def loadProtIdsOrgType(self,db,idGenSeq,inserterSeq,orgType):
"""Load Fasta deflines for protein sequences generated by pullSeq, parse and insert them into SQL table.
"""
inFasta = self.store.getFilePath('%s.protein.cat.gz' % orgType)
inp = FastaReader(inFasta)
for rec in inp.records():
hdr = CvTreeId.splitFastaDeflineCvTree(rec.header())
idSeq = idGenSeq()
seqLen = rec.seqLen()
values = (idSeq,hdr.taxid,seqLen,hdr.acc,hdr.acc_gen,orgType[:4])
inserterSeq(values)
inp.close()
def loadGenomicIdsOrgType(self,db,idGenSeq,inserterSeq,orgType):
"""Load Fasta deflines for genomic sequences, index them by accession, and drop non-NC_ and all plasmids.
@todo It might be more robust to parse the GenBank file, e.g.
FEATURES Location/Qualifiers
source 1..208369
/organism="Bacillus cereus ATCC 10987"
/mol_type="genomic DNA"
/strain="ATCC 10987"
/db_xref="ATCC:10987"
/db_xref="taxon:222523"
/plasmid="pBc10987"
gene join(207497..208369,1..687)
We would have to fix the gap(unk100) bug first, and also check how the "extrachromosomal" is labeled
in GB file.
"""
if orgType == "outgroup":
inFasta = self.outGroupFna
else:
inFasta = pjoin(options.refSeqDataDir,"%s.genomic.fna.gz" % orgType)
inp = FastaReader(inFasta)
for rec in inp.records():
line = rec.header()[1:]
parts = line.strip().split('|',4)
assert parts[0] == 'gi'
gi = int(parts[1])
assert parts[2] == 'ref'
acc = parts[3].strip()
# we can do re.search(r'\bplasmid\b',) instead, but this is safer
# (there is a record called 'megaplasmid'):
if acc[:3] == 'NC_':
hdr = (' '.join(parts[4:])).strip()
hlow = hdr.lower()
## genel values must differ by the first letter - this is used
## by the name generation method later
if 'plasmid' in hlow:
genel = "pla"
elif 'extrachromosomal' in hlow or 'extra-chromosomal' in hlow:
genel = "ext"
elif 'transposon' in hlow:
genel = "tra"
else:
genel = "chr"
idSeq = idGenSeq()
seqLen = rec.seqLen()
values = (idSeq,gi,0,seqLen,acc,genel,orgType[:4],hdr)
#values = [ str(x) for x in values ]
inserterSeq(values)
inp.close()
def makeFeat(self):
"""Create feature vectors out of FASTA files."""
maxSampLen = 100000
kmerCnt = KmerSparseFeatures(sampLen=maxSampLen,
kmerLen=2,
rcPolicy=RC_POLICY.MERGE,
normPolicy=NORM_POLICY.FREQ)
for fastaFile in self.store.getFilePaths("*.fasta.gz"):
inpFasta = FastaReader(fastaFile)
iRec = 0
for rec in inpFasta.records():
kmerCnt.process(rec.sequence(format="array"))
iRec += 1
if iRec > 100:
break
inpFasta.close()
feat = kmerCnt.kmerFrequencies()
id = stripSfx(os.path.basename(fastaFile),".fasta.gz")
print id, feat
