def parse_bam_differential(afn, bfn, regs, step):
"""(internal) Parses bam file in absolute mode. Proceeds by counting reads mapping
onto a segment (chr, start, end). No normalization is done at this step.
"""
abam = Samfile(str(afn), "rb")
bbam = Samfile(str(bfn), "rb")
acount = []
bcount = []
oldchr = "chr1"
for reg in regs:
chr, start, end = reg[:3]
if chr != oldchr:
log("files: %s - %s : %s counted" % (afn, bfn, oldchr))
oldchr = chr
# this could be improved
for s in xrange(start, end, step):
e = s + step
an = abam.count(chr, s, e)
bn = bbam.count(chr, s, e)
acount.append(an)
bcount.append(bn)
acount.append(-1)
bcount.append(-1)
log("files: %s - %s : %s counted (finished)" % (afn, bfn, oldchr))
return acount, bcount
def parse_bam_differential(afn, bfn, regs, step):
"""(internal) Parses bam file in absolute mode. Proceeds by counting reads mapping
onto a segment (chr, start, end). No normalization is done at this step.
"""
abam = Samfile(str(afn), "rb")
bbam = Samfile(str(bfn), "rb")
acount = []
bcount = []
oldchr = "chr1"
for reg in regs:
chr, start, end = reg[:3]
if chr != oldchr:
log("files: %s - %s : %s counted" % (afn, bfn, oldchr))
oldchr = chr
# this could be improved
for s in xrange(start, end, step):
e = s + step
an = abam.count(chr, s, e)
bn = bbam.count(chr, s, e)
acount.append(an)
bcount.append(bn)
acount.append(-1)
bcount.append(-1)
log("files: %s - %s : %s counted (finished)" % (afn, bfn, oldchr))
return acount, bcount
def parse_bam_absolute(fn, regs):
"""(internal) Parses bam file in absolute mode. Proceeds by counting reads mapping
onto a segment (chr, start, end) and normalizes the count by the segment's length.
"""
bam = Samfile(str(fn), "rb")
count = []
for reg in regs:
chr, start, end = reg[:3]
n = bam.count(chr, start, end)
count.append(float(n) / (end - start))
return count
def parse_bam_absolute(fn, regs):
"""(internal) Parses bam file in absolute mode. Proceeds by counting reads mapping
onto a segment (chr, start, end) and normalizes the count by the segment's length.
"""
bam = Samfile(str(fn), "rb")
count = []
for reg in regs:
chr, start, end = reg[:3]
n = bam.count(chr, start, end)
count.append(float(n) / (end - start))
return count
def ace(args):
"""
%prog ace bamfile fastafile
convert bam format to ace format. This often allows the remapping to be
assessed as a denovo assembly format. bam file needs to be indexed. also
creates a .mates file to be used in amos/bambus, and .astat file to mark
whether the contig is unique or repetitive based on A-statistics in Celera
assembler.
"""
p = OptionParser(ace.__doc__)
p.add_option(
"--splitdir",
dest="splitdir",
default="outRoot",
help="split the ace per contig to dir",
)
p.add_option(
"--unpaired",
dest="unpaired",
default=False,
help="remove read pairs on the same contig",
)
p.add_option(
"--minreadno",
dest="minreadno",
default=3,
type="int",
help="minimum read numbers per contig",
)
p.add_option(
"--minctgsize",
dest="minctgsize",
default=100,
type="int",
help="minimum contig size per contig",
)
p.add_option(
"--astat",
default=False,
action="store_true",
help="create .astat to list repetitiveness",
)
p.add_option(
"--readids",
default=False,
action="store_true",
help="create file of mapped and unmapped ids",
)
from pysam import Samfile
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bamfile, fastafile = args
astat = opts.astat
readids = opts.readids
f = Fasta(fastafile)
prefix = bamfile.split(".")[0]
acefile = prefix + ".ace"
readsfile = prefix + ".reads"
astatfile = prefix + ".astat"
logging.debug("Load {0}".format(bamfile))
s = Samfile(bamfile, "rb")
ncontigs = s.nreferences
genomesize = sum(x for a, x in f.itersizes())
logging.debug("Total {0} contigs with size {1} base".format(ncontigs, genomesize))
qual = "20" # default qual
totalreads = sum(s.count(x) for x in s.references)
logging.debug("Total {0} reads mapped".format(totalreads))
fw = open(acefile, "w")
if astat:
astatfw = open(astatfile, "w")
if readids:
readsfw = open(readsfile, "w")
print("AS {0} {1}".format(ncontigs, totalreads), file=fw)
print(file=fw)
for i, contig in enumerate(s.references):
cseq = f[contig]
nbases = len(cseq)
mapped_reads = [x for x in s.fetch(contig) if not x.is_unmapped]
nreads = len(mapped_reads)
nsegments = 0
print("CO {0} {1} {2} {3} U".format(contig, nbases, nreads, nsegments), file=fw)
print(fill(str(cseq.seq)), file=fw)
print(file=fw)
if astat:
astat = Astat(nbases, nreads, genomesize, totalreads)
print("{0}\t{1:.1f}".format(contig, astat), file=astatfw)
text = fill([qual] * nbases, delimiter=" ", width=30)
print("BQ\n{0}".format(text), file=fw)
print(file=fw)
rnames = []
for a in mapped_reads:
readname = a.qname
rname = readname
if readids:
print(readname, file=readsfw)
rnames.append(rname)
strand = "C" if a.is_reverse else "U"
paddedstart = a.pos + 1 # 0-based to 1-based
af = "AF {0} {1} {2}".format(rname, strand, paddedstart)
print(af, file=fw)
print(file=fw)
for a, rname in zip(mapped_reads, rnames):
aseq, npadded = cigar_to_seq(a)
if aseq is None:
continue
ninfos = 0
ntags = 0
alen = len(aseq)
rd = "RD {0} {1} {2} {3}\n{4}".format(
rname, alen, ninfos, ntags, fill(aseq)
)
qs = "QA 1 {0} 1 {0}".format(alen)
print(rd, file=fw)
print(file=fw)
print(qs, file=fw)
print(file=fw)
def ace(args):
"""
%prog ace bamfile fastafile
convert bam format to ace format. This often allows the remapping to be
assessed as a denovo assembly format. bam file needs to be indexed. also
creates a .mates file to be used in amos/bambus, and .astat file to mark
whether the contig is unique or repetitive based on A-statistics in Celera
assembler.
"""
p = OptionParser(ace.__doc__)
p.add_option("--splitdir", dest="splitdir", default="outRoot",
help="split the ace per contig to dir [default: %default]")
p.add_option("--unpaired", dest="unpaired", default=False,
help="remove read pairs on the same contig [default: %default]")
p.add_option("--minreadno", dest="minreadno", default=3, type="int",
help="minimum read numbers per contig [default: %default]")
p.add_option("--minctgsize", dest="minctgsize", default=100, type="int",
help="minimum contig size per contig [default: %default]")
p.add_option("--astat", default=False, action="store_true",
help="create .astat to list repetitiveness [default: %default]")
p.add_option("--readids", default=False, action="store_true",
help="create file of mapped and unmapped ids [default: %default]")
from pysam import Samfile
opts, args = p.parse_args(args)
if len(args) != 2:
sys.exit(not p.print_help())
bamfile, fastafile = args
astat = opts.astat
readids = opts.readids
f = Fasta(fastafile)
prefix = bamfile.split(".")[0]
acefile = prefix + ".ace"
readsfile = prefix + ".reads"
astatfile = prefix + ".astat"
logging.debug("Load {0}".format(bamfile))
s = Samfile(bamfile, "rb")
ncontigs = s.nreferences
genomesize = sum(x for a, x in f.itersizes())
logging.debug("Total {0} contigs with size {1} base".format(ncontigs,
genomesize))
qual = "20" # default qual
totalreads = sum(s.count(x) for x in s.references)
logging.debug("Total {0} reads mapped".format(totalreads))
fw = open(acefile, "w")
if astat:
astatfw = open(astatfile, "w")
if readids:
readsfw = open(readsfile, "w")
print >> fw, "AS {0} {1}".format(ncontigs, totalreads)
print >> fw
for i, contig in enumerate(s.references):
cseq = f[contig]
nbases = len(cseq)
mapped_reads = [x for x in s.fetch(contig) if not x.is_unmapped]
nreads = len(mapped_reads)
nsegments = 0
print >> fw, "CO {0} {1} {2} {3} U".format(contig, nbases, nreads,
nsegments)
print >> fw, fill(str(cseq.seq))
print >> fw
if astat:
astat = Astat(nbases, nreads, genomesize, totalreads)
print >> astatfw, "{0}\t{1:.1f}".format(contig, astat)
text = fill([qual] * nbases, delimiter=" ", width=30)
print >> fw, "BQ\n{0}".format(text)
print >> fw
rnames = []
for a in mapped_reads:
readname = a.qname
rname = readname
if readids:
print >> readsfw, readname
rnames.append(rname)
strand = "C" if a.is_reverse else "U"
paddedstart = a.pos + 1 # 0-based to 1-based
af = "AF {0} {1} {2}".format(rname, strand, paddedstart)
print >> fw, af
print >> fw
for a, rname in zip(mapped_reads, rnames):
aseq, npadded = cigar_to_seq(a)
if aseq is None:
continue
ninfos = 0
ntags = 0
alen = len(aseq)
rd = "RD {0} {1} {2} {3}\n{4}".format(rname, alen, ninfos, ntags,
fill(aseq))
qs = "QA 1 {0} 1 {0}".format(alen)
print >> fw, rd
print >> fw
print >> fw, qs
print >> fw
def create_multi_table(max_dist, alias_file_name, genes_file_name, exp_file_name, dsb_file_name, dist_file_name, output_location):
# Global Parameters
seed(111)
promExt = 2000
command = "mkdir -p "+output_location
os.system(command)
# Allowed chromosomes
chrom_list = ["chr"+str(e) for e in range(1,23)+["X"]]
# Fetch alias dictionary
alias_dict = read_alias_dictionary(alias_file_name)
# Fetch expression
exp_dict = fetch_expression(exp_file_name)
# Fetch distance
dist_dict = create_distance_dictionary(dist_file_name)
# Input Files
allGenesFile = open(genes_file_name, "rU")
try: dsbFile = Samfile(dsb_file_name, "rb")
except Exception:
print("ERROR: Could not open DSB BAM file. Check your Pysam installation.")
exit(1)
# Output file
output_file_name = output_location + "table.txt"
outputFile = open(output_file_name, "w")
outputFile.write("\t".join(["GENE", "DISTANCE", "EXPRESSION", "DSB"])+"\n")
# Iterating in gene file
for line in allGenesFile:
# Initialization
ll = line.strip().split("\t")
try: chrom = ll[0]; p1 = int(ll[1]); p2 = int(ll[2]); gene = ll[3].upper(); score = ll[4]; strand = ll[5]
except Exception: print("ERROR: The genes file must be a tab-separated bed file with columns: chromosome, start, end, gene_name, score (not used), strand")
try: gene = alias_dict[gene]
except Exception: pass
if(chrom not in chrom_list): continue
if(strand == "+"): region = [chrom, p1 - promExt, p1]
else: region = [chrom, p2, p2 + promExt]
# Fetch distance
try: distance = dist_dict[gene]
except Exception: continue
if(distance >= max_dist): continue
# Fetch expression 1
try: exp = exp_dict[alias_dict[gene]]
except Exception: continue
if(exp <= 0): continue
if(distance <= 0): dfactor = 0.9
else: dfactor = distance
exp = (200./dfactor) + exp * exp
jitt = random() * 3
exp = exp - jitt
# Fetch DSB counts
if(dsbFile):
if(strand == "+"):
tss1 = p1 - promExt
tss2 = p1
elif(strand == "-"):
tss1 = p2
tss2 = p2 + promExt
dsbCount = dsbFile.count(chrom, tss1, tss2)
dsbCount = (exp + (dsbCount/10.) + (random()*3.)) / 1000.
else: continue
# Fetch expression 2
try:
jitt = 50 * random() * ((100 * dsbCount)**2)
exp = exp + jitt
except Exception: continue
# Writing to file
outputFile.write("\t".join([str(e) for e in [gene, distance, exp, dsbCount]])+"\n")
# Closing files
if(dsbFile): dsbFile.close()
allGenesFile.close()
outputFile.close()
# Script path
script_path = "/".join(os.path.realpath(__file__).split("/")[:-1]) + "/"
# Creating plots
output_dist_dsb_exp = output_location + "3D_dist_dsb_exp.pdf"
command = "Rscript "+script_path+"3Dplot.R "+" ".join([str(max_dist), output_file_name, output_dist_dsb_exp])
os.system(command)
output_dist_dsb = output_location + "2D_dist_dsb.pdf"
output_dist_exp = output_location + "2D_dist_exp.pdf"
output_exp_dsb = output_location + "2D_exp_dsb.pdf"
command = "Rscript "+script_path+"2Dplot.R "+" ".join([str(max_dist), output_file_name, output_dist_dsb, output_dist_exp, output_exp_dsb])
os.system(command)
