def runGenomescan(features, debug=False):
"""Run genomescan supplying extracted features from genome as
homologous proteins."""
for i, feature in enumerate(features):
print i + 1, feature
oFilename = 'gsOutput/%s.html' % feature.domain
annotFilename = 'gsAnnotations/%s.txt' % feature.domain
pepFilename = 'gsPeptides/%s.fa' % feature.domain
if not os.path.exists(oFilename):
html = genomescanFromFeature(feature,
blastDb,
oFileHandle=oFilename)
else:
html = open(oFilename).read()
html = html.split('\n')
annotation, peptides = parseGenomeScanOutput(html)
print >> open(annotFilename, 'w'), annotation
fakeFaFile = StringIO.StringIO(peptides)
faIter = fasta.load_iter(fakeFaFile)
writer = fasta.MfaWriter(pepFilename)
for j, (h, s) in enumerate(faIter):
block = h.split('|')[0]
if j == 1: print feature
h = '%s.%i %s' % (feature.domain, j + 1, block)
writer.write(h, s + '\n')
writer.close()
def Initialize():
header, seq = fasta.load('MHC_hg18.fa')
sixFrameIter = sequence.sixFrameTranslationIter(seq)
writer = fasta.MfaWriter('6frames.fa')
for frame, p in sixFrameIter:
print 'Frame:', frame
writer.write('%s:%i' % (header, frame), p)
writer.close()
sys.exit()
import os, sys
import re, copy
import fasta, sequence, hmmer3
seqFilename = sys.argv[1]
header, seq = fasta.load(seqFilename)
header = header.split()[0]
L = len(seq)
pattern = re.compile('\*')
minLen = 10
sixFrameIter = sequence.sixFrameTranslationIter(seq)
writer = fasta.MfaWriter(sys.stdout)
i = 0
for frame, p in sixFrameIter:
print >> sys.stderr, 'Frame:', frame
matchIter = pattern.finditer(p)
match = matchIter.next()
start = match.start()
for match in matchIter:
end = match.start()
orf = p[start + 1:end]
length = len(orf)
if length >= minLen:
gStart, gEnd, strand = hmmer3.convertSixFrameToGenomic(
start + 1, end + 1, frame, L)
Date: Tue Aug 15 10:18:46 EST 2006
"""
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 = []
Author: Tony Papenfuss
Date: Wed Aug 23 08:52:58 EST 2006
"""
import os, sys
import re, copy
import fasta, sequence, hmmer3
from hmmer3 import hmmer2frame
pattern = re.compile('[\*|X{200,}]')
minLen = 20
i = 0
writer = fasta.MfaWriter('ORFs.fa')
faFile = fasta.load_iter('6frames.fa')
for header, seq in faFile:
header = header.strip()
print >> sys.stderr, header
block, hmmerFrame = header.split(':')
frame = hmmer2frame[int(hmmerFrame)]
matchIter = pattern.finditer(seq)
try:
match = matchIter.next()
except StopIteration:
print match
print seq
sys.exit()
if len(args)!=3:
sys.exit(__doc__)
gffFilename = args[1]
faFilename = args[2]
data = gff.load(gffFilename)
header,seq = fasta.load(faFilename)
if options.oFilename:
oFile = open(options.oFilename, 'w')
else:
oFile = sys.stdout
writer = fasta.MfaWriter(oFile)
for name in data:
s = []
extrema = []
for f in data[name]:
if f.type in options.features:
if f.strand=='+':
start,end = f.start,f.end
_seq = seq[start-1:end]
else:
start,end = f.start,f.end
_seq = seq[start-1:end]
_seq = sequence.reverse_complement(_seq)
s.append(_seq)
extrema.append(f.start)
extrema.append(f.end)
return isCoding, warnings, errors
# ----------------------------------------------------------------------
ioDir = sys.argv[1]
os.chdir(ioDir)
oFile = open('checkResults.txt', 'w')
sys.stdout = oFile
hmmerModel = {
'round1': '../../HMMs/Defensin_beta.hmm',
'round2': '../../HMMs/Defensin_beta_new.hmm'
}[ioDir]
writer = fasta.MfaWriter('peptides.fa')
annotFile = open('annot.txt', 'w')
annotFilenames = glob.glob('gsAnnotations/*.txt')
for annotFilename in annotFilenames:
name = extractRootName(annotFilename)
print '>>>', name + '\n'
annotFilename = 'gsAnnotations/%s.txt' % name
annotation = open(annotFilename).readlines()
predictions = parseGenscan(annotation)
pepFilename = 'gsPeptides/%s.fa' % name
peptides = fasta.load_mfa(pepFilename)
peptides = [(h.split()[0], s) for h, s in peptides]
peptides = dict(peptides)
