def main():
usage = "%(prog)s [options]"
parser = argparse.ArgumentParser( usage=usage,description=desc,epilog=epilog )
parser.add_argument("-v", dest="verbose", default=False, action="store_true")
parser.add_argument("-i", dest="coords", default=sys.stdin, type=file,
help="coords file name [stdin]")
parser.add_argument("-f", dest="fasta", required=True, type=file,
help="query fasta file" )
parser.add_argument("-o", dest="out", default=sys.stdout, type=argparse.FileType("w"),
help="output base name [stdout]")
o = parser.parse_args()
if o.verbose:
sys.stderr.write( "Options: %s\n" % str(o) )
#load query genome
query2fasta = genome2dict( o.fasta.name )
# load nucmer
matches = nucmer2list( o.coords.name )#; print matches
# sort hits by ref position
sort_hits( matches,query2fasta,o.out,o.verbose )
def main():
usage = "%(prog)s [options]"
parser = argparse.ArgumentParser( usage=usage,description=desc,epilog=epilog )
parser.add_argument("-v", dest="verbose", default=False, action="store_true")
parser.add_argument("-i", dest="coords", default=sys.stdin, type=file,
help="coords file name [stdin]")
parser.add_argument("-f", dest="fasta", required=True, type=file,
help="query fasta file" )
parser.add_argument("-o", dest="out", default=sys.stdout, type=argparse.FileType("w"),
help="output base name [stdout]")
o = parser.parse_args()
if o.verbose:
sys.stderr.write( "Options: %s\n" % str(o) )
#load query genome
query2fasta = genome2dict( o.fasta.name )
# load nucmer
matches = nucmer2list( o.coords.name )#; print matches
# sort hits by ref position
sort_hits( matches,query2fasta,o.out,o.verbose )
def gff2fasta(gff, fasta, entireGene, codonTable, verbose):
"""Report gene, cds, peptide.
not reporting 1000bp flanking intergenic sequence.
"""
#load genome
chr2seq = genome2dict(fasta)
#load gff
gene2position, contig2gene = load_gtf(gff)
#get out streams
genout = open(gff.name+".gene.fa", "w")
cdsout = open(gff.name+".cds.fa", "w")
pepout = open(gff.name+".pep.fa", "w")
#process entries
i = 0
genes = set()
for ci, contig in enumerate(sorted(contig2gene), 1):
sys.stderr.write(" %s %s \r" % (ci, contig))
for s, e, feature, gene in contig2gene[contig]:
i += 1
contig, boundaries, strand, function, frames = gene2position[gene]
#store CDS and peptide
cds, pep = get_cds_pep(chr2seq[contig], gene, boundaries, strand, function, frames, codonTable)
cdsout.write(cds.format('fasta'))
pepout.write(pep.format('fasta'))
#get geneid and store gene
geneid = ".".join(gene.split(".")[:-1])#; print geneid
if geneid not in genes:
genes.add(geneid)
seq = chr2seq[contig][s-1:e]
if strand == "-":
seq = seq.reverse_complement()
gen = SeqRecord(seq, id=geneid, name="", description=function)
genout.write(gen.format('fasta'))
def gff2fasta(gff, fasta, entireGene, codonTable, verbose):
"""Report gene, cds, peptide.
not reporting 1000bp flanking intergenic sequence.
"""
#load genome
chr2seq = genome2dict(fasta)
#load gff
gene2position, contig2gene = load_gtf(gff)
#get out streams
genout = open(gff.name+".gene.fa", "w")
cdsout = open(gff.name+".cds.fa", "w")
pepout = open(gff.name+".pep.fa", "w")
#process entries
i = 0
genes = set()
for ci, contig in enumerate(sorted(contig2gene), 1):
sys.stderr.write(" %s %s \r" % (ci, contig))
for s, e, feature, gene in contig2gene[contig]:
i += 1
contig, boundaries, strand, function, frames = gene2position[gene]
#store CDS and peptide
cds, pep = get_cds_pep(chr2seq[contig], gene, boundaries, strand, function, frames, codonTable)
cdsout.write(cds.format('fasta'))
pepout.write(pep.format('fasta'))
#get geneid and store gene
geneid = ".".join(gene.split(".")[:-1])#; print geneid
if geneid not in genes:
genes.add(geneid)
seq = chr2seq[contig][s-1:e]
if strand == "-":
seq = seq.reverse_complement()
gen = SeqRecord(seq, id=geneid, name="", description=function)
genout.write(gen.format('fasta'))
def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) #allow_interspersed_args=True
parser.add_option("-i", dest="input", default="",
help="input file with tab-separated ids [mandatory]" )
parser.add_option("-f", dest="fasta", default="",
help="multifasta file [mandatory]" )
parser.add_option("-o", dest="out", default="out/out",
help="output fname [%default]" )
parser.add_option("-s", dest="split", default=False, action="store_true",
help="split fasta for ids from every line")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
for f in ( o.input,o.fasta ):
if not f:
parser.error( "Specify mandatory parameters!" )
if not f.isdigit and not os.path.isfile( f ):
parser.error( "No such file: %s" % f )
#check if outdir exists
outdir = os.path.dirname(o.out)
if not os.path.isdir( outdir ):
os.makedirs( outdir )
#get id2fasta
sys.stderr.write( "Loading multifasta...\n" )
id2fasta = genome2dict( o.fasta )
sys.stderr.write( "Saving fastas...\n" )
#load ids
i = 1
#open common output
if not o.split:
outfn = "%s_%5i.fasta" % (o.out,i)
outfn = outfn.replace(" ","0")
out = open( outfn,"w" )
for l in open( o.input ):
#open output for each line if requested
if o.split:
outfn = "%s_%5i.fasta" % (o.out,i)
outfn = outfn.replace(" ","0")
out = open( outfn,"w" )
for id in l.split():
sys.stderr.write( " %s \r" % id )
if id in id2fasta:
seq = id2fasta[id]
elif id+"_1" in id2fasta:
seq = id2fasta[id+"_1"]
else:
sys.stderr.write( " No fasta for: %s\n" % id )
continue
out.write( ">%s\n%s\n" % (id,seq) )
i += 1
def main():
usage = "%(prog)s [options]"
parser = argparse.ArgumentParser(usage=usage, description=desc, epilog=epilog, \
formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument("-v", "--verbose", default=False, action="store_true", help="verbose")
parser.add_argument('--version', action='version', version='1.1')
parser.add_argument("-g", "--gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_argument("-f", "--fasta",
help="genome fasta [can be gzipped]" )
parser.add_argument("-i", "--input", type=file, #default=sys.stdin,
help="input stream [stdin]")
parser.add_argument("-o", "--out", default=sys.stdout,
help="output stream [stdout]")
parser.add_argument("-p", "--pfam", default="",
help="pfam tblout file")
parser.add_argument("-q", "--faa", default="",
help="proteome fasta (to get protein annotation)")
parser.add_argument("-t", "--tab", default="",
help="tab-delimited annotation")
o = parser.parse_args()
if o.verbose:
sys.stderr.write("Options: %s\n"%str(o))
ctg2cds, id2gene, ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer("Fasta file (-f) is requeired!")
elif not os.path.isfile( o.fasta ):
parser.error("No such file: %s"%o.fasta)
ctg2seq = genome2dict(o.fasta)
# load genome annotation
if not os.path.isfile(o.gtf): # check if correct file
parser.error("No such file: %s"%o.gtf)
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff(o.gtf)
else:
id2gene,ctg2cds = load_gtf(o.gtf)
if o.verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n"%(len(id2gene), o.gtf))
#load function annotation
trans2ann = trans2pfam = trans2tab = {}
if o.faa:
trans2ann = load_fasta_headers(o.faa)
if o.pfam:
trans2pfam = load_pfam(o.pfam)
if o.tab:
trans2tab = load_tab(o.tab)
# parse pileup
parse_snps(o.input, o.out, ctg2cds, id2gene, ctg2seq, trans2ann, trans2pfam, \
trans2tab, o.verbose)
def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) #allow_interspersed_args=True
parser.add_option("-i", dest="input", default="",
help="input file with tab-separated ids [mandatory]" )
parser.add_option("-f", dest="fasta", default="",
help="multifasta file [mandatory]" )
parser.add_option("-o", dest="out", default="out/out",
help="output fname [%default]" )
parser.add_option("-s", dest="split", default=False, action="store_true",
help="split fasta for ids from every line")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
for f in ( o.input,o.fasta ):
if not f:
parser.error( "Specify mandatory parameters!" )
if not f.isdigit and not os.path.isfile( f ):
parser.error( "No such file: %s" % f )
#check if outdir exists
outdir = os.path.dirname(o.out)
if not os.path.isdir( outdir ):
os.makedirs( outdir )
#get id2fasta
sys.stderr.write( "Loading multifasta...\n" )
id2fasta = genome2dict( o.fasta )
sys.stderr.write( "Saving fastas...\n" )
#load ids
i = 1
#open common output
if not o.split:
outfn = "%s_%5i.fasta" % (o.out,i)
outfn = outfn.replace(" ","0")
out = open( outfn,"w" )
for l in open( o.input ):
#open output for each line if requested
if o.split:
outfn = "%s_%5i.fasta" % (o.out,i)
outfn = outfn.replace(" ","0")
out = open( outfn,"w" )
for id in l.split():
sys.stderr.write( " %s \r" % id )
if id in id2fasta:
seq = id2fasta[id]
elif id+"_1" in id2fasta:
seq = id2fasta[id+"_1"]
else:
sys.stderr.write( " No fasta for: %s\n" % id )
continue
out.write( ">%s\n%s\n" % (id,seq) )
i += 1
def main():
usage = "usage: %prog [options]"
desc = """Parse multi-fasta file and report sequences without overlap
with already reported sequences. Starts from the longest."""
epilog = ""
parser = OptionParser( usage=usage,version="%prog 1.0",description=desc,epilog=epilog )
parser.add_option("-i", dest="infile",
help="multi-fasta file [mandatory]")
parser.add_option("-m", dest="minIdentity", default=90, type=int,
help="min identity [%default]")
parser.add_option("-o", dest="overlap", default=0.3, type=float,
help="max overlap allowed [%default]")
parser.add_option("-v", dest="verbose", default=False, action="store_true" )
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "Options: %s\nArgs: %s\n" % ( o,args ) )
for fn in [ o.infile, ]:
if not fn:
parser.error( "Provide input file!" )
if not os.path.isfile( fn ):
parser.error( "No such file: %s" % fn )
#load fastas
fastas = genome2dict( o.infile )
#contigs by descending length
contigs = sorted( fastas.keys(),key=lambda x: len(fastas[x]), reverse=True )
#report non-overlapping
i = 0
added,skipped = set(), set()
##remove outfile if exists
outfn = o.infile + ".collapsed_o%s_i%s.fa" % ( o.overlap,o.minIdentity )
if os.path.isfile( outfn ):
os.unlink( outfn )
##execute blat vs itself
pslfn = run_blat( o.infile,o.infile,o.minIdentity,o.verbose )
matches = parse_blat( pslfn,o.verbose,header=0,skipSelfMatches=1 )
##add contigs without overlap
for c in contigs:
i += 1
if o.verbose:
sys.stderr.write( " %3s %20s [ %7.2f kb]\n" % (i,c,len(fastas[c])/1000.0) )
#get fasta entry
fasta = ">%s\n%s\n" % (c,_get_formatted_seq(fastas[c]))
#save contig if first or if no overlapping already processed
if not added or not overlapping( c,added,matches,o.overlap,o.verbose ):
added.add( c )
out = open(outfn,"a"); out.write( fasta ); out.close()
else:
skipped.add( c )
sys.stderr.write( "Selected %s [ %7.2f kb] out of %s [ %7.2f kb] contigs.\n" % ( len(added),sum([len(fastas[c]) for c in added])/10.0**3,len(fastas),sum([len(fastas[c]) for c in fastas])/10.0**3) )
def main():
usage = "usage: %prog [options]"
desc = """Order contigs based on nucmer output."""
epilog = """Make sure, coords file is sorted by reference (show-coords -r).
Monoploid number (-x) has to be specified correctly. For details look at: http://en.wikipedia.org/wiki/Ploidy"""
parser = OptionParser( usage=usage,version="%prog 1.0",description=desc,epilog=epilog )
parser.add_option("-o", dest="outfn", default="out",
help="output base name [%default]")
parser.add_option("-i", dest="coords", default="",
help="coords file name [mandatory]")
parser.add_option("-q", dest="query", default="",
help="query file name [mandatory]")
parser.add_option("-r", dest="ref", default="",
help="reference file name [mandatory]")
parser.add_option("-c", dest="qOverlap", default=0.05, type=float,
help="fract of query aligned [%default]")
parser.add_option("-n", dest="haploid", default=2, type=int,
help="haploid number [%default]")
parser.add_option("-x", dest="monoploid", default=2, type=int,
help="monoploid number [%default]")
parser.add_option("-v", dest="verbose", default=False, action="store_true" )
( o, fnames ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "Options: %s\nFastQ files: %s\n" % ( o,fnames ) )
# check input files
for fn in [ o.coords,o.query,o.ref ]:
if not fn:
parser.error( "Provide input file!" )
if not os.path.isfile( fn ):
parser.error( "No such file: %s" % fn )
#load query genome
query2fasta = genome2dict( o.query )
ref2fasta = genome2dict( o.ref )
# load nucmer
matches = nucmer2list( o.coords )
# sort hits by ref position
sort_hits( matches,query2fasta,ref2fasta,o.outfn,o.qOverlap,o.haploid,o.monoploid,o.verbose )
def main():
usage = "usage: %prog [options]\nfor f in *.bam; do echo `date` $f; bam2counts.py -rv -i $f -g F.oxysporum.gtf > $f.genecounts.txt; done"
parser = OptionParser(usage=usage,
version="%prog 1.0") #allow_interspersed_args=True
parser.add_option("-i", dest="bam", default="", help="bam file")
parser.add_option("-g",
dest="gtf",
default="",
help="genome annotation gtf/gff")
parser.add_option(
"-r",
dest="rpkm",
default=False,
action="store_true",
help=
"RPKM normalisation (reads per kb of gene per million of aligned reads)"
)
parser.add_option("-f",
dest="fasta",
default="",
help="genome fasta [required if -r]")
parser.add_option("-v", dest="verbose", default=False, action="store_true")
(o, fnames) = parser.parse_args()
if o.verbose:
sys.stderr.write("Options: %s\nArgs: %s\n" % (o, fnames))
for fn in (o.bam, o.gtf):
if not fn:
parser.error("Provide input file!")
if not os.path.isfile(fn):
parser.error("No such file: %s" % fn)
ctg2cds, id2gene, ctg2seq = {}, {}, {}
# load gtf/gff
if o.gtf:
if o.gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(o.gtf)
else:
id2gene, ctg2cds = load_gtf(o.gtf)
if o.verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" %
(len(id2gene), o.gtf))
if o.rpkm:
if not o.fasta:
parser.error("Specify genome fasta file!")
if not os.path.isfile(o.fasta):
parser.error("No such file: %s" % o.fasta)
ctg2seq = genome2dict(o.fasta)
bam2counts(o.bam, o.rpkm, id2gene, ctg2cds, ctg2seq, o.verbose)
def main():
usage = "%(prog)s [options]"
parser = argparse.ArgumentParser(
usage=usage, description=desc, epilog=epilog, formatter_class=argparse.RawTextHelpFormatter
)
parser.add_argument("-v", "--verbose", default=False, action="store_true", help="verbose")
parser.add_argument("--version", action="version", version="1.1")
parser.add_argument("-g", "--gtf", help="genome annotation gtf/gff [requires -f]")
parser.add_argument("-f", "--fasta", help="genome fasta [can be gzipped]")
parser.add_argument("-i", "--input", type=file, help="input stream [stdin]") # default=sys.stdin,
parser.add_argument("-o", "--out", default=sys.stdout, help="output stream [stdout]")
parser.add_argument("-p", "--pfam", default="", help="pfam tblout file")
parser.add_argument("-q", "--faa", default="", help="proteome fasta (to get protein annotation)")
parser.add_argument("-t", "--tab", default="", help="tab-delimited annotation")
o = parser.parse_args()
if o.verbose:
sys.stderr.write("Options: %s\n" % str(o))
ctg2cds, id2gene, ctg2seq = {}, {}, {}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer("Fasta file (-f) is requeired!")
elif not os.path.isfile(o.fasta):
parser.error("No such file: %s" % o.fasta)
ctg2seq = genome2dict(o.fasta)
# load genome annotation
if not os.path.isfile(o.gtf): # check if correct file
parser.error("No such file: %s" % o.gtf)
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(o.gtf)
else:
id2gene, ctg2cds = load_gtf(o.gtf)
if o.verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" % (len(id2gene), o.gtf))
# load function annotation
trans2ann = trans2pfam = trans2tab = {}
if o.faa:
trans2ann = load_fasta_headers(o.faa)
if o.pfam:
trans2pfam = load_pfam(o.pfam)
if o.tab:
trans2tab = load_tab(o.tab)
# parse pileup
parse_snps(o.input, o.out, ctg2cds, id2gene, ctg2seq, trans2ann, trans2pfam, trans2tab, o.verbose)
def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta [can be gzipped]" )
parser.add_option("-i", dest="fpath",
help="input file [stdin]")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=10, type=int,
help="minimal depth [%default]")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# parse pileup
parse_vcf( o.fpath,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta [can be gzipped]" )
parser.add_option("-i", dest="fpath",
help="input file [stdin]")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=10, type=int,
help="minimal depth [%default]")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# parse pileup
parse_vcf( o.fpath,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def main():
usage = "usage: %prog [options]\nfor f in *.bam; do echo `date` $f; bam2counts.py -rv -i $f -g F.oxysporum.gtf > $f.genecounts.txt; done"
parser = OptionParser( usage=usage,version="%prog 1.0" ) #allow_interspersed_args=True
parser.add_option("-i", dest="bam", default="",
help="bam file")
parser.add_option("-g", dest="gtf",default="",
help="genome annotation gtf/gff" )
parser.add_option("-r", dest="rpkm", default=False, action="store_true",
help="RPKM normalisation (reads per kb of gene per million of aligned reads)" )
parser.add_option("-f", dest="fasta", default="",
help="genome fasta [required if -r]")
parser.add_option("-v", dest="verbose", default=False, action="store_true" )
( o, fnames ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "Options: %s\nArgs: %s\n" % ( o,fnames ) )
for fn in ( o.bam,o.gtf ):
if not fn:
parser.error( "Provide input file!" )
if not os.path.isfile( fn ):
parser.error( "No such file: %s" % fn )
ctg2cds,id2gene,ctg2seq = {},{},{}
# load gtf/gff
if o.gtf:
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
if o.rpkm:
if not o.fasta:
parser.error( "Specify genome fasta file!" )
if not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
bam2counts( o.bam,o.rpkm,id2gene,ctg2cds,ctg2seq,o.verbose )
def main():
usage = "usage: %prog [options]"
desc = """Order contigs based on nucmer output."""
epilog = """Make sure, coords file is sorted by reference (show-coords -r).
Monoploid number (-x) has to be specified correctly. For details look at: http://en.wikipedia.org/wiki/Ploidy"""
parser = OptionParser(usage=usage,
version="%prog 1.0",
description=desc,
epilog=epilog)
parser.add_option("-o",
dest="outfn",
default="out",
help="output base name [%default]")
parser.add_option("-i",
dest="coords",
default="",
help="coords file name [mandatory]")
parser.add_option("-q",
dest="query",
default="",
help="query file name [mandatory]")
parser.add_option("-r",
dest="ref",
default="",
help="reference file name [mandatory]")
parser.add_option("-c",
dest="qOverlap",
default=0.05,
type=float,
help="fract of query aligned [%default]")
parser.add_option("-n",
dest="haploid",
default=2,
type=int,
help="haploid number [%default]")
parser.add_option("-x",
dest="monoploid",
default=2,
type=int,
help="monoploid number [%default]")
parser.add_option("-v", dest="verbose", default=False, action="store_true")
(o, fnames) = parser.parse_args()
if o.verbose:
sys.stderr.write("Options: %s\nFastQ files: %s\n" % (o, fnames))
# check input files
for fn in [o.coords, o.query, o.ref]:
if not fn:
parser.error("Provide input file!")
if not os.path.isfile(fn):
parser.error("No such file: %s" % fn)
#load query genome
query2fasta = genome2dict(o.query)
ref2fasta = genome2dict(o.ref)
# load nucmer
matches = nucmer2list(o.coords)
# sort hits by ref position
sort_hits(matches, query2fasta, ref2fasta, o.outfn, o.qOverlap, o.haploid,
o.monoploid, o.verbose)
def main():
usage = "usage: %prog [options] *.vcf"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta" )
parser.add_option("-1", dest="bam1",
help="sample bam")
parser.add_option("-2", dest="bam2",
help="reference bam")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=5, type=int,
help="""minimal depth; note both samples need to have pass depth filtering [%default]""")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels [%default]")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
if not args:
parser.error( "At least one vcf file has to be specified!" )
for fn in args:
if not os.path.isfile( fn ):
parser.error( "No such file: %s" % fn )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# load possible SNPs coordinates
coords = load_vcf( args,o.indels )
# check with mpileup
check_snps( coords,o.bam1,o.bam2,o.fasta,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def main():
usage = "usage: %prog [options]"
desc = """Parse multi-fasta file and report sequences without overlap
with already reported sequences. Starts from the longest."""
epilog = ""
parser = OptionParser(usage=usage,
version="%prog 1.0",
description=desc,
epilog=epilog)
parser.add_option("-i",
dest="infile",
help="multi-fasta file [mandatory]")
parser.add_option("-m",
dest="minIdentity",
default=90,
type=int,
help="min identity [%default]")
parser.add_option("-o",
dest="overlap",
default=0.3,
type=float,
help="max overlap allowed [%default]")
parser.add_option("-v", dest="verbose", default=False, action="store_true")
(o, args) = parser.parse_args()
if o.verbose:
sys.stderr.write("Options: %s\nArgs: %s\n" % (o, args))
for fn in [
o.infile,
]:
if not fn:
parser.error("Provide input file!")
if not os.path.isfile(fn):
parser.error("No such file: %s" % fn)
#load fastas
fastas = genome2dict(o.infile)
#contigs by descending length
contigs = sorted(fastas.keys(), key=lambda x: len(fastas[x]), reverse=True)
#report non-overlapping
i = 0
added, skipped = set(), set()
##remove outfile if exists
outfn = o.infile + ".collapsed_o%s_i%s.fa" % (o.overlap, o.minIdentity)
if os.path.isfile(outfn):
os.unlink(outfn)
##execute blat vs itself
pslfn = run_blat(o.infile, o.infile, o.minIdentity, o.verbose)
matches = parse_blat(pslfn, o.verbose, header=0, skipSelfMatches=1)
##add contigs without overlap
for c in contigs:
i += 1
if o.verbose:
sys.stderr.write(" %3s %20s [ %7.2f kb]\n" %
(i, c, len(fastas[c]) / 1000.0))
#get fasta entry
fasta = ">%s\n%s\n" % (c, _get_formatted_seq(fastas[c]))
#save contig if first or if no overlapping already processed
if not added or not overlapping(c, added, matches, o.overlap,
o.verbose):
added.add(c)
out = open(outfn, "a")
out.write(fasta)
out.close()
else:
skipped.add(c)
sys.stderr.write(
"Selected %s [ %7.2f kb] out of %s [ %7.2f kb] contigs.\n" %
(len(added), sum([len(fastas[c]) for c in added]) / 10.0**3,
len(fastas), sum([len(fastas[c]) for c in fastas]) / 10.0**3))
def main():
usage = "usage: %prog [options] *.vcf"
parser = OptionParser(usage=usage,
version="%prog 1.0") # allow_interspersed_args=True
parser.add_option("-g",
dest="gtf",
help="genome annotation gtf/gff [requires -f]")
parser.add_option("-f", dest="fasta", help="genome fasta")
parser.add_option("-1", dest="bam1", help="sample bam")
parser.add_option("-2", dest="bam2", help="reference bam")
parser.add_option("-o", dest="outfn", help="output fname [stdout]")
parser.add_option(
"-d",
dest="minDepth",
default=5,
type=int,
help=
"""minimal depth; note both samples need to have pass depth filtering [%default]"""
)
parser.add_option("-m",
dest="minFreq",
default=0.8,
type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n",
dest="indels",
default=True,
action="store_false",
help="ignore indels [%default]")
parser.add_option("-b",
dest="bothStrands",
default=True,
action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
(o, args) = parser.parse_args()
if o.verbose:
sys.stderr.write("%s\n" % (str(o), ))
if not args:
parser.error("At least one vcf file has to be specified!")
for fn in args:
if not os.path.isfile(fn):
parser.error("No such file: %s" % fn)
ctg2cds, id2gene, ctg2seq = {}, {}, {}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer("Fasta file (-f) is requeired!")
elif not os.path.isfile(o.fasta):
parser.error("No such file: %s" % o.fasta)
ctg2seq = genome2dict(o.fasta)
# load genome annotation
if not os.path.isfile(o.gtf): # check if correct file
parser.error("No such file: %s" % o.gtf)
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(o.gtf)
else:
id2gene, ctg2cds = load_gtf(o.gtf)
if o.verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" %
(len(id2gene), o.gtf))
# load possible SNPs coordinates
coords = load_vcf(args, o.indels)
# check with mpileup
check_snps(coords, o.bam1, o.bam2, o.fasta, o.outfn, ctg2cds, id2gene,
ctg2seq, o.minDepth, o.minFreq, o.indels, o.bothStrands)
