def evidence_run(args):
# Expanding summits
chip_summit_regions = GenomicRegionSet("TFBS Summit Regions")
chip_summit_regions.read(args.chip_file)
for region in iter(chip_summit_regions):
summit = int(region.data.split()[-1]) + region.initial
region.initial = max(summit - (args.peak_ext / 2), 0)
region.final = summit + (args.peak_ext / 2)
# Calculating intersections
mpbs_regions = GenomicRegionSet("MPBS Regions")
mpbs_regions.read(args.mpbs_file)
chip_summit_regions.sort()
mpbs_regions.sort()
tfbs_regions = GenomicRegionSet("TFBS Regions")
for mpbs_region in mpbs_regions:
if chip_summit_regions.include(mpbs_region):
mpbs_region.name = mpbs_region.name.split(":")[0] + ":Y"
else:
mpbs_region.name = mpbs_region.name.split(":")[0] + ":N"
tfbs_regions.add(mpbs_region)
tfbs_regions.sort()
tfbs_fname = os.path.join(args.output_location,
"{}.bed".format(args.output_prefix))
tfbs_regions.write(tfbs_fname)
if seqrec.id in organisms.values():
seqs.append(seqrec)
except:
continue
new_alignment = MultipleSeqAlignment(records=seqs)
#print(len(new_alignment))
AlignIO.write(new_alignment, "mm9_" + rg.name + ".fa", "fasta")
process = subprocess.Popen([
"/home/joseph/Apps/PhyloCSF/PhyloCSF", "29mammals",
"mm9_" + rg.name + ".fa", "--removeRefGaps", "--strategy=omega",
"--orf=StopStop3", "--minCodons=25", "--frames=3"
],
stdout=subprocess.PIPE)
out, err = process.communicate()
print(out)
#print(out.split("\t")[2])
#print(out.split("\t")[3])
#print(out.split("\t")[4])
data = rg.data.split("\t")
score = out.split("\t")[2]
rg.data = "\t".join([score] + data[1:])
bed.write(args.o)
# 29/9/2015
# python /projects/reg-gen/tools/phylocsf_check.py -i /projects/ig440396_dendriticcells/exp/RNASeq/expression/isofroms/deseq/new_bed/all_TCONs.bed -o all_TCONS_phyloCSF.bed -organism mm9 -mafdir /data/genome/mm9/multiz30way/maf/