def loadHmmerData(filename, eValueCutoff=0.1, basename='hmm'):
domains = hmmer.loadDomains(filename, seqType='BlockSixFrame')
data = []
for i,d in enumerate(domains):
if d.eValue<=eValueCutoff:
# print d
name = '%s%0.2i' % (basename, i)
d.toGenomic()
f = Feature(name,d.accession,d.sStart,d.sEnd,d.strand,d.eValue)
print f
data.append(f)
data = DSU(data, lambda x: (x.chrom, x.start))
return data
if len(warnings2)>0:
h = '%s %s' % (name, '; '.join(warnings2))
else:
h = name
writer.write(h, seq+'\n')
for exon in prediction:
exon.gene_exon = name
print >> annotFile, exon
print >> annotFile
else:
print 'Annotation warnings:', warnings
print 'Annotation errors: ', errors
print
hmmerFilename = 'gsPepHmmer/%s.txt' % name
os.system('hmmsearch %s %s > %s' % (hmmerModel, pepFilename, hmmerFilename))
domains = hmmer.loadDomains(hmmerFilename)
if domains:
print 'Defensin motifs:'
for d in domains:
print d
else:
print 'No defensin motifs'
print
print '='*80 + '\n'
writer.close()
annotFile.close()
oFile.close()
import os, sys
import hmmer, fasta, sequence
homeDir = os.environ['HOME']
blastdb = os.path.join(homeDir, 'databases/opossum/assembly/blastdb/assembly')
ioDir = sys.argv[1]
os.chdir(ioDir)
genomicFile = open('DEFB_genomic.txt', 'w')
summaryFile = open('DEFB_summary.txt', 'w')
dnaWriter = fasta.MfaWriter('DEFB_extracted.fa')
pepWriter = fasta.MfaWriter('DEFB_extracted_pep.fa')
domains = hmmer.loadDomains('DEFB.txt', seqType='BlockSixFrame')
print >> genomicFile, '\t'.join(
domains[0].fields + ['strand', 'lowScoring', 'pseudogene', 'nCysteines'])
for i, domain in enumerate(domains):
if i > 99: break
domain.domain = 'DEFB_%0.2i' % (i + 1)
domain.toGenomic(relative=True)
domain.addField('lowScoring', 'N')
domain.addField('pseudogene', 'N')
domain.addField('nCysteines', 0)
summary = []
h, s = fasta.getSequence(blastdb,
domain.accession,
start=domain.sStart,
import hmmer, fasta, sequence
homeDir = os.environ['HOME']
blastdb = os.path.join(homeDir, 'databases/opossum/assembly/blastdb/assembly')
ioDir = sys.argv[1]
os.chdir(ioDir)
genomicFile = open('DEFB_genomic.txt', 'w')
summaryFile = open('DEFB_summary.txt', 'w')
dnaWriter = fasta.MfaWriter('DEFB_extracted.fa')
pepWriter = fasta.MfaWriter('DEFB_extracted_pep.fa')
domains = hmmer.loadDomains('DEFB.txt', seqType='BlockSixFrame')
print >> genomicFile, '\t'.join(domains[0].fields
+ ['strand', 'lowScoring', 'pseudogene', 'nCysteines'])
for i,domain in enumerate(domains):
if i>99: break
domain.domain = 'DEFB_%0.2i' % (i+1)
domain.toGenomic(relative=True)
domain.addField('lowScoring', 'N')
domain.addField('pseudogene', 'N')
domain.addField('nCysteines', 0)
summary = []
h,s = fasta.getSequence(blastdb, domain.accession,
start=domain.sStart, end=domain.sEnd, strand=domain.strand)
pep = sequence.translate(s)
h = '%s %s' % (name, '; '.join(warnings2))
else:
h = name
writer.write(h, seq + '\n')
for exon in prediction:
exon.gene_exon = name
print >> annotFile, exon
print >> annotFile
else:
print 'Annotation warnings:', warnings
print 'Annotation errors: ', errors
print
hmmerFilename = 'gsPepHmmer/%s.txt' % name
os.system('hmmsearch %s %s > %s' %
(hmmerModel, pepFilename, hmmerFilename))
domains = hmmer.loadDomains(hmmerFilename)
if domains:
print 'Defensin motifs:'
for d in domains:
print d
else:
print 'No defensin motifs'
print
print '=' * 80 + '\n'
writer.close()
annotFile.close()
oFile.close()
