def form_alleles(self, regions, qrySeq, qryQual, genome_id, accepted, argument) :
alleles = {}
regions.sort(key=lambda x:x['identity'], reverse=True)
regions.sort(key=lambda x:min(x['flanking'] + [0]), reverse=True)
for region in regions:
if sum(region['flanking']) >= -30 and (argument.get('ORF', False) or argument.get('CDS', False)) and region['CIGAR'] != 'intergenic' :
flag = self.lookForORF(qrySeq, region)
region['accepted'] = region['accepted'] | flag
region['seq'] = self.get_seq(qrySeq, *region['coordinates'])
region['id'] = ''
region['value_md5'] = get_md5(region['seq'])
if min(region['flanking']) >= 0 and len(re.findall(r'[^ACGT]', region['seq'])) == 0 : ## add proportional check
region['accepted'] = region['accepted'] | 1
else :
region['status'] += '{Fragmented}'
region['accepted'] = region['accepted'] | 64
region['allele_id'] = -1
if region['locus'] in alleles :
if region['accepted'] & 64 > 0 :
if alleles[ region['locus'] ]['accepted'] & 64 > 0 :
if 'secondary' not in alleles[ region['locus'] ] :
alleles[ region['locus'] ]['secondary'] = []
alleles[ region['locus'] ]['secondary'].append( dict(coordinates =region['coordinates'], seq=region['seq'], identity=region['identity']) )
elif alleles[ region['locus'] ] ['accepted'] & 32 == 0 :
alleles[ region['locus'] ] ['status'] += '{Duplicated}'
alleles[ region['locus'] ] ['seq'] = 'DUPLICATED'
alleles[ region['locus'] ] ['value_md5'] = get_md5('DUPLICATED')
alleles[ region['locus'] ] ['accepted'] = (alleles[ region['locus'] ] ['accepted'] | 32) & (~1)
alleles[ region['locus'] ] ['allele_id'] = -1
if 'secondary' not in alleles[ region['locus'] ] :
alleles[ region['locus'] ]['secondary'] = []
alleles[ region['locus'] ]['secondary'].append( dict(coordinates =region['coordinates'], seq=region['seq'], identity=region['identity']) )
else :
if accepted == 0 or self.get_qual(qryQual, *region['coordinates']) < 10:
region['accepted'] = region['accepted'] | 2
region['reference'] = 'MLSType:'+genome_id
alleles[region['locus']] = region
if region['accepted'] & 2 > 0 :
region['accepted'] = region['accepted'] & (~1)
for locus, allele in alleles.items() :
if allele['accepted'] & 65 == 64 :
allele_len = allele['coordinates'][2] - allele['coordinates'][1] + 1
for ale in allele.get('secondary', {}) :
allele_len += ale['coordinates'][2] - ale['coordinates'][1] + 1
if allele_len < argument['min_frag_prop'] :
alleles.pop(locus)
if 'identity' in allele and allele['identity'] < argument['min_iden'] :
allele['allele_id'] = -1
allele['accepted'] = (allele['accepted'] & (~1)) | 256
allele['status'] += '{Low identities:'+str(allele['identity'])+'}'
if allele['accepted'] & 224 > 0 :
alleles.pop(locus, None)
return alleles
def MLSTdb(args):
params = getParams(args)
database, refset, alleleFasta, refstrain, max_iden, min_iden, coverage, paralog, relaxEnd = params[
'database'], params['refset'], params['alleleFasta'], params[
'refstrain'], params['max_iden'], params['min_iden'], params[
'coverage'], params['paralog'], params['relaxEnd']
if os.path.isfile(alleleFasta):
alleles = readFasta(uopen(alleleFasta))
else:
alleles = readFasta(StringIO(alleleFasta))
alleles = [allele for allele in alleles \
if allele['value_id'].isdigit() and int(allele['value_id']) > 0 and allele['fieldname'].find('/') < 0]
refAlleles = ''
if refset is not None:
if refstrain:
if os.path.isfile(refstrain):
references = readFasta(uopen(refstrain))
else:
references = readFasta(StringIO(refstrain))
else:
loci, references = {}, []
for allele in alleles:
if allele['fieldname'] not in loci:
loci[allele['fieldname']] = 1
references.append(allele)
allele_text, refAlleles = buildReference(alleles, references, max_iden,
min_iden, coverage, paralog,
relaxEnd)
if refset:
with open(str(refset), 'w') as fout:
fout.write(refAlleles + '\n')
logger('A file of reference alleles has been generated: {0}'.format(
refset))
if database:
conversion = [[], []]
with open(database, 'w') as fout:
for allele in alleles:
conversion[0].append(get_md5(allele['value']))
conversion[1].append(
[allele['fieldname'],
int(allele['value_id'])])
conversion = pd.DataFrame(conversion[1], index=conversion[0])
conversion.to_csv(database, header=False)
logger('A lookup table of all alleles has been generated: {0}'.format(
database))
return allele_text, refAlleles