def runGeneFasta(argNamespace):
paftolTargetSet = paftol.PaftolTargetSet()
paftolTargetSet.readFasta(argNamespace.infile)
fastaFnameList = []
for geneName in paftolTargetSet.paftolGeneDict:
srList = paftolTargetSet.getSeqRecordSelection(organismNameList=None,
geneNameList=[geneName])
fastaFname = argNamespace.outFastaFormat % geneName
Bio.SeqIO.write(srList, fastaFname, 'fasta')
fastaFnameList.append(fastaFname)
sys.stdout.write('%s\n' % ' '.join(fastaFnameList))
def runRetrieveTargets(argNamespace):
paftolTargetSet = paftol.PaftolTargetSet()
if argNamespace.targetsfile is None:
paftolTargetSet.readFasta(sys.stdin)
else:
paftolTargetSet.readFasta(argNamespace.targetsfile)
blastnRunner = argToBlastnRunner(argNamespace)
paftolTargetSeqRetriever = paftol.PaftolTargetSeqRetriever()
targetList = paftolTargetSeqRetriever.retrievePaftolTargetList(
argNamespace.genomeName, argNamespace.fastaFname, paftolTargetSet,
blastnRunner)
if argNamespace.outfile is None:
Bio.SeqIO.write(targetList, sys.stdout, 'fasta')
else:
with open(argNamespace.outfile, 'w') as f:
Bio.SeqIO.write(targetList, f, 'fasta')
def runGeneSetStats(argNamespace):
paftolTargetSet = paftol.PaftolTargetSet()
sampleId = 'unknown'
if argNamespace.sampleId is not None:
sampleId = argNamespace.sampleId
if argNamespace.targetsfile is None:
raise StandardError, 'no targets file specified'
else:
paftolTargetSet.readFasta(argNamespace.targetsfile)
if argNamespace.seqfile is None:
geneSetStatsDataFrame = paftol.makeGeneSetStatsDataFrame(
sys.stdin, sampleId, paftolTargetSet)
else:
with open(argNamespace.seqfile, 'r') as f:
geneSetStatsDataFrame = paftol.makeGeneSetStatsDataFrame(
f, sampleId, paftolTargetSet)
if argNamespace.outfile is None:
geneSetStatsDataFrame.writeCsv(sys.stdout)
else:
with open(argNamespace.outfile, 'w') as f:
geneSetStatsDataFrame.writeCsv(f)
def runTargetGeneScan(argNamespace):
paftolTargetSet = paftol.PaftolTargetSet()
if argNamespace.targetsfile is None:
paftolTargetSet.readFasta(sys.stdin)
else:
paftolTargetSet.readFasta(argNamespace.targetsfile)
sys.stderr.write('read target set with %d genes and %d organisms\n' % (len(
paftolTargetSet.paftolGeneDict), len(paftolTargetSet.organismDict)))
# FIXME: hack to use scanMethod as the genome name as well
referenceGenome = paftol.ReferenceGenome(argNamespace.scanMethod,
argNamespace.refFasta,
argNamespace.refGenbank)
referenceGenome.scanGenes(argNamespace.scanMethod)
sys.stderr.write('read reference genome and scanned %d genes\n' %
len(referenceGenome.geneList))
targetGeneTable, cdsList = referenceGenome.blastTargetSet(paftolTargetSet)
if argNamespace.outfile is None:
targetGeneTable.writeCsv(sys.stdout)
else:
with open(argNamespace.outfile, 'w') as csvFile:
targetGeneTable.writeCsv(csvFile)
if argNamespace.cdsFasta is not None:
Bio.SeqIO.write(cdsList, argNamespace.cdsFasta, 'fasta')
def runSelectgenes(argNamespace):
organismNameSet = None
if argNamespace.organism is not None:
organismNameSet = set(argNamespace.organism)
geneNameSet = []
if argNamespace.gene is not None:
geneNameSet = set(argNamespace.gene)
if argNamespace.genefile is not None:
with open(argNamespace.genefile) as f:
for line in f:
geneNameSet.append(line.strip())
if len(geneNameSet) == 0:
geneNameSet = None
paftolTargetSet = paftol.PaftolTargetSet()
if argNamespace.targetsfile is None:
paftolTargetSet.readFasta(sys.stdin)
else:
paftolTargetSet.readFasta(argNamespace.targetsfile)
srList = paftolTargetSet.getSeqRecordSelection(organismNameSet,
geneNameSet)
if argNamespace.outfile is None:
Bio.SeqIO.write(srList, sys.stdout, 'fasta')
else:
Bio.SeqIO.write(srList, argNamespace.outfile, 'fasta')