QC = str(case_SeqInfo['QC'])
# PS1
PS_set = ['PS1', 'PS2']
for PS in PS_set:
HLATyping = case_SeqInfo[PS]['HLATyping']
Donor = case_SeqInfo[PS]['Donor']
Recipient = case_SeqInfo[PS]['Recipient']
record = (BMT_caseID, Audit, Active, Comment, QC, HLATyping, PS, Donor, Recipient, )
cursor.execute('INSERT INTO OriginalSeqs VALUES (?,?,?,?,?,?,?,?,?)', record)
conn.commit()
conn.close()
fname = output + 'SG41_52_HLA_' + locus + '_paired'
IMGTdbIO.save_dict2pickle(available_records, fname)
#aa = IMGTdbIO.load_pickle2dict(fname, output)
#################
# Class II
#################
all_DB_files = glob.glob("../Output/SG41_52/2018/IMGTv3310/AvailDB/*.db")
db_file = all_DB_files[4] ## 0: DPB1 2:DRB1 5:DQB1
locus = db_file.split('_')[4]
conn = sql.connect(db_file) # automatically creates a file if doesn't exist
conn.row_factory = sql.Row # Each row is a dictionary: {colNames: Value}
cursor = conn.cursor()
PS2_HLATyping,
PS2_GLstringM,
PS2_SeqM,
Active,
Audit,
Comment,
)
cursor.execute(
'INSERT INTO DR_pair_comparison VALUES (?,?,?,?,?,?,?,?,?,?,?)',
record)
conn.commit()
conn.close()
fname = '../Output/SG39/2018/SG39_DRpairs/SG39_HLA_' + locus + '_wComparison'
IMGTdbIO.save_dict2pickle(DRpair_seqInfo, fname)
########### check GL-string match, sequence matching
DRpair_seqInfo = {}
Loci = ['A', 'B', 'C', 'DRB1', 'DQB1'] #, 'DPB1']
All_caseIDs = []
for locus in Loci:
fname = '../Output/SG39/2018/SG39_DRpairs/SG39_HLA_' + locus + '_wComparison.pkl'
DRpair_seqInfo[locus] = IMGTdbIO.load_pickle2dict(fname)
All_caseIDs += list(DRpair_seqInfo[locus].keys())
All_caseIDs = list(set(All_caseIDs)) # 3412 total
Matching_cases_stats = {
"ClassI_paired": [],
"fiveLoci_paired": [],
if CaseStats[caseID][locus]['PS1']['ARS'] > 0:
LocusStats[typing]['ARS'].append(caseID)
if CaseStats[caseID][locus]['PS1']['Non_ARS_exon'] >0:
LocusStats[typing]['Non_ARS_exon'].append(caseID)
if CaseStats[caseID][locus]['PS1']['Intron'] > 0:
LocusStats[typing]['Intron'].append(caseID)
for key, item in mm_locus_stats['MMannotation'].items():
if key.isdigit():
if item in LocusStats[typing].keys():
LocusStats[typing][item].append(caseID)
else:
LocusStats[typing] = {item: [caseID]}
ClassI_stats = {'CaseStats': CaseStats, 'LocusStats': LocusStats}
IMGTdbIO.save_dict2pickle(ClassI_stats, '../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/ClassI_Stats_0125_'+groupType) #1220_'+groupType)
# Class II
#Group_fname = '../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/ClassI_Stats_0125_' + groupType + '.pkl'
#Stats_Dict = IMGTdbIO.load_pickle2dict(Group_fname)
#CaseStats = Stats_Dict['CaseStats']
#LocusStats = Stats_Dict['LocusStats']
for caseID in group_caseIDs:
#
for locus in ClassII_loci:
bothMM_output = "../Output/SG41_52/2018/IMGTv3310/SG41_52_bothMisMatched_locus_" + locus + "_0125_TargetedAlignment/"
singleMM_output = "../Output/SG41_52/2018/IMGTv3310/SG41_52_singleMisMatched_" + locus + "_0125_TargetedAlignment/"
### Cases where both sequences don't match
CaseMatchTable[key][locus][ps][
'Intron'].append(annReads)
elif 'UTR' in annItem.split('.')[0]:
CaseMatchTable[key][locus][ps][
'UTR'].append(annReads)
elif 'Exon' in annItem.split('.')[0]:
if annItem.split('.')[0] in ARS_exon:
CaseMatchTable[key][locus][ps][
'ARS'].append(annReads)
else:
CaseMatchTable[key][locus][ps][
'non_ARS_exon'].append(
annReads)
IMGTdbIO.save_dict2pickle(
CaseMatchTable,
'../Output/SG39/2018/SG39_Stats/FiveLoci_paired_case_MatchRecord_Locus_'
+ locus)
IMGTdbIO.save_dict2pickle(
CaseMatchTable,
'../Output/SG39/2018/SG39_Stats/FiveLoci_paired_case_MatchRecord')
################
# Count the cases
################
CaseMatchTable = IMGTdbIO.load_pickle2dict(
'../Output/SG39/2018/SG39_Stats/FiveLoci_paired_case_MatchRecord.pkl')
## : paired cases HLA typing stats
fname = '../Output/SG39/2018/SG39_DRpairs/SG39_pairedCases_Stats.pkl'
Matching_cases_stats = IMGTdbIO.load_pickle2dict(fname)
## Matching_cases_stats['fiveLoci_paired']
if CaseStats[caseID][locus]['PS1']['ARS'] > 0:
LocusStats[typing]['ARS'].append(caseID)
if CaseStats[caseID][locus]['PS1']['Non_ARS_exon'] >0:
LocusStats[typing]['Non_ARS_exon'].append(caseID)
if CaseStats[caseID][locus]['PS1']['Intron'] > 0:
LocusStats[typing]['Intron'].append(caseID)
for key, item in mm_locus_stats['MMannotation'].items():
if key.isdigit():
if item in LocusStats[typing].keys():
LocusStats[typing][item].append(caseID)
else:
LocusStats[typing] = {item: [caseID]}
ClassI_stats = {'CaseStats': CaseStats, 'LocusStats': LocusStats}
IMGTdbIO.save_dict2pickle(ClassI_stats, '../Output/SG39/2018/SG39_Stats/ClassI_Stats_0125_'+groupType)
# Class II
for caseID in group_caseIDs:
#
for locus in ClassII_loci:
bothMM_output = "../Output/SG39/2018/SG39_bothMisMatched_locus_" + locus + "_0125_TargetedAlignment/"
singleMM_output = "../Output/SG39/2018/SG39_singleMisMatched_" + locus + "_0125_TargetedAlignment/"
### Cases where both sequences don't match
if caseID in Matching_cases_stats[locus+'_both_Seqmm']:
mm_file_PS1 = glob.glob(bothMM_output+ 'CaseID_'+ caseID + '_Locus_' + locus + '_annotation_PS1*.pkl')
for file_id in mm_file_PS1:
mm_locus_stats_PS1 = IMGTdbIO.load_pickle2dict(file_id)
#CaseStats[key][locus]
for annKey, annItem in seqAlgn_stats['MMannotation'].items():
if annKey.isdigit():
annReads = IMGTdbIO.annotationFormat(annKey, annItem, seqAlgn_stats['alignment']) #annItem+'[D:'+seqAlgn_stats['alignment']['Donor-'+ps]
if 'Intron' in annItem.split('.')[0]:
CaseMatchTable[key][locus][ps]['Intron'].append(annReads)
elif 'UTR' in annItem.split('.')[0]:
CaseMatchTable[key][locus][ps]['UTR'].append(annReads)
elif 'Exon' in annItem.split('.')[0]:
if annItem.split('.')[0] in ARS_exon:
CaseMatchTable[key][locus][ps]['ARS'].append(annReads)
else:
CaseMatchTable[key][locus][ps]['non_ARS_exon'].append(annReads)
IMGTdbIO.save_dict2pickle(CaseMatchTable, '../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/'+groupType+'_case_MatchRecord_Locus_'+locus)
IMGTdbIO.save_dict2pickle(CaseMatchTable, '../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/'+groupType+'_case_MatchRecord')
################
# Count the cases
################
CaseMatchTable = IMGTdbIO.load_pickle2dict('../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/'+groupType+'_case_MatchRecord.pkl')
#caseID = '44107'
#CaseMatchTable[caseID]
## : paired cases HLA typing stats
fname = '../Output/SG41_52/2018/IMGTv3310/SG41_52_DRpair_Stats/SG41_52_pairedCases_Stats.pkl'
Matching_cases_stats = IMGTdbIO.load_pickle2dict(fname)