutagenesis in silico
SPCC188.06c srp54-G408P G408P amino_acid_mutation PMID:10079327 G407P srp54-G407P checked primer mutagenesis in silico
SPSNRNA.02 snu2-M1 CTTCTTCT187TACTAGTG nucleotide_mutation PMID:10445882 CTTCTTCT-189-TACTAGTG coords were shifted by 2
SPSNRNA.02 snu2-M2 GTTGACAG195TACTAGTA nucleotide_mutation PMID:10445882 GTTGACAG-197-TACTAGTA coords were shifted by 2
SPSNRNA.02 snu2-M3 ATTTGTGA203GACTAGTC nucleotide_mutation PMID:10445882 ATTTGTGA-205-GACTAGTC coords were shifted by 2
Expand All @@ -21,9 +21,9 @@ SPAC644.14c rad51-ATGTG G-188T,G-237T nucleotide_mutation PMID:11073995 G(-231)T
SPAC644.14c rad51-CT2CA AGGTG-236CTTCA,AGGTA187CTTCG nucleotide_mutation PMID:11073995 AGGTG-(-232)-CTTCA,AGGTA-(-211)-CTTCG
SPAC3H5.06c pol1-ts11 C2519T nucleotide_mutation PMID:11581276,PMID:12697806,PMID:9693370,PMID:9891047 T840I amino_acid_mutation
SPCC736.14 dis1-203 Q265* partial_amino_acid_deletion PMID:11683390 S265*
SPCC645.03c isa1-C136A C136A amino_acid_mutation PMID:11941510 C180A checked primer mutagenesis in silico
SPCC645.03c isa1-C138A C138A amino_acid_mutation PMID:11941510 C182A checked primer mutagenesis in silico
SPCC645.03c isa1-C72A C72A amino_acid_mutation PMID:11941510 C116A checked primer mutagenesis in silico
SPCC645.03c isa1-C136A C136A amino_acid_mutation PMID:11941510 C180A isa1-C180A checked primer mutagenesis in silico
SPCC645.03c isa1-C138A C138A amino_acid_mutation PMID:11941510 C182A isa1-C182A checked primer mutagenesis in silico
SPCC645.03c isa1-C72A C72A amino_acid_mutation PMID:11941510 C116A isa1-C116A checked primer mutagenesis in silico
SPBC336.04 cdc6-ts3 G3191A nucleotide_mutation PMID:12697806,PMID:7700230,PMID:8367300,PMID:9135148,PMID:9154809,PMID:9348105,PMID:9794798,PMID:9891047 R1064Q amino_acid_mutation
SPBC336.04 cdc6-ts1 C428U,C430U nucleotide_mutation PMID:12697806,PMID:7700230,PMID:8367300,PMID:9794798,PMID:9891047 AP-143-VS amino_acid_mutation
SPBC336.04 cdc6-ts2 G811A nucleotide_mutation PMID:12697806,PMID:7700230,PMID:8367300,PMID:9891047 E271K amino_acid_mutation
Expand All @@ -34,11 +34,11 @@ SPBC1685.01 pmp1-M13 A1288U,A1300U nucleotide_mutation PMID:12931193 A1009T,A102
SPBC1685.01 pmp1-M2 A1293U nucleotide_mutation PMID:12931193 A1014T
SPBC1685.01 pmp1-M23 A1293U,A1300U nucleotide_mutation PMID:12931193 A1014T,A1021T
SPBC1685.01 pmp1-M3 A1300U nucleotide_mutation PMID:12931193 A1021T
SPSNRNA.04 snu4-4 TTTTG104ACGTC nucleotide_mutation PMID:1441744 T105A,T106C,T107G,G109C
SPSNRNA.04 snu4-4 TTTTG104ACGTC nucleotide_mutation PMID:1441744 T105A,T106C,T107G,G109C
SPSNRNA.04 snu4-6 AAAACT87CCCGGG nucleotide_mutation PMID:1441744 AAAACT-67-CCCGGG
SPSNRNA.04 snu4-7 CGTAGT59GCATCG nucleotide_mutation PMID:1441744 GCTAGT-59-CGATCG
SPCC5E4.04 ptr4-1 T3487A,T3505A nucleotide_mutation PMID:14511667,PMID:9168469 T1099A,T1117A
SPAC57A10.10c sla1-R266E,R267L R266E,R267L amino_acid_mutation PMID:14665462 R256E,R257L
SPAC57A10.10c sla1-R266E,R267L R266E,R267L amino_acid_mutation PMID:14665462 R256E,R257L sla1-R256E,R257L
SPCC285.09c cgs2-CRE promoter binding site mutant -G67T,-C68A nucleotide_mutation PMID:15448137 C(-68)A,G(-67)T
SPBC1734.02c cdc27-R39 A837-TCGACAATCGATAAGACTGACA nucleotide_insertion PMID:15576681 A827-TCGACAATCGATAAGACTGACA
SPBC336.04 cdc6-R18 C2905T nucleotide_mutation PMID:15576681 C2957T
Expand All @@ -60,15 +60,15 @@ SPBP19A11.06 lid2-H512A H512A amino_acid_mutation PMID:18957202 H542A lid2-H542A
SPAC19B12.05c fcp1-W405S W405S amino_acid_mutation PMID:19026779 W305S fcp1-W305S typo in pombase
SPAC19E9.02 fin1-KD K63R,N165A amino_acid_mutation PMID:22684255 K33R,N165A typo in PomBase
SPAC24B11.11c sid2-as4 M285A,T384A amino_acid_insertion_and_mutation PMID:22684255,PMID:23333317 M285A,T348A amino_acid_mutation typo in PomBase
SPAC22A12.15c bip1-G373C G373C nucleotide_mutation PMID:23066505 G2365C
SPAC22A12.15c bip1-G373U G373U nucleotide_mutation PMID:23066505 G2365T
SPAC22A12.15c bip1-deltaTTAACTGGTG\C 364-374 partial_nucleotide_deletion PMID:23066505 2356-2366
SPBC23G7.11 mag2-A56S A56S amino_acid_mutation PMID:23273506 D56A typo in PomBase
SPCC825.02 gbs1-W409A W409A amino_acid_mutation PMID:23609449 W432A simulated primer mutagenesis
SPCC825.02 gbs1-W409F W409F amino_acid_mutation PMID:23609449 W432F simulated primer mutagenesis
SPAC22A12.15c bip1-G373C G373C nucleotide_mutation PMID:23066505 G2365C bip1-G2365C
SPAC22A12.15c bip1-G373U G373U nucleotide_mutation PMID:23066505 G2365T bip1-G2365T
SPAC22A12.15c bip1-deltaTTAACTGGTG\C 364-374 partial_nucleotide_deletion PMID:23066505 2356-2366
SPBC23G7.11 mag2-A56S A56S amino_acid_mutation PMID:23273506 D56A mag2-D56A typo in PomBase
SPCC825.02 gbs1-W409A W409A amino_acid_mutation PMID:23609449 W432A gbs1-W432A simulated primer mutagenesis
SPCC825.02 gbs1-W409F W409F amino_acid_mutation PMID:23609449 W432F gbs1-W432F simulated primer mutagenesis
SPNCRNA.214 ter1-STEloop UUUU1071AAAA nucleotide_mutation PMID:26305931 TTTT-1065-AAAA
SPNCRNA.98 srp7-A163C,C164A A163C,G164A nucleotide_mutation PMID:2657742 A163C,C164A
SPBC36B7.09 gcn2-Y1119L,R1120L Y1119L,R1120L amino_acid_mutation PMID:28771613 F1066A,R1067L PomBase value was the cerevisiae coords
SPBC36B7.09 gcn2-Y1119L,R1120L Y1119L,R1120L amino_acid_mutation PMID:28771613 F1066A,R1067L gcn2-F1066A,R1067L PomBase value was the cerevisiae coords
SPBC1718.07c zfs1-S164A,T1645A S164A,T164A amino_acid_mutation PMID:29084823 S164A,T165A zfs1-S164A,T1645A typo in PomBase
SPBC8E4.01c pho84-TATA box mutant T-33C,A-32G,T-31C,A-30G,T-29C,A-28G,T-27C,A-26G nucleotide_mutation PMID:29414789 TATATATA-(-184)-CGCGCGCG negative coords in paper refer to the 5UTR, not the transcription start
SPNCRNA.1698 nc-tgp-+5_seb1_bs G521T,T543A,A554T,C569G,C578G nucleotide_mutation PMID:32499400 T543A,G549C,A554T,A560-T,T561A,C570G,G573A,C579G,T582A nucleotide_insertion_and_mutation
Expand All @@ -83,17 +83,17 @@ SPAC926.04c hsp90-EATK E34A,E384K amino_acid_mutation PMID:37120429 E34A,E367K
SPNCRNA.82 mrp1-B7 A370G nucleotide_mutation PMID:8887563 A371G
SPNCRNA.82 mrp1-LoopB U339A,A340C,U343G nucleotide_mutation PMID:8948095 T340A,A341C,T344G simulated primer mutagenesis
SPNCRNA.82 mrp1-Pt1-9 U359A,C356A nucleotide_mutation PMID:8948095 C357A,T360A drawing
SPNCRNA.82 mrp1-U359A U359A nucleotide_mutation PMID:8948095 C357A drawing
SPNCRNA.82 mrp1-LoopA T372A,C373A,C375-G,T378G fusion_or_chimera PMID:8948095 nucleotide_insertion_and_mutation
SPNCRNA.82 mrp1-U359A U359A nucleotide_mutation PMID:8948095 C357A mrp1-C357A drawing
SPNCRNA.82 mrp1-LoopA T372A,C373A,C375-G,T378G fusion_or_chimera PMID:8948095 nucleotide_insertion_and_mutation
SPBC1604.21c ptr3-1 C1892A nucleotide_mutation PMID:9168469 C1893A From drawing, Thr576 to Lys
SPBC800.05c alp2-996 G1065A nucleotide_mutation PMID:9658169 G1067A From drawing Fig. 4 C356Y
SPBC800.05c ban5-996 unknown PMID:8876193 G1067A nucleotide_mutation From drawing Fig. 4 C356Y in PMID:9658169
SPBC26H8.07c alp12-1828 unknown unknown PMID:9658169 T1566C nucleotide_mutation Text description: substitution of Tyr by His at residue 422
SPAC3H5.06c pol1-L471A L471A amino_acid_mutation PMID:9693370 S471A typo in paper
SPAC3H5.06c pol1-S470A S470A amino_acid_mutation PMID:9693370 L470A typo in paper
SPAC3H5.06c pol1-L471A L471A amino_acid_mutation PMID:9693370 S471A pol1-S471A typo in paper
SPAC3H5.06c pol1-S470A S470A amino_acid_mutation PMID:9693370 L470A pol1-L470A typo in paper
SPAC3H5.06c pol1-ts17 C1388T,C1870T,G3547A nucleotide_mutation PMID:9693370 A463V,H624Y,D1183N amino_acid_mutation
SPBC216.07c tor2-ts10 asked amino_acid_mutation PMID:17261596,PMID:20144990,PMID:22976295,PMID:26152587,PMID:27165118,PMID:29079657 A1399E,F2198L
SPBC216.07c tor2-ts6 asked amino_acid_mutation PMID:17261596,PMID:19620394,PMID:20144990,PMID:22976295,PMID:24741065,PMID:27165118,PMID:28671615,PMID:29330317,PMID:33574613 S550P,K711M
SPBC216.07c tor2-ts10 asked amino_acid_mutation PMID:17261596,PMID:20144990,PMID:22976295,PMID:26152587,PMID:27165118,PMID:29079657 A1399E,F2198L
SPBC216.07c tor2-ts6 asked amino_acid_mutation PMID:17261596,PMID:19620394,PMID:20144990,PMID:22976295,PMID:24741065,PMID:27165118,PMID:28671615,PMID:29330317,PMID:33574613 S550P,K711M
SPBC660.13c rad11A unknown unknown PMID:10888871,PMID:9111307 R339H amino_acid_mutation from PMID:37200372
SPNCRNA.98 srp7-A163U,C169U6 A163U,C169U6 nucleotide_mutation PMID:1315954 A163U,C169U srp7-A163T,C169T
SPNCRNA.98 srp7-G72A,G78A,G100A,G107A,Gl12A,G141A G72A,G78A,G100A,G107A,Gl12A,G141A nucleotide_mutation PMID:1315954 G72A,G78A,G100A,G107A,G112A,G141A srp7-G72A,G78A,G100A,G107A,G112A,G141A
Expand Down Expand Up @@ -150,7 +150,7 @@ SPCC306.03c L318E amino_acid_mutation PMID:31072933 K318E cnd2-K318E typo in P
SPCC576.15c P320R amino_acid_mutation PMID:31072933 T320R ksg1-T320R typo in PomBase
SPBC31E1.02c pmr1-W880->stop W800->stop nonsense_mutation PMID:31201205 W880* pmr1-W880* typo in pombase
SPAC222.14c sey1-K53A K53A amino_acid_mutation PMID:32023460 K52A sey1-K52A Fig. 6 of https://doi.org/10.1016/j.cell.2009.05.025
SPNCRNA.899 SPNCRNA.899-G754C G754C nucleotide_mutation PMID:32142608 C754G Wrong orientation in the original description
SPNCRNA.899 SPNCRNA.899-G754C G754C nucleotide_mutation PMID:32142608 C754G SPNCRNA.899-C754G Wrong orientation in the original description
SPBC31F10.14c hip3-Q808-stop Q808stop amino_acid_mutation PMID:34580178 C808* hip3-C808* typo in pombase
SPAC6B12.07c pqr1-I84S I87S amino_acid_mutation PMID:35012333 I84S typo in pombase
SPCC16C4.11 pef1-N146S N146S amino_acid_mutation PMID:31895039 N131S
SPCC16C4.11 pef1-N146S N146S amino_acid_mutation PMID:31895039 N131S pef1-N131S

0 comments on commit e647532

Please sign in to comment.