def append_ti_into_fasta_hash(nt, gi2taxFn, Ti2sel, enable_descF, enable_onlineF,
nt2, noTaxIdFa, invalSelFlag):
NOT_AVAIL=0
NOT_VALID=-1
GET_ALL_TAX=-2
TAXONOMY_ID=1
#check if nt has ti tagged already
tiReadyF=False
if check_if_nt_has_ti(nt):
tiReadyF=True
if not tiReadyF:
(maxGi,gi2ti)=gi2tax_list(gi2taxFn)
get_all_taxF=False
if Ti2sel[0]==GET_ALL_TAX:
get_all_taxF=True
if os.path.exists(nt2):
return (nt2,noTaxIdFa)
print 'selecting some reference genome sequences in [%s]...' % nt
if (invalSelFlag):
fp1 = open(noTaxIdFa,'w')
with open(nt2,'w') as fp2:
with open(nt,'r') as fp:
if tiReadyF:
for r in seqParse.parse(fp,'fasta'):
#print r.id #debug
mObj=re.search(r'ti\|(\d+)\|',r.id)
if not mObj:
continue
ti=int(mObj.group(1))
if get_all_taxF or (ti in Ti2sel):
if enable_descF and r.description:
fp2.write('>%s\n%s\n' % (r.description, r.seq))
else:
fp2.write('>%s\n%s\n' % (r.id, r.seq))
else:
for r in seqParse.parse(fp,'fasta'):
mObj=re.search(r'gi\|(\d+)\|\S+\|(\S+)',r.id)
if not mObj:
continue
gi=int(mObj.group(1))
if gi>maxGi or gi2ti[gi]==NOT_AVAIL:
if enable_onlineF:
genbank_id=mObj.group(2) #telling exactly, it must be any gene name in a database
#genbank_id=entries[3] #telling exactly, it must be any gene name in a database
ti=pathoUtilsA.ncbi_eutil(gi,genbank_id,TAXONOMY_ID) #updated ti
else:
ti=NOT_VALID
else:
ti=gi2ti[gi]
if gi<maxGi:
gi2ti[gi]=ti
if ti==NOT_VALID:
if invalSelFlag:
fp1.write('>ti|-1|%s\n%s\n' % (r.description, r.seq))
else:
if get_all_taxF or (ti in Ti2sel):
if enable_descF:
fp2.write('>ti|%d|%s\n%s\n' % (ti, r.description, r.seq))
else:
fp2.write('>ti|%d|%s\n%s\n' % (ti, r.id, r.seq))
print 'check %s' % nt2
if (invalSelFlag):
fp1.close()
print 'check %s' % noTaxIdFa
print 'done.'
def append_ti_into_fasta_mysql(con, nt, Ti2sel, enable_descF, enable_onlineF,
nt2, noTaxIdFa, invalSelFlag):
NOT_VALID=-1
GET_ALL_TAX=-2
TAXON_ID=1
#check if nt has ti tagged already
tiReadyF=False
if check_if_nt_has_ti(nt):
tiReadyF=True
get_all_taxF=False
if Ti2sel[0]==GET_ALL_TAX:
get_all_taxF=True
print 'selecting some reference genome sequences in [%s]' % nt
if (invalSelFlag):
fp1 = open(noTaxIdFa,'w')
with open(nt2,'w') as fp2:
with open(nt,'r') as fp:
for r in seqParse.parse(fp,'fasta'):
if tiReadyF:
mObj=re.search(r'ti\|(\d+)\|',r.id)
if not mObj:
continue
ti=int(mObj.group(1))
if ti!=NOT_VALID and (get_all_taxF or (ti in Ti2sel)):
if enable_descF and r.description:
fp2.write('>%s\n%s\n' % (r.description, r.seq))
else:
fp2.write('>%s\n%s\n' % (r.id, r.seq))
else:
mObj=re.search(r'gi\|(\d+)\|\S+\|(\S+)',r.id)
if not mObj:
continue
gi=int(mObj.group(1))
with con:
cur=con.cursor()
sqlcmd='select taxon from giAnnoT where gi=%d' %gi
cur.execute(sqlcmd)
entr = cur.fetchone()
if entr:
ti=int(entr[0])
elif enable_onlineF:
seqId=int(mObj.group(2))
ti=pathoUtilsA.ncbi_eutil(gi,seqId,TAXON_ID) #updated ti
else:
ti=NOT_VALID
if ti==NOT_VALID:
if (invalSelFlag):
fp1.write('>ti|-1|%s\n%s\n' % (r.description,r.seq))
else:
if get_all_taxF or (ti in Ti2sel):
organismName, _ = dbUtils.findOrganismLineage(con, ti)
organismName = re.sub('\s+', '_', organismName)
if enable_descF and r.description:
fp2.write('>ti|%d|org|%s|%s\n%s\n' % (ti, organismName,
r.description, r.seq))
else:
fp2.write('>ti|%d|org|%s|%s\n%s\n' % (ti, organismName,
r.id, r.seq))
print 'check %s' % nt2
if (invalSelFlag):
fp1.close()
print 'check %s' % noTaxIdFa
print 'done.'
