def main():
if len(sys.argv) < 2:
bb.fun_print_help("species_query", "species_target", "path_out", "chain_files(eg: rn5ToRn6,rn6ToMm10)","[query.ns.bed]",
"[query.bed]")
global_para()
if not os.path.exists(PATH_OUT):
bb.fun_print("create out path......", "red", "black", 1)
os.mkdir(PATH_OUT)
dict_pi = get_pi()
psl_map()
dict_exon_intron = read_exon_intron()
write_exon_intron_length(dict_exon_intron)
dict_cover = calculate_coverage(dict_exon_intron)
list_ortho = find_ortho_pi(dict_cover)
dict_synteny = get_synteny(dict_pi, list_ortho)
run_lastz(dict_synteny, dict_pi, dict_cover)
for i in dict_pi:
if i not in list_ortho and i not in dict_synteny:
LIST_OUT.append([i, 0, "none", "0", "0", "0", "chrNA", 1, 1, "+"])
file_out = bb.fun_open_file("{0}/{1}_{2}.conserve.tab".format(PATH_OUT, SPECIES1, SPECIES2), "w")
for i in LIST_OUT:
file_out.write(i[0])
for j in range(1, len(i)):
file_out.write("\t" + str(i[j]))
file_out.write("\n")
file_out.close()
os.system("rm {0}/temp*".format(PATH_OUT))
def main():
if len(sys.argv) < 2:
bb.fun_print_help("in.fastq", "out.fastq")
global RECODE
RECODE = {
"0": {
"A": "A",
"C": "C",
"G": "G",
"T": "T"
},
"1": {
"A": "C",
"C": "A",
"G": "T",
"T": "G"
},
"2": {
"A": "G",
"C": "T",
"G": "A",
"T": "C"
},
"3": {
"A": "T",
"C": "G",
"G": "C",
"T": "A"
}
}
file_solid = bb.fun_open_file(sys.argv[1])
file_illumina = bb.fun_open_file(sys.argv[2], "w")
count = 0
for l in file_solid:
count += 1
if count % 100000 == 0:
sys.stdout.write(".")
sys.stdout.flush()
if l.startswith("@") or l.startswith("+"):
file_illumina.write(l)
elif l.startswith("!"):
file_illumina.write(l[1:])
else:
string_solid = l.strip()
string_illumina = decode(string_solid)
file_illumina.write(string_illumina + "\n")
file_illumina.close()
def print_help():
if len(sys.argv) < 2:
bb.fun_print_help(args)
def print_help():
if len(sys.argv) < 2:
bb.fun_print_help("in.gtf", "out.bed12")
def print_help():
if len(sys.argv) < 2:
bb.fun_print_help("in.bed2", "in.feature.sizes", "out.dir")
def print_help():
if len(sys.argv) < 4:
bb.fun_print_help(
"in.bed2", "chrom.size", "out.prefix", "factor", "CPU",
"\nGenerally, bed2_to_bw.py will seperate uniqMappers and allMappers in Watson and Crick strand.\nYou can set CPU to 0 to suppress seperation."
)
def print_help():
if len(sys.argv) < 2:
bb.fun_print_help("in.bw", "gene.bed", "out.mat", "dataPoints")