def Cufflinks_mask_GTF(assembly):
chromInfo = kent.fetch_ucsc_table(assembly, "chromInfo")
chrM_size = 0
masks = []
for line in chromInfo:
if not line.strip(): continue
line_split = line.strip().split("\t")
if line_split[0] == "chrM":
chrM_size = int(line_split[1])
masks.append(kent.fetch_ucsc_table(assembly, line_split[0] + "_rmsk"))
masks.append(kent.fetch_ucsc_table(assembly, "rmsk"))
rmsk = sum(masks, [])
del masks
output = []
maskid = 0
rmsk.append("\t".join(["."] * 5 + \
["real_chrM", "0", str(chrM_size),
".", "+", ".", "rRNA"]))
rmsk.append("\t".join(["."] * 5 + \
["real_chrM", "0", str(chrM_size),
".", "-", ".", "rRNA"]))
for line in rmsk:
if not line.strip(): continue
line_split = line.strip().split("\t")
if line_split[11] not in ("tRNA", "rRNA"): continue
if line_split[5] == "chrM": continue
if line_split[5] == "real_chrM":
line_split[5] = "chrM"
maskid += 1
GTF_line = [line_split[5],
"rmsk",
"exon",
line_split[6],
line_split[7],
"0.000000",
line_split[9],
".",
"gene_id \"MASK%06d\"; transcript_id \"MASK%06d\";" % (maskid, maskid)]
output.append("\t".join(GTF_line))
return output
def Cufflinks_mask_GTF(assembly):
chromInfo = kent.fetch_ucsc_table(assembly, "chromInfo")
chrM_size = 0
masks = []
for line in chromInfo:
if not line.strip(): continue
line_split = line.strip().split("\t")
if line_split[0] == "chrM":
chrM_size = int(line_split[1])
masks.append(kent.fetch_ucsc_table(assembly, line_split[0] + "_rmsk"))
masks.append(kent.fetch_ucsc_table(assembly, "rmsk"))
rmsk = sum(masks, [])
del masks
output = []
maskid = 0
rmsk.append("\t".join(["."] * 5 + \
["real_chrM", "0", str(chrM_size),
".", "+", ".", "rRNA"]))
rmsk.append("\t".join(["."] * 5 + \
["real_chrM", "0", str(chrM_size),
".", "-", ".", "rRNA"]))
for line in rmsk:
if not line.strip(): continue
line_split = line.strip().split("\t")
if line_split[11] not in ("tRNA", "rRNA"): continue
if line_split[5] == "chrM": continue
if line_split[5] == "real_chrM":
line_split[5] = "chrM"
maskid += 1
GTF_line = [
line_split[5], "rmsk", "exon", line_split[6], line_split[7],
"0.000000", line_split[9], ".",
"gene_id \"MASK%06d\"; transcript_id \"MASK%06d\";" %
(maskid, maskid)
]
output.append("\t".join(GTF_line))
return output
def Cufflinks_knownGene_GTF(assembly):
kgXref = kent.fetch_ucsc_table(assembly, "kgXref")
knownIsoforms = kent.fetch_ucsc_table(assembly, "knownIsoforms")
knownGene = kent.fetch_ucsc_gtf(assembly, "knownGene")
ucscid_to_xref = {}
for line in kgXref:
if line.startswith("#"): continue
line_split = line.strip().split("\t")
ucscid_to_xref[line_split[0]] = {
"mRNA": line_split[1],
"gene_symbol": line_split[4],
"protein_id": line_split[6]
}
ucscid_to_clusterid = {}
for line in knownIsoforms:
if line.startswith("#"): continue
line_split = line.strip().split("\t")
ucscid_to_clusterid[line_split[1]] = int(line_split[0])
output = []
for line in knownGene:
if not line.strip(): continue
line_split = line.strip().split("\t", 8)
ucscid = line_split[8].split("\"")[1]
xref = ucscid_to_xref[ucscid]
clusterid = ucscid_to_clusterid[ucscid]
line = "\t".join(line_split[:8]) + "\t" + \
" ".join(["gene_id \"CLUST%05d\";" % clusterid,
"transcript_id \"%s\";" % ucscid,
"gene_name \"%s\";" % xref["gene_symbol"],
"transcript_name \"%s\";" % xref["mRNA"],
"protein_id \"%s\";" % xref["protein_id"] if xref["protein_id"] != "" else ""])
output.append(line)
return output
def Cufflinks_knownGene_GTF(assembly):
kgXref = kent.fetch_ucsc_table(assembly, "kgXref")
knownIsoforms = kent.fetch_ucsc_table(assembly, "knownIsoforms")
knownGene = kent.fetch_ucsc_gtf(assembly, "knownGene")
ucscid_to_xref = {}
for line in kgXref:
if line.startswith("#"): continue
line_split = line.strip().split("\t")
ucscid_to_xref[line_split[0]] = {"mRNA": line_split[1],
"gene_symbol": line_split[4],
"protein_id": line_split[6]}
ucscid_to_clusterid = {}
for line in knownIsoforms:
if line.startswith("#"): continue
line_split = line.strip().split("\t")
ucscid_to_clusterid[line_split[1]] = int(line_split[0])
output = []
for line in knownGene:
if not line.strip(): continue
line_split = line.strip().split("\t", 8)
ucscid = line_split[8].split("\"")[1]
xref = ucscid_to_xref[ucscid]
clusterid = ucscid_to_clusterid[ucscid]
line = "\t".join(line_split[:8]) + "\t" + \
" ".join(["gene_id \"CLUST%05d\";" % clusterid,
"transcript_id \"%s\";" % ucscid,
"gene_name \"%s\";" % xref["gene_symbol"],
"transcript_name \"%s\";" % xref["mRNA"],
"protein_id \"%s\";" % xref["protein_id"] if xref["protein_id"] != "" else ""])
output.append(line)
return output
