def __readBins(self, binFiles):
bins = {}
for binFile in binFiles:
binId = binIdFromFilename(binFile)
bins[binId] = set(readFastaSeqIds(binFile))
return bins
def __readBins(self, binFiles):
bins = {}
for binFile in binFiles:
binId = binIdFromFilename(binFile)
bins[binId] = set(readFastaSeqIds(binFile))
return bins
def unique(self, binFiles):
"""Check if sequences are assigned to multiple bins."""
# read seq ids from all bins
binSeqs = {}
for f in binFiles:
binId = binIdFromFilename(f)
binSeqs[binId] = readFastaSeqIds(f)
# check for sequences assigned to multiple bins
bDuplicates = False
binIds = binSeqs.keys()
for i in xrange(0, len(binIds)):
for j in xrange(i+1, len(binIds)):
seqInter = set(binSeqs[binIds[i]]).intersection(set(binSeqs[binIds[j]]))
if len(seqInter) > 0:
bDuplicates = True
print ' Sequences shared between %s and %s: ' % (binIds[i], binIds[j])
for seqId in seqInter:
print ' ' + seqId
print ''
if not bDuplicates:
print ' No sequences assigned to multiple bins.'
def run(self, contigFile, binFiles, outputDir, evalueThreshold, concatenateThreshold):
# make sure output directory exists
if not os.path.exists(outputDir):
os.makedirs(outputDir)
# get bin id of binned contigs
self.logger.info(' Determining bin assignment of sequences.')
seqIdToBinId = {}
for f in binFiles:
binId = binIdFromFilename(f)
seqIds = readFastaSeqIds(f)
for seqId in seqIds:
seqIdToBinId[seqId] = binId
# identify 16S reads from contigs/scaffolds
self.logger.info(' Identifying SSU rRNAs on sequences.')
self.__hmmSearch(contigFile, evalueThreshold, os.path.join(outputDir, 'ssu'))
# read HMM hits
hitsPerDomain = {}
for domain in ['archaea', 'bacteria', 'euk']:
hits = {}
seqInfo = self.__readHits(os.path.join(outputDir, 'ssu' + '.' + domain + '.txt'), domain, evalueThreshold)
if len(seqInfo) > 0:
for seqId, seqHits in seqInfo.iteritems():
for hit in seqHits:
self.__addHit(hits, seqId, hit, concatenateThreshold)
hitsPerDomain[domain] = hits
# find best domain hit for each sequence
bestHits = {}
for _, hits in hitsPerDomain.iteritems():
for seqId, info in hits.iteritems():
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
self.__addDomainHit(bestHits, seqId, info)
# write summary file and putative SSU rRNAs to file
summaryFile = os.path.join(outputDir, 'ssu_summary.tsv')
summaryOut = open(summaryFile, 'w')
summaryOut.write('Bin Id\tSeq. Id\tHMM\ti-Evalue\tStart hit\tEnd hit\t16S/18S gene length\tRev. Complement\tSequence length\n')
seqFile = os.path.join(outputDir, 'ssu.fna')
seqOut = open(seqFile, 'w')
seqs = readFasta(contigFile)
hitsToBins = {}
for seqId in bestHits:
origSeqId = seqId
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
if seqId in seqIdToBinId:
binId = seqIdToBinId[seqId]
else:
binId = DefaultValues.UNBINNED
seqInfo = [origSeqId] + bestHits[origSeqId]
hitsToBins[binId] = hitsToBins.get(binId, []) + [seqInfo]
for binId in sorted(hitsToBins.keys()):
for seqInfo in hitsToBins[binId]:
seqId = seqInfo[0]
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
seq = seqs[seqId]
summaryOut.write(binId + '\t' + '\t'.join(seqInfo) + '\t' + str(len(seq)) + '\n')
seqOut.write('>' + binId + DefaultValues.SEQ_CONCAT_CHAR + seqInfo[0] + '\n')
seqOut.write(seq[int(seqInfo[3]):int(seqInfo[4])] + '\n')
summaryOut.close()
seqOut.close()
self.logger.info('')
self.logger.info(' Identified ' + str(len(bestHits)) + ' putative SSU genes:')
self.logger.info(' Summary of identified hits written to: ' + summaryFile)
self.logger.info(' SSU sequences written to: ' + seqFile)
def run(self, contigFile, binFiles, outputDir, evalueThreshold,
concatenateThreshold):
# make sure output directory exists
if not os.path.exists(outputDir):
os.makedirs(outputDir)
# get bin id of binned contigs
self.logger.info('Determining bin assignment of sequences.')
seqIdToBinId = {}
for f in binFiles:
binId = binIdFromFilename(f)
seqIds = readFastaSeqIds(f)
for seqId in seqIds:
seqIdToBinId[seqId] = binId
# identify 16S reads from contigs/scaffolds
self.logger.info('Identifying SSU rRNAs on sequences.')
self.__hmmSearch(contigFile, evalueThreshold,
os.path.join(outputDir, 'ssu'))
# read HMM hits
hitsPerDomain = {}
for domain in ['archaea', 'bacteria', 'euk']:
hits = {}
seqInfo = self.__readHits(
os.path.join(outputDir, 'ssu' + '.' + domain + '.txt'), domain,
evalueThreshold)
if len(seqInfo) > 0:
for seqId, seqHits in seqInfo.items():
for hit in seqHits:
self.__addHit(hits, seqId, hit, concatenateThreshold)
hitsPerDomain[domain] = hits
# find best domain hit for each sequence
bestHits = {}
for _, hits in hitsPerDomain.items():
for seqId, info in hits.items():
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
self.__addDomainHit(bestHits, seqId, info)
# write summary file and putative SSU rRNAs to file
summaryFile = os.path.join(outputDir, 'ssu_summary.tsv')
summaryOut = open(summaryFile, 'w')
summaryOut.write(
'Bin Id\tSeq. Id\tHMM\ti-Evalue\tStart hit\tEnd hit\t16S/18S gene length\tRev. Complement\tSequence length\n'
)
seqFile = os.path.join(outputDir, 'ssu.fna')
seqOut = open(seqFile, 'w')
seqs = readFasta(contigFile)
hitsToBins = {}
for seqId in bestHits:
origSeqId = seqId
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
if seqId in seqIdToBinId:
binId = seqIdToBinId[seqId]
else:
binId = DefaultValues.UNBINNED
seqInfo = [origSeqId] + bestHits[origSeqId]
hitsToBins[binId] = hitsToBins.get(binId, []) + [seqInfo]
for binId in sorted(hitsToBins.keys()):
for seqInfo in hitsToBins[binId]:
seqId = seqInfo[0]
if '-#' in seqId:
seqId = seqId[0:seqId.rfind('-#')]
seq = seqs[seqId]
summaryOut.write(binId + '\t' + '\t'.join(seqInfo) + '\t' +
str(len(seq)) + '\n')
seqOut.write('>' + binId + DefaultValues.SEQ_CONCAT_CHAR +
seqInfo[0] + '\n')
seqOut.write(seq[int(seqInfo[3]) + 1:int(seqInfo[4]) + 1] +
'\n')
summaryOut.close()
seqOut.close()
self.logger.info('Identified ' + str(len(bestHits)) +
' putative SSU genes.')
self.logger.info('Summary of identified hits written to: ' +
summaryFile)
self.logger.info('SSU sequences written to: ' + seqFile)