Created
April 29, 2016 20:43
-
-
Save dpryan79/ce3d119113646bb1b7752a721fd7eb79 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
e2g = [] | |
e2u = [] | |
g2e = [] | |
g2u = [] | |
u2e = [] | |
u2g = [] | |
ifile = open("GCA_000001405.22_GRCh38.p7_assembly_report.txt", "r") | |
for line in ifile: | |
if line.startswith("#"): | |
continue | |
cols = line.strip().split("\t") | |
ctype = cols[1] | |
if ctype == "assembled-molecule": | |
e2g.append("{}\t{}\n".format(cols[2], cols[9])) | |
g2e.append("{}\t{}\n".format(cols[9], cols[2])) | |
e2u.append("{}\t{}\n".format(cols[2], cols[9])) | |
u2e.append("{}\t{}\n".format(cols[9], cols[2])) | |
u2g.append("{}\t{}\n".format(cols[9], cols[9])) | |
g2u.append("{}\t{}\n".format(cols[9], cols[9])) | |
elif ctype == "unlocalized-scaffold" or ctype == "unplaced-scaffold": | |
#UCSC 9 | |
#gencode/ensembl 4 | |
e2g.append("{}\t{}\n".format(cols[4], cols[4])) | |
g2e.append("{}\t{}\n".format(cols[4], cols[4])) | |
e2u.append("{}\t{}\n".format(cols[4], cols[9])) | |
u2e.append("{}\t{}\n".format(cols[9], cols[4])) | |
u2g.append("{}\t{}\n".format(cols[9], cols[4])) | |
g2u.append("{}\t{}\n".format(cols[4], cols[9])) | |
elif ctype in ["fix-patch", "novel-patch"]: | |
#gencode 4 | |
#ensembl CHR_0 | |
e2g.append("CHR_{}\t{}\n".format(cols[0], cols[4])) | |
g2e.append("{}\tCHR_{}\n".format(cols[4], cols[0])) | |
e2u.append("CHR_{}\t\n".format(cols[0])) | |
g2u.append("{}\t\n".format(cols[4])) | |
elif ctype == "alt-scaffold": | |
#UCSC 9 | |
#gencode 4 | |
#ensembl CHR_0 | |
e2g.append("CHR_{}\t{}\n".format(cols[0], cols[4])) | |
g2e.append("{}\tCHR_{}\n".format(cols[4], cols[0])) | |
e2u.append("CHR_{}\t{}\n".format(cols[0], cols[9])) | |
u2e.append("{}\tCHR_{}\n".format(cols[9], cols[0])) | |
u2g.append("{}\t{}\n".format(cols[9], cols[4])) | |
g2u.append("{}\t{}\n".format(cols[4], cols[9])) | |
else: | |
print("can't handle {}".format(ctype)) | |
f = open("GRCh38_ensembl2gencode.txt", "w") | |
for line in sorted(e2g, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
f = open("GRCh38_gencode2ensembl.txt", "w") | |
for line in sorted(g2e, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
f = open("GRCh38_UCSC2gencode.txt", "w") | |
for line in sorted(u2g, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
f = open("GRCh38_UCSC2ensembl.txt", "w") | |
for line in sorted(u2e, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
f = open("GRCh38_ensembl2UCSC.txt", "w") | |
for line in sorted(e2u, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
f = open("GRCh38_gencode2UCSC.txt", "w") | |
for line in sorted(g2u, key=lambda x: x.lower()): | |
f.write(line) | |
f.close() | |
ifile.close() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
e2g = [] #open("GRCm38_ensembl2gencode.txt", "w") | |
e2u = [] #open("GRCm38_ensembl2UCSC.txt", "w") | |
g2e = [] #open("GRCm38_gencode2ensembl.txt", "w") | |
g2u = [] #open("GRCm38_gencode2UCSC.txt", "w") | |
u2e = [] #open("GRCm38_UCSC2ensembl.txt", "w") | |
u2g = [] #open("GRCm38_UCSC2gencode.txt", "w") | |
ifile = open("GCA_000001635.6_GRCm38.p4_assembly_report.txt", "r") | |
for line in ifile: | |
if line.startswith("#"): | |
continue | |
cols = line.strip().split("\t") | |
ctype = cols[1] | |
if ctype == "assembled-molecule": | |
e2g.append("{}\t{}\n".format(cols[2], cols[9])) | |
g2e.append("{}\t{}\n".format(cols[9], cols[2])) | |
e2u.append("{}\t{}\n".format(cols[2], cols[9])) | |
u2e.append("{}\t{}\n".format(cols[9], cols[2])) | |
u2g.append("{}\t{}\n".format(cols[9], cols[9])) | |
g2u.append("{}\t{}\n".format(cols[9], cols[9])) | |
elif ctype == "unlocalized-scaffold" or ctype == "unplaced-scaffold": | |
#UCSC 9 | |
#gencode/ensembl 4 | |
e2g.append("{}\t{}\n".format(cols[4], cols[4])) | |
g2e.append("{}\t{}\n".format(cols[4], cols[4])) | |
e2u.append("{}\t{}\n".format(cols[4], cols[9])) | |
u2e.append("{}\t{}\n".format(cols[9], cols[4])) | |
u2g.append("{}\t{}\n".format(cols[9], cols[4])) | |
g2u.append("{}\t{}\n".format(cols[4], cols[9])) | |
elif ctype == "novel-patch" or ctype == "fix-patch": | |
#UCSC ignore | |
#gencode 4 | |
#ensembl CHR_0 | |
e2g.append("CHR_{}\t{}\n".format(cols[0], cols[4])) | |
g2e.append("{}\tCHR_{}\n".format(cols[4], cols[0])) | |
e2u.append("CHR_{}\t\n".format(cols[0])) | |
g2u.append("{}\t\n".format(cols[4])) | |
elif ctype == "alt-scaffold": | |
continue | |
else: | |
print("can't handle {}".format(ctype)) | |
f = open("GRCm38_ensembl2gencode.txt", "w") | |
for line in sorted(e2g): | |
f.write(line) | |
f.close() | |
f = open("GRCm38_gencode2ensembl.txt", "w") | |
for line in sorted(g2e): | |
f.write(line) | |
f.close() | |
f = open("GRCm38_UCSC2gencode.txt", "w") | |
for line in sorted(u2g): | |
f.write(line) | |
f.close() | |
f = open("GRCm38_UCSC2ensembl.txt", "w") | |
for line in sorted(u2e): | |
f.write(line) | |
f.close() | |
f = open("GRCm38_ensembl2UCSC.txt", "w") | |
for line in sorted(e2u): | |
f.write(line) | |
f.close() | |
f = open("GRCm38_gencode2UCSC.txt", "w") | |
for line in sorted(g2u): | |
f.write(line) | |
f.close() | |
ifile.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment