def Index_Fasta( self ):
"""
Create/update .fasta.fai file using samtools faidx.
"""
LE.info('Creating index {0}.fai.'.format(self.outfastapath))
self.cleanUpExecution(
*COMPASSCFG['tools']['samtools'].execute(append="faidx {0}".format(self.outfastapath)))
def merge(self):
LE.info("Merging SAMfiles from different readgroup mappings")
input = pysam.Samfile(self.input)
self.seqstat = self.generateSeqStats(self.input)
newheaders = dict(input.header.items())
# samheader = pysam.Samfile(
# self.tmpdir + "/" + self.readgroups[0] + ".sam")
samheader = input
newheaders["SQ"] = samheader.header["SQ"]
samheader.close()
input.close()
newheaders["PG"] = [{
"PN": "bwa",
"VN": "0.7.10",
"CL": self.commandsHistory[0]
}]
if "CO" in newheaders.keys():
newheaders["CO"] = list(set(newheaders["CO"]))
else:
newheaders["CO"] = []
newheaders["CO"].append("CMD:{0}".format(" ".join(sys.argv)))
for i in self.commandsHistory:
newheaders["CO"].append("CMD:{0}".format(i))
LE.debug("Doing merge, writing in " + self.output)
unsortedBamName = self.output + "_unsorted.bam"
# print unsortedBamName
output = pysam.Samfile(unsortedBamName, "wb", header=newheaders)
# print "========"
# print self.readgroups
# print "========"
for i in self.readgroups:
with pysam.Samfile(i + "_alignment.sam") as source:
for j in source:
if not j.flag & 2048:
output.write(j)
# os.unlink(self.tmpdir + "/" + i + ".sam")
output.close()
outputNames = self.output.split(".")
outputPrefix = ".".join(outputNames[0:len(outputNames) - 1])
pysam.sort(unsortedBamName, self.output)
os.unlink(unsortedBamName)
shutil.move(self.output + ".bam", self.output)
def Fix_Fasta_Headers( self ):
"""
Create correctly formatted fasta file. Contigs must be in the form REFID[, REFID-2, REFID-3,...].
"""
LE.info('Creating master fasta file {0}.'.format(self.outfastapath))
# helper function to reformat each fasta record on the fly
def _fixed_records():
"""
"""
for i, contig in enumerate(SeqIO.parse(self.infasta, 'fasta'), 1):
correct_name = contig.id = self.newrefid + \
('-{0}'.format(i), '')[i == 1]
if contig.name != correct_name:
contig.name = correct_name
contig.description = '{0} {1} {2}'.format(
correct_name, self.newrefid, contig.description)
yield contig
SeqIO.write(_fixed_records(), self.outfastapath, 'fasta')
return
parser.add_argument(
'-dh',
dest="headerinfo",
help=
"Default ummaped header, you must specify [readgroup,platform,lib,sample,SeqCentre] ex: -dh RG0045,ILLUMINA,LIB03,SN123,Sanger",
default=None)
parser.add_argument(
'-o',
dest="output.bam",
help="You must specifiy a file with the SAM header in text format",
default="-")
args = parser.parse_args()
# print " ".join(sys.argv)
LE.info("Input fastq files in {0} , {1}".format(args.fq1, args.fq2))
LE.info("Output bam in {0}".format(args.output))
if args.headerinfo == "None":
args.headerinfo = None
if (not args.header and not args.headerinfo) or (args.header
and args.headerinfo):
print(
"You must specify either a header file for the SAM header or default header information (-H/-dh)"
)
sys.exit(-1)
'''if args.output.bam=="-":
output.bam=sys.stdout
else:
output.bam=open(args.output.bam,"w")'''
calcLDforadjacentsites=options.bcftools_calcLDforadjacentsites,
scaledsubstmutrate=options.bcftools_scaledsubstmutrate,
indeltosubstratio=options.bcftools_indeltosubstratio,
variantifprobltint=options.bcftools_variantifprobltint,
typeofprior=options.bcftools_typeofprior,
inbam=options.inbam,
inref=options.ref_id,
pileup_out=options.outpileup)
try:
c.runPileup()
if c.annotate():
print "Error with annotation!"
c.dumpStdError()
sys.exit(-1)
c.merge(options.output)
c.clean()
LE.info("Finished!")
except:
c.dumpStdError()
c.clean()
dump_exc()
try:
pass
c.dumpStdError()
c.clean()
except:
pass
dump_exc()
def generateAll( self ):
self.Fix_Fasta_Headers()
self.Create_Indexes()
self.Make_Repeat_Mask_Txt()
LE.info("Everything went OKAY!")