def main(argv):
parser = OptionParser()
parser.add_option("-s", "--species", action="store", type="string",
dest="species", help="species under consideration", metavar="<str>")
parser.add_option("-b", "--raw_bed_file", action="store", type="string",
dest="bed_file", help="raw bed file", metavar="<file>")
parser.add_option("-t", "--threshold", action="store", type="int",
dest="threshold", help="threshold for copy number", metavar="<int>")
parser.add_option("-o", "--output_file_name", action="store", type="string",
dest="out_file", help="output file name", metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 8:
parser.print_help()
sys.exit(1)
if opt.species in GenomeData.species_chroms.keys():
chroms = GenomeData.species_chroms[opt.species];
else:
print "This species is not recognized, exiting";
sys.exit(1);
SeparateByChrom.separateByChrom(chroms, opt.bed_file, '.bed1')
for chrom in chroms:
if (Utility.fileExists(chrom + ".bed1")):
strand_broken_remove(chrom, opt.threshold)
SeparateByChrom.combineAllGraphFiles(chroms, '.bed2', opt.out_file)
SeparateByChrom.cleanup(chroms, '.bed1')
SeparateByChrom.cleanup(chroms, '.bed2')
def main(argv):
parser = OptionParser()
parser.add_option("-s", "--species", action="store",
type="string", dest="species",
help="species, mm8, hg18, etc", metavar="<str>")
parser.add_option("-a", "--rawbedfile", action="store",
type="string", dest="bedfile",
metavar="<file>",
help="raw data file in bed format")
parser.add_option("-i", "--shift", action="store",
type="int", dest="shift",
metavar="<int>",
help="shift for finding the center of DNA fragment represented by the read")
parser.add_option("-b", "--islandfile", action="store", type="string",
dest="islandbedfile", metavar="<file>",
help="island file")
parser.add_option("-o", "--outfile", action="store", type="string",
dest="out_file", metavar="<file>",
help="filtered raw bed file")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species];
else:
print "This species is not recognized, exiting";
sys.exit(1);
islands = BED_revised.BED_annotated(opt.species, opt.islandbedfile, "BED3", 0);
libName = (opt.bedfile).split('/')[-1] #remove directories
libName = libName.split('.')[0] #remove .bed
extension = "-" + libName +'.bed1'
SeparateByChrom.separateByChrom(chroms, opt.bedfile, extension)
for chrom in chroms:
if chrom in islands.keys():
outfile = chrom + "-filtered" + extension
# [(island, rc)]
island_rc = filter_tags_by_islands(chrom + extension, islands[chrom], opt.shift, outfile, boundary_extension=0)
output_island_with_rc(island_rc, chrom + "-islands" + extension)
SeparateByChrom.combineAllGraphFiles(chroms, "-islands" + extension, "islands" + extension);
SeparateByChrom.combineAllGraphFiles(chroms, "-filtered" + extension, opt.out_file);
SeparateByChrom.cleanup(chroms, extension);
SeparateByChrom.cleanup(chroms, "-filtered" + extension);
SeparateByChrom.cleanup(chroms, "-islands" + extension);
def main(argv):
"""
Note the window_size and the fragment_size are both input as strings, as they are used in
a shell script in makeGraphFile.
"""
parser = OptionParser()
parser.add_option("-s",
"--species",
action="store",
type="string",
dest="species",
help="mm8,hg18,dm2,etc",
metavar="<str>")
parser.add_option("-b",
"--bed_file",
action="store",
type="string",
dest="bedfile",
help="bed file to make graph file of",
metavar="<file>")
parser.add_option("-w",
"--window_size",
action="store",
type="int",
dest="window_size",
help="window size",
metavar="<int>")
parser.add_option("-i",
"--fragment_size",
action="store",
type="int",
dest="fragment_size",
help="size of fragments after CHIP experiment",
metavar="<int>")
parser.add_option("-o",
"--outfile",
action="store",
type="string",
dest="outfile",
help="output bed summary file name",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in GenomeData.species_chroms.keys():
chroms = GenomeData.species_chroms[opt.species]
chrom_lengths = GenomeData.species_chrom_lengths[opt.species]
SeparateByChrom.separateByChrom(chroms, opt.bedfile, ".bed")
makeGraphFile(chroms, chrom_lengths, opt.window_size,
opt.fragment_size)
final_output_file = opt.outfile
final_output_file = SeparateByChrom.combineAllGraphFiles(
chroms, ".graph", final_output_file)
SeparateByChrom.cleanup(chroms, ".bed")
SeparateByChrom.cleanup(chroms, ".graph")
else:
print opt.species + " is not in the species list "
def main(argv):
parser = OptionParser()
parser.add_option("-a", "--islandfile1", action="store", type="string", dest="islandfile1", metavar="<file>", help="file 1 with islands info to be unioned")
parser.add_option("-b", "--islandfile2", action="store", type="string", dest="islandfile2", metavar="<file>", help="file 2 with islands info to be unioned; if no, type in any word")
parser.add_option("-s", "--species", action="store", type="string", dest="species", help="species, mm8 or hg18", metavar="<str>")
parser.add_option("-o", "--outputfile", action="store", type="string", dest="outfile", metavar="<file>", help="output file name")
(opt, args) = parser.parse_args(argv)
if len(argv) < 8:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species];
else:
print "This species is not recognized, exiting";
sys.exit(1);
SeparateByChrom.separateByChrom(chroms, opt.islandfile1, '.island1')
if Utility.fileExists(opt.islandfile2):
SeparateByChrom.separateByChrom(chroms, opt.islandfile2, '.island2')
for chrom in chroms:
f = open(chrom + '.output', 'w')
bed_vals_1 = BED.BED(opt.species, chrom+'.island1', "BED3", 0)
bed_vals_2 = BED.BED(opt.species, chrom+'.island2', "BED3", 0)
if len(bed_vals_1[chrom]) > 0 or len(bed_vals_2[chrom]) > 0:
islandlist = bed_vals_1[chrom] + bed_vals_2[chrom];
union_islands_to_file(islandlist, f)
f.close()
SeparateByChrom.cleanup(chroms, '.island2')
else:
for chrom in chroms:
f = open(chrom + '.output', 'w')
bed_vals_1 = BED.BED(opt.species, chrom+'.island1', "BED3", 0)
if len(bed_vals_1[chrom]) > 0:
islandlist = bed_vals_1[chrom]
union_islands_to_file(islandlist, f)
f.close()
SeparateByChrom.combineAllGraphFiles(chroms, '.output', opt.outfile);
SeparateByChrom.cleanup(chroms, '.output')
SeparateByChrom.cleanup(chroms, '.island1')
def main(argv):
"""
Note the window_size and the fragment_size are both input as strings, as they are used in
a shell script in makeGraphFile.
"""
parser = OptionParser()
parser.add_option("-s", "--species", action="store", type="string",
dest="species", help="mm8,hg18,dm2,etc", metavar="<str>")
parser.add_option("-b", "--bed_file", action="store", type="string",
dest="bamfile", help="bed file to make graph file of",
metavar="<file>")
parser.add_option("-w", "--window_size", action="store", type="int",
dest="window_size", help="window size", metavar="<int>")
parser.add_option("-i", "--fragment_size", action="store", type="int",
dest="fragment_size",
help="size of fragments after CHIP experiment",
metavar="<int>")
parser.add_option("-o", "--outfile", action="store", type="string",
dest="outfile", help="output bed summary file name",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
#if len(argv) < 10:
# sys.stderr.write(str(len(argv)) + '\n')
# parser.print_help()
# sys.exit(1)
#
#if opt.species in GenomeData.species_chroms.keys():
# chroms = GenomeData.species_chroms[opt.species];
#
#chrom_lengths = GenomeData.species_chrom_lengths[opt.species];
chromsDict= SeparateByChrom.getChromsFromBam(opt.bamfile)
SeparateByChrom.separateByChromBamToBed(chromsDict.keys(), opt.bamfile, '.bed');
makeGraphFile(chromsDict.keys(), chromsDict, opt.window_size, opt.fragment_size);
final_output_file = opt.outfile;
final_output_file = SeparateByChrom.combineAllGraphFiles(chromsDict.keys(), ".graph", final_output_file);
SeparateByChrom.cleanup(chromsDict.keys(), ".bed");
SeparateByChrom.cleanup(chromsDict.keys(), ".graph");
def main(argv):
parser = OptionParser()
parser.add_option("-s", "--species", action="store",
type="string", dest="species",
help="species, mm8, hg18", metavar="<str>")
parser.add_option("-a", "--rawbedfile", action="store",
type="string", dest="bedfile",
metavar="<file>",
help="raw data file in bed format")
parser.add_option("-i", "--fragment_size", action="store",
type="int", dest="fragment_size",
metavar="<int>",
help="average size of a fragment after CHIP experiment")
parser.add_option("-b", "--islandfile", action="store", type="string",
dest="islandbedfile", metavar="<file>",
help="island file")
parser.add_option("-o", "--outfile", action="store", type="string",
dest="out_file", metavar="<file>",
help="filtered raw bed file")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species];
else:
print "This species is not recognized, exiting";
sys.exit(1);
islands = BED.BED(opt.species, opt.islandbedfile, "BED3", 0);
SeparateByChrom.separateByChrom(chroms, opt.bedfile, '.bed1')
filter_tags_by_islands(chroms, islands, opt.fragment_size)
final_output_file = opt.out_file;
final_output_file = SeparateByChrom.combineAllGraphFiles(chroms,
'_filtered.bed1',
final_output_file);
SeparateByChrom.cleanup(chroms,'.bed1');
SeparateByChrom.cleanup(chroms,'_filtered.bed1');
def main(argv):
"""
Note the window_size and the fragment_size are both input as strings, as they are used in
a shell script in makeGraphFile.
"""
parser = OptionParser()
parser.add_option("-s", "--species", action="store", type="string",
dest="species", help="mm8,hg18,dm2,etc", metavar="<str>")
parser.add_option("-b", "--bed_file", action="store", type="string",
dest="bedfile", help="bed file to make graph file of",
metavar="<file>")
parser.add_option("-w", "--window_size", action="store", type="int",
dest="window_size", help="window size", metavar="<int>")
parser.add_option("-i", "--fragment_size", action="store", type="int",
dest="fragment_size",
help="size of fragments after CHIP experiment",
metavar="<int>")
parser.add_option("-o", "--outfile", action="store", type="string",
dest="outfile", help="output bed summary file name",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in GenomeData.species_chroms.keys():
chroms = GenomeData.species_chroms[opt.species];
chrom_lengths = GenomeData.species_chrom_lengths[opt.species];
SeparateByChrom.separateByChrom(chroms, opt.bedfile, ".bed");
makeGraphFile(chroms, chrom_lengths, opt.window_size, opt.fragment_size);
final_output_file = opt.outfile;
final_output_file = SeparateByChrom.combineAllGraphFiles(chroms, ".graph", final_output_file);
SeparateByChrom.cleanup(chroms, ".bed");
SeparateByChrom.cleanup(chroms, ".graph");
else:
print opt.species + " is not in the species list ";
def main(argv):
parser = OptionParser()
parser.add_option("-a",
"--islandfile1",
action="store",
type="string",
dest="islandfile1",
metavar="<file>",
help="file 1 with islands info to be unioned")
parser.add_option(
"-b",
"--islandfile2",
action="store",
type="string",
dest="islandfile2",
metavar="<file>",
help="file 2 with islands info to be unioned; if no, type in any word")
parser.add_option("-s",
"--species",
action="store",
type="string",
dest="species",
help="species, mm8 or hg18",
metavar="<str>")
parser.add_option("-o",
"--outputfile",
action="store",
type="string",
dest="outfile",
metavar="<file>",
help="output file name")
(opt, args) = parser.parse_args(argv)
if len(argv) < 8:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species]
else:
print "This species is not recognized, exiting"
sys.exit(1)
SeparateByChrom.separateByChrom(chroms, opt.islandfile1, '.island1')
if Utility.fileExists(opt.islandfile2):
SeparateByChrom.separateByChrom(chroms, opt.islandfile2, '.island2')
for chrom in chroms:
f = open(chrom + '.output', 'w')
bed_vals_1 = BED.BED(opt.species, chrom + '.island1', "BED3", 0)
bed_vals_2 = BED.BED(opt.species, chrom + '.island2', "BED3", 0)
if len(bed_vals_1[chrom]) > 0 or len(bed_vals_2[chrom]) > 0:
islandlist = bed_vals_1[chrom] + bed_vals_2[chrom]
union_islands_to_file(islandlist, f)
f.close()
SeparateByChrom.cleanup(chroms, '.island2')
else:
for chrom in chroms:
f = open(chrom + '.output', 'w')
bed_vals_1 = BED.BED(opt.species, chrom + '.island1', "BED3", 0)
if len(bed_vals_1[chrom]) > 0:
islandlist = bed_vals_1[chrom]
union_islands_to_file(islandlist, f)
f.close()
SeparateByChrom.combineAllGraphFiles(chroms, '.output', opt.outfile)
SeparateByChrom.cleanup(chroms, '.output')
SeparateByChrom.cleanup(chroms, '.island1')
def main(argv):
"""
Note the window_size and the fragment_size are both input as strings, as they are used in
a shell script in makeGraphFile.
"""
parser = OptionParser()
parser.add_option("-s",
"--species",
action="store",
type="string",
dest="species",
help="mm8,hg18,dm2,etc",
metavar="<str>")
parser.add_option("-b",
"--bed_file",
action="store",
type="string",
dest="bamfile",
help="bed file to make graph file of",
metavar="<file>")
parser.add_option("-w",
"--window_size",
action="store",
type="int",
dest="window_size",
help="window size",
metavar="<int>")
parser.add_option("-i",
"--fragment_size",
action="store",
type="int",
dest="fragment_size",
help="size of fragments after CHIP experiment",
metavar="<int>")
parser.add_option("-o",
"--outfile",
action="store",
type="string",
dest="outfile",
help="output bed summary file name",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
#if len(argv) < 10:
# sys.stderr.write(str(len(argv)) + '\n')
# parser.print_help()
# sys.exit(1)
#
#if opt.species in GenomeData.species_chroms.keys():
# chroms = GenomeData.species_chroms[opt.species];
#
#chrom_lengths = GenomeData.species_chrom_lengths[opt.species];
chromsDict = SeparateByChrom.getChromsFromBam(opt.bamfile)
SeparateByChrom.separateByChromBamToBed(chromsDict.keys(), opt.bamfile,
'.bed')
makeGraphFile(chromsDict.keys(), chromsDict, opt.window_size,
opt.fragment_size)
final_output_file = opt.outfile
final_output_file = SeparateByChrom.combineAllGraphFiles(
chromsDict.keys(), ".graph", final_output_file)
SeparateByChrom.cleanup(chromsDict.keys(), ".bed")
SeparateByChrom.cleanup(chromsDict.keys(), ".graph")
def main(argv):
'''
Coarse graining test chr1, input must only have chr1
'''
parser = OptionParser()
parser.add_option("-s", "--species", action="store", type="string", dest="species", help="mm8, hg18, background, etc", metavar="<str>")
parser.add_option("-b", "--summarygraph", action="store",type="string", dest="summarygraph", help="summarygraph", metavar="<file>")
parser.add_option("-w", "--window_size(bp)", action="store", type="int", dest="window_size", help="window_size(in bps)", metavar="<int>")
parser.add_option("-g", "--graining_size", action="store", type="int", dest="step", help="graining unit size (>0)", metavar="<int>")
parser.add_option("-e", "--score", action="store", type="int", dest="score", help="graining criterion, 0<score<=graining_size", metavar="<int>")
parser.add_option("-t", "--mappable_faction_of_genome_size", action="store", type="float", dest="fraction", help="mapable fraction of genome size", metavar="<float>")
parser.add_option("-f", "--output_file", action="store", type="string", dest="out_file", help="output file name", metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 14:
parser.print_help()
sys.exit(1)
print "Coarse-graining approach to identify ChIP-Seq enriched domains:"
if opt.species in GenomeData.species_chroms.keys():
print "Species: ", opt.species;
print "Window_size: ", opt.window_size;
print "Coarse graining step: ", opt.step;
print "Coarse graining score:", opt.score;
chroms = GenomeData.species_chroms[opt.species]
total_read_count = get_total_tag_counts.get_total_tag_counts_bed_graph(opt.summarygraph);
print "Total read count:", total_read_count
genome_length = sum (GenomeData.species_chrom_lengths[opt.species].values());
genome_length = int(opt.fraction * genome_length);
average = float(total_read_count) * opt.window_size/genome_length;
print "Effective genome length: ", genome_length;
print "window average:", average;
min_tags_in_window = int(average) + 1
print "Minimum read count in a qualified window: ", min_tags_in_window
print "Generate preprocessed data list";
#read in the summary graph file
bed_val = BED.BED(opt.species, opt.summarygraph, "BED_GRAPH");
#generate the probscore summary graph file, only care about enrichment
for chrom in chroms:
if chrom in bed_val.keys() and len(bed_val[chrom]) > 0:
chrom_length = GenomeData.species_chrom_lengths[opt.species][chrom]
eligible_start_list = []
for index in xrange(len(bed_val[chrom])):
read_count = bed_val[chrom][index].value;
if read_count >= min_tags_in_window:
eligible_start_list.append(bed_val[chrom][index].start)
print "Coarse graining:";
(result_list, island_list) = coarsegraining(eligible_start_list, opt.window_size, opt.step, opt.score, chrom_length)
print "Trace back...", len(island_list)
islands = traceback(island_list, opt.window_size, opt.step, 0, chrom_length, chrom)
print len(islands), "islands found in", chrom
f = open(chrom + ".islandstemp", 'w')
for i in range(0, len(islands)):
f.write(chrom + '\t' + str(int(islands[i].start)) + '\t' + str(int(islands[i].end)) + '\t1\n')
f.close()
o = open(opt.out_file, 'w')
o.write('track type=bedGraph name=' + opt.out_file + '\n')
o.close()
SeparateByChrom.combineAllGraphFiles(chroms, ".islandstemp", opt.out_file)
SeparateByChrom.cleanup(chroms, ".islandstemp")
#else:
#print "input data error!"
else:
print "This species is not in my list!";
def main(argv):
parser = OptionParser()
parser.add_option("-a", "--islandfile1", action="store", type="string", dest="islandfile1", metavar="<file>", help="file 1 with islands info to be compared")
parser.add_option("-b", "--islandfile2", action="store", type="string", dest="islandfile2", metavar="<file>", help="file 2 with islands info to be compared")
parser.add_option("-s", "--species", action="store", type="string", dest="species", help="species, mm8 or hg18", metavar="<str>")
parser.add_option("-p", "--overlapin1", action="store", type="string", dest="overlapin1", metavar="<file>", help="file for islands in 1 overlapping with islands in 2")
parser.add_option("-q", "--nonoverlapin1", action="store", type="string", dest="nonoverlapin1", help="file for islands in 1 not overlapping with islands in 2 ", metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species];
else:
print "This species is not recognized, exiting";
sys.exit(1);
total_overlap_number_1 = 0
total_islands_1 = 0
SeparateByChrom.separateByChrom(chroms, opt.islandfile1, '.island1')
SeparateByChrom.separateByChrom(chroms, opt.islandfile2, '.island2')
for chrom in chroms:
f = open(chrom + '.1in2', 'w')
g = open(chrom + '.1notin2', 'w')
bed_vals_2 = BED.BED(opt.species, chrom+'.island2', "BED3", 0)
if Utility.fileExists(chrom+'.island1') and len(bed_vals_2[chrom])>0:
islandlist2 = bed_vals_2[chrom];
if (are_islands_sorted(islandlist2) != 1):
islandlist2.sort(key=operator.attrgetter('start'));
(island2_start_list, island2_end_list) = union_islands(islandlist2)
islands1 = open(chrom+'.island1', 'r')
for line in islands1:
if not re.match("#", line):
total_islands_1 += 1
line = line.strip()
sline = line.split()
start = int(sline[1])
end = int(sline[2])
if (region_overlap(start, end, island2_start_list, island2_end_list) == 1):
f.write('\t'.join(sline) + '\n')
total_overlap_number_1 += 1;
else:
g.write('\t'.join(sline) + '\n');
elif Utility.fileExists(chrom+'.island1') and (len(bed_vals_2[chrom])==0):
islands1 = open(chrom+'.island1', 'r')
for line in islands1:
if not re.match("#", line):
total_islands_1 += 1
line = line.strip()
sline = line.split()
g.write('\t'.join(sline) + '\n');
f.close()
g.close()
print "total number of island in "+opt.islandfile1+": ", total_islands_1;
print "total number of island in "+opt.overlapin1+": ", total_overlap_number_1;
SeparateByChrom.combineAllGraphFiles(chroms, '.1in2', opt.overlapin1);
SeparateByChrom.combineAllGraphFiles(chroms, '.1notin2', opt.nonoverlapin1);
SeparateByChrom.cleanup(chroms, '.1in2')
SeparateByChrom.cleanup(chroms, '.1notin2')
SeparateByChrom.cleanup(chroms, '.island1')
SeparateByChrom.cleanup(chroms, '.island2')
def main(argv):
parser = OptionParser()
parser.add_option("-a",
"--islandfile1",
action="store",
type="string",
dest="islandfile1",
metavar="<file>",
help="file 1 with islands info to be compared")
parser.add_option("-b",
"--islandfile2",
action="store",
type="string",
dest="islandfile2",
metavar="<file>",
help="file 2 with islands info to be compared")
parser.add_option("-s",
"--species",
action="store",
type="string",
dest="species",
help="species, mm8 or hg18",
metavar="<str>")
parser.add_option(
"-p",
"--overlapin1",
action="store",
type="string",
dest="overlapin1",
metavar="<file>",
help="file for islands in 1 overlapping with islands in 2")
parser.add_option(
"-q",
"--nonoverlapin1",
action="store",
type="string",
dest="nonoverlapin1",
help="file for islands in 1 not overlapping with islands in 2 ",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species]
else:
print "This species is not recognized, exiting"
sys.exit(1)
total_overlap_number_1 = 0
total_islands_1 = 0
SeparateByChrom.separateByChrom(chroms, opt.islandfile1, '.island1')
SeparateByChrom.separateByChrom(chroms, opt.islandfile2, '.island2')
for chrom in chroms:
f = open(chrom + '.1in2', 'w')
g = open(chrom + '.1notin2', 'w')
bed_vals_2 = BED.BED(opt.species, chrom + '.island2', "BED3", 0)
if Utility.fileExists(chrom +
'.island1') and len(bed_vals_2[chrom]) > 0:
islandlist2 = bed_vals_2[chrom]
if (are_islands_sorted(islandlist2) != 1):
islandlist2.sort(key=operator.attrgetter('start'))
(island2_start_list, island2_end_list) = union_islands(islandlist2)
islands1 = open(chrom + '.island1', 'r')
for line in islands1:
if not re.match("#", line):
total_islands_1 += 1
line = line.strip()
sline = line.split()
start = int(sline[1])
end = int(sline[2])
if (region_overlap(start, end, island2_start_list,
island2_end_list) == 1):
f.write('\t'.join(sline) + '\n')
total_overlap_number_1 += 1
else:
g.write('\t'.join(sline) + '\n')
elif Utility.fileExists(chrom + '.island1') and (len(bed_vals_2[chrom])
== 0):
islands1 = open(chrom + '.island1', 'r')
for line in islands1:
if not re.match("#", line):
total_islands_1 += 1
line = line.strip()
sline = line.split()
g.write('\t'.join(sline) + '\n')
f.close()
g.close()
print "total number of island in " + opt.islandfile1 + ": ", total_islands_1
print "total number of island in " + opt.overlapin1 + ": ", total_overlap_number_1
SeparateByChrom.combineAllGraphFiles(chroms, '.1in2', opt.overlapin1)
SeparateByChrom.combineAllGraphFiles(chroms, '.1notin2', opt.nonoverlapin1)
SeparateByChrom.cleanup(chroms, '.1in2')
SeparateByChrom.cleanup(chroms, '.1notin2')
SeparateByChrom.cleanup(chroms, '.island1')
SeparateByChrom.cleanup(chroms, '.island2')
def main(argv):
parser = OptionParser()
parser.add_option("-a",
"--islandfile1",
action="store",
type="string",
dest="islandfile1",
metavar="<file>",
help="file 1 with islands info to be compared")
parser.add_option("-b",
"--islandfile2",
action="store",
type="string",
dest="islandfile2",
metavar="<file>",
help="file 2 with islands info to be compared")
parser.add_option("-s",
"--species",
action="store",
type="string",
dest="species",
help="species, mm8 or hg18",
metavar="<str>")
parser.add_option(
"-p",
"--overlapin1",
action="store",
type="string",
dest="overlapin1",
metavar="<file>",
help="file for islands in 1 overlapping with islands in 2")
parser.add_option(
"-q",
"--nonoverlapin1",
action="store",
type="string",
dest="nonoverlapin1",
help="file for islands in 1 not overlapping with islands in 2 ",
metavar="<file>")
(opt, args) = parser.parse_args(argv)
if len(argv) < 10:
parser.print_help()
sys.exit(1)
if opt.species in species_chroms.keys():
chroms = species_chroms[opt.species]
else:
print "This species is not recognized, exiting"
sys.exit(1)
total_overlap_number_1 = 0
total_islands_1 = 0
SeparateByChrom.separateByChrom(chroms, opt.islandfile1, '.island1')
SeparateByChrom.separateByChrom(chroms, opt.islandfile2, '.island2')
for chrom in chroms:
f = open(chrom + '.1in2', 'w')
g = open(chrom + '.1notin2', 'w')
bed_vals_1 = BED.BED(opt.species, chrom + '.island1', "BED_GRAPH", 0)
bed_vals_2 = BED.BED(opt.species, chrom + '.island2', "BED_GRAPH", 0)
if len(bed_vals_1[chrom]) > 0 and len(bed_vals_2[chrom]) > 0:
islandlist1 = bed_vals_1[chrom]
islandlist2 = bed_vals_2[chrom]
total_islands_1 += len(bed_vals_1[chrom])
for islandlist1_item in islandlist1:
start = islandlist1_item.start
end = islandlist1_item.end
if (region_overlap(start, end, islandlist2) == 1):
write(islandlist1_item, f)
total_overlap_number_1 += 1
else:
write(islandlist1_item, g)
elif (len(bed_vals_1[chrom]) > 0) and (len(bed_vals_2[chrom]) == 0):
total_islands_1 += len(bed_vals_1[chrom])
for islandlist1_item in bed_vals_1[chrom]:
write(islandlist1_item, g)
f.close()
g.close()
print "total number of island in " + opt.islandfile1 + ": ", total_islands_1
print "total number of island in " + opt.overlapin1 + ": ", total_overlap_number_1
SeparateByChrom.combineAllGraphFiles(chroms, '.1in2', opt.overlapin1)
SeparateByChrom.combineAllGraphFiles(chroms, '.1notin2', opt.nonoverlapin1)
SeparateByChrom.cleanup(chroms, '.1in2')
SeparateByChrom.cleanup(chroms, '.1notin2')
SeparateByChrom.cleanup(chroms, '.island1')
SeparateByChrom.cleanup(chroms, '.island2')
