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] vcf1 [ vcf2 ... vcfN ]"
parser = OptionParser(usage=usage,
version="%prog 1.0") #allow_interspersed_args=True
parser.add_option("-g", dest="gtf", help="genome annotation")
parser.add_option("-f", dest="fasta", help="genome fasta")
parser.add_option("-o",
dest="outbase",
default="plots",
help="output directory [%default]")
parser.add_option("-s",
dest="splitFn",
default=False,
action="store_true",
help="split fname (sheet name) by dot")
parser.add_option("-w",
dest="window",
default=10,
type=int,
help="window size in kb [%default]")
parser.add_option(
"-p",
dest="ext",
default="png",
help=
"Supported: emf, eps, pdf, png, ps, raw, rgba, svg, svgz [%default]")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
(o, args) = parser.parse_args()
if o.verbose:
sys.stderr.write("%s\nFiles to process: %s\n" %
(str(o), ", ".join(args)))
#check if any input file
if not args:
parser.error("At least one input file has to be specified!")
#check if files exists
for fn in args:
if not os.path.isfile(fn):
parser.error("No such file: %s")
#load genome - in fact need only contig sizes
contig2size = get_contig2size(o.fasta)
#load gtf
if o.gtf.endswith(".gff"):
gene2position, contig2gene = load_gff(o.gtf)
else:
gene2position, contig2gene = load_gtf(o.gtf)
#process vcf
for fn in args:
print fn
snps2plot(fn, o.window, contig2gene, contig2size, o.outbase, o.splitFn,
o.ext, 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] vcf1 [ vcf2 ... vcfN ]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) #allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation" )
parser.add_option("-f", dest="fasta",
help="genome fasta" )
parser.add_option("-o", dest="outbase", default="plots",
help="output directory [%default]" )
parser.add_option("-s", dest="splitFn", default=False, action="store_true",
help="split fname (sheet name) by dot")
parser.add_option("-w", dest="window", default=10, type=int,
help="window size in kb [%default]")
parser.add_option("-p", dest="ext", default="png",
help="Supported: emf, eps, pdf, png, ps, raw, rgba, svg, svgz [%default]")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\nFiles to process: %s\n" % ( str(o),", ".join( args ) ) )
#check if any input file
if not args:
parser.error( "At least one input file has to be specified!" )
#check if files exists
for fn in args:
if not os.path.isfile( fn ):
parser.error( "No such file: %s" )
#load genome - in fact need only contig sizes
contig2size = get_contig2size( o.fasta )
#load gtf
if o.gtf.endswith(".gff"):
gene2position, contig2gene = load_gff( o.gtf )
else:
gene2position, contig2gene = load_gtf( o.gtf )
#process vcf
for fn in args:
print fn
snps2plot( fn,o.window,contig2gene,contig2size,o.outbase,o.splitFn,o.ext,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 process(fnames, faa, pfam, gtf, log2th, splitFn, skipExons, verbose):
"""main function
"""
#load function annotation
trans2ann = trans2pfam = {}
if faa:
trans2ann = load_fasta_headers(faa)
if pfam:
trans2pfam = load_pfam(pfam)
ctg2cds, id2gene = {}, {}
if gtf:
# load gtf/gff
if gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(gtf)
else:
id2gene, ctg2cds = load_gtf(gtf)
if verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" %
(len(id2gene), o.gtf))
#get samples names
samples = []
for fn in fnames:
if splitFn:
fn = fn.split(".")[0]
samples.append(fn)
#load gene counts
if verbose:
sys.stderr.write("Loading gene counts...\n")
gene2counts = {}
for fn in fnames:
if verbose:
sys.stderr.write(" %s \r" % fn)
gene2counts = load_counts(fn, gene2counts)
## print results
# header
if verbose:
sys.stderr.write("Calculating...\n")
header = "#gene\tcoordinate\t%s" % samples[0]
for s in samples[1:]:
header += "\t%s\tlog2(%s/%s)" % (s, s, samples[0])
header += "\tannotation\tpfam"
print header
# per gene scores
for gene in sorted(gene2counts.keys()):
#if genes only requested then skip
if skipExons:
#check if exon, and skip if so
if gene.split(".")[-1].isdigit():
continue
#
coord, counts = gene2counts[gene]
passed = False
line = "%s\t%s\t%.2f" % (gene, coord, counts[0])
for c in counts[1:]:
line += "\t%.2f" % c
#ref 0
if not counts[0]:
line += "\t+NA"
passed = True
elif not c:
line += "\t-NA"
passed = True
else:
log2 = log(c * 1.0 / counts[0], 2)
line += "\t%.2f" % log2
#filter lines that contain log2 > than log2th or log2 < -log2th
if log2th:
if not -log2th < log2 < log2th:
passed = True
else:
passed = True
#print only if passed filtering
if passed:
ann = pfam = ""
if gene in id2gene:
ann = id2gene[gene][-1] #contig,cdsList,strand,function
if gene in trans2ann:
ann = trans2ann[gene]
if gene in trans2pfam:
pfam = trans2pfam[gene]
line += "\t%s\t%s" % (ann, pfam)
print line
def process(fnames, expCov, genome, faa, pfam, gtf, log2th, splitFn, skipExons,
verbose):
"""main function
"""
#load function annotation
trans2ann = trans2pfam = {}
if faa:
trans2ann = load_fasta_headers(faa)
if pfam:
trans2pfam = load_pfam(pfam)
ctg2cds, id2gene = {}, {}
if gtf:
# load gtf/gff
if gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(gtf)
else:
id2gene, ctg2cds = load_gtf(gtf)
if verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" %
(len(id2gene), gtf))
#get samples names
samples = []
for fn in fnames:
if splitFn:
fn = fn.split(".")[0]
samples.append(fn)
#get expected coverage (RPKMs)
if not expCov:
c2cs = get_contig2size_samtools(genome)
gsize = sum([s for c, s in c2cs.itervalues()])
rcount = sum([c for c, s in c2cs.itervalues()])
expCov = rcount * 10.0**3 / gsize
if verbose:
sys.stderr.write("Set expected coverage [RPKM]: %.3f\n" % expCov)
#load gene counts and calculate means
if verbose:
sys.stderr.write("Loading gene counts...\n")
means = []
gene2counts = {}
for fn in fnames:
if verbose:
sys.stderr.write(" %s \r" % fn)
gene2counts = load_counts(fn, gene2counts)
## print results
# header
if verbose:
sys.stderr.write("Calculating...\n")
header = "#gene\tcoordinate"
for s in samples:
header += "\t%s\tlog2 vs mean" % (s, )
header += "\tannotation\tpfam"
print header
# per gene scores
for gene in sorted(gene2counts.keys()):
#if genes only requested then skip
if skipExons:
#check if exon, and skip if so
if gene.split(".")[-1].isdigit():
continue
#
coord, counts = gene2counts[gene]
passed = False
line = "%s\t%s" % (gene, coord)
for c in counts:
line += "\t%.2f" % c
if not c:
line += "\t-NA"
passed = True
else:
log2 = log(c * 1.0 / expCov, 2)
line += "\t%.2f" % log2
#filter lines that contain log2 > than log2th or log2 < -log2th
if log2th:
if not -log2th < log2 < log2th:
passed = True
else:
passed = True
#print only if passed filtering
if passed:
ann = pfam = ""
if gene in id2gene:
ann = id2gene[gene][-1] #contig,cdsList,strand,function
if gene in trans2ann:
ann = trans2ann[gene]
if gene in trans2pfam:
pfam = trans2pfam[gene]
line += "\t%s\t%s" % (ann, pfam)
print line
def main():
"""
"""
usage = "%prog [options] file1 [file2 ... fileN]"
parser = OptionParser(usage)
parser.add_option("-a",
dest="annotation",
default='',
type=str,
help="GTF annotation file [%default]")
parser.add_option("-f",
dest="fdr",
default=1e-04,
type=float,
help="false dicovery rate [%default]")
(o, fnames) = parser.parse_args()
sys.stderr.write("Options: %s\nFiles to be processed: %s\n" % (o, fnames))
if not fnames:
sys.exit("Speficy at least one input file")
prot2ann, prot2locus = {}, {}
if o.annotation.endswith(".gff"):
gene2position, contig2gene = load_gff(o.annotation)
elif o.annotation:
gene2position, contig2gene = load_gtf(o.annotation)
#process files
i = 0
samples = []
gene2fc = {}
gene2reads = {}
sys.stderr.write("Processing files...\n")
de2sample = {}
for fn in fnames:
i += 1
sys.stderr.write("%s\t%s\n" % (
datetime.now(),
fn,
))
s = fn.split('.')[0]
samples.append(s)
#load files
i = 0
for l in open(fn):
#skip header
i += 1
if i == 1:
continue
id, baseMean, baseMeanA, baseMeanB, foldChange, log2FoldChange, pval, padj = l.split(
'\t')
baseMeanA, baseMeanB = float(baseMeanA), float(baseMeanB)
if id not in gene2fc:
gene2fc[id] = []
gene2reads[id] = [] #baseMeanA
#add expression info
gene2fc[id].append(log2FoldChange)
gene2reads[id].append((baseMeanA, baseMeanB))
try:
padj = float(padj)
except:
continue
if padj < o.fdr:
if id in de2sample:
de2sample[id].append(s)
else:
de2sample[id] = [s]
#print out
header = "#gene\tlocus\t#de\tcontrol"
for s in samples:
header += "\t%s log2" % s
header += "\tannotation"
print header
for gene in sorted(de2sample.keys()):
#annotation
function = ''
if gene in gene2position:
contig, coords, strand, function = gene2position[gene]
locus = "%s:%s-%s %s" % (contig, coords[0][0], coords[-1][-1],
strand)
out = "%s\t%s\t%s" % (
gene, locus, len(de2sample[gene])
) #,gene2control[gene],'\t'.join(gene2fc[gene]),ann )
#
i = 0
for reads, fc in zip(gene2reads[gene], gene2fc[gene]):
a, b = reads
if not i:
out += "\t%s" % a
i += 1
out += "\t%s" % fc
out += "\t%s" % function
print out
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 process( fnames,expCov,genome,faa,pfam,gtf,log2th,splitFn,skipExons,verbose ):
"""main function
"""
#load function annotation
trans2ann = trans2pfam = {}
if faa:
trans2ann = load_fasta_headers( faa )
if pfam:
trans2pfam = load_pfam( pfam )
ctg2cds,id2gene = {},{}
if gtf:
# load gtf/gff
if gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( gtf )
else:
id2gene,ctg2cds = load_gtf( gtf )
if verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),gtf ) )
#get samples names
samples = []
for fn in fnames:
if splitFn:
fn = fn.split(".")[0]
samples.append( fn )
#get expected coverage (RPKMs)
if not expCov:
c2cs = get_contig2size_samtools( genome )
gsize = sum( [ s for c,s in c2cs.itervalues() ] )
rcount = sum( [ c for c,s in c2cs.itervalues() ] )
expCov = rcount * 10.0**3 / gsize
if verbose:
sys.stderr.write( "Set expected coverage [RPKM]: %.3f\n" % expCov )
#load gene counts and calculate means
if verbose:
sys.stderr.write( "Loading gene counts...\n" )
means = []
gene2counts = {}
for fn in fnames:
if verbose:
sys.stderr.write( " %s \r" % fn )
gene2counts = load_counts( fn,gene2counts )
## print results
# header
if verbose:
sys.stderr.write( "Calculating...\n" )
header = "#gene\tcoordinate"
for s in samples:
header += "\t%s\tlog2 vs mean" % ( s, )
header += "\tannotation\tpfam"
print header
# per gene scores
for gene in sorted( gene2counts.keys() ):
#if genes only requested then skip
if skipExons:
#check if exon, and skip if so
if gene.split(".")[-1].isdigit():
continue
#
coord,counts = gene2counts[gene]
passed = False
line = "%s\t%s" % ( gene,coord )
for c in counts:
line += "\t%.2f" % c
if not c:
line += "\t-NA"
passed = True
else:
log2 = log( c*1.0/expCov,2 )
line += "\t%.2f" % log2
#filter lines that contain log2 > than log2th or log2 < -log2th
if log2th:
if not -log2th < log2 < log2th:
passed = True
else:
passed = True
#print only if passed filtering
if passed:
ann = pfam = ""
if gene in id2gene:
ann = id2gene[gene][-1] #contig,cdsList,strand,function
if gene in trans2ann:
ann = trans2ann[gene]
if gene in trans2pfam:
pfam = trans2pfam[gene]
line += "\t%s\t%s" % ( ann,pfam )
print line
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 process( fnames,faa,pfam,gtf,log2th,splitFn,skipExons,verbose ):
"""main function
"""
#load function annotation
trans2ann = trans2pfam = {}
if faa:
trans2ann = load_fasta_headers( faa )
if pfam:
trans2pfam = load_pfam( pfam )
ctg2cds,id2gene = {},{}
if gtf:
# load gtf/gff
if gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( gtf )
else:
id2gene,ctg2cds = load_gtf( gtf )
if verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
#get samples names
samples = []
for fn in fnames:
if splitFn:
fn = fn.split(".")[0]
samples.append( fn )
#load gene counts
if verbose:
sys.stderr.write( "Loading gene counts...\n" )
gene2counts = {}
for fn in fnames:
if verbose:
sys.stderr.write( " %s \r" % fn )
gene2counts = load_counts( fn,gene2counts )
## print results
# header
if verbose:
sys.stderr.write( "Calculating...\n" )
header = "#gene\tcoordinate\t%s" % samples[0]
for s in samples[1:]:
header += "\t%s\tlog2(%s/%s)" % ( s,s,samples[0] )
header += "\tannotation\tpfam"
print header
# per gene scores
for gene in sorted( gene2counts.keys() ):
#if genes only requested then skip
if skipExons:
#check if exon, and skip if so
if gene.split(".")[-1].isdigit():
continue
#
coord,counts = gene2counts[gene]
passed = False
line = "%s\t%s\t%.2f" % ( gene,coord,counts[0] )
for c in counts[1:]:
line += "\t%.2f" % c
#ref 0
if not counts[0]:
line += "\t+NA"
passed = True
elif not c:
line += "\t-NA"
passed = True
else:
log2 = log( c*1.0/counts[0],2 )
line += "\t%.2f" % log2
#filter lines that contain log2 > than log2th or log2 < -log2th
if log2th:
if not -log2th < log2 < log2th:
passed = True
else:
passed = True
#print only if passed filtering
if passed:
ann = pfam = ""
if gene in id2gene:
ann = id2gene[gene][-1] #contig,cdsList,strand,function
if gene in trans2ann:
ann = trans2ann[gene]
if gene in trans2pfam:
pfam = trans2pfam[gene]
line += "\t%s\t%s" % ( ann,pfam )
print line
