def init():
def get_scaf2seqid():
#return secf2seqid dict
#needs ygap_corr file
scaf2seqid = {}
f = open(ygap_corr)
for line in f:
scaf,seqid,chrname = line.split("\t")
scaf = scaf.split("_")[-1]
scaf2seqid[scaf] = seqid
return scaf2seqid
#generate blast compare file
scaf2seqid = get_scaf2seqid()
if REF:
refs = []
dubious = []
for record in gff_parse.gffIterator(Ref_anno):
if record.type == "gene" and record.attributes["orf_classification"][0] == "Dubious":
dubious.append(record.attributes["ID"][0])
elif record.type == "gene" and not record.attributes["ID"][0].startswith("Q"):
seqid = record.seqid
start = int(record.start)
end = int(record.end)
record.id = record.attributes["ID"][0]
if record.strand == "+":
record.coord = "(%d..%d)"%(start,end)
record.seq = Ref_seq[seqid][start-1:end]
elif record.strand == "-":
record.coord = "complement(%d..%d)"%(start,end)
record.seq = Ref_seq[seqid][start-1:end].reverse_complement()
else:
print "Check strand:%s"%record.type
refs.append(record)
ygap = []
for record in YGAPIterator(ygap_anno):
if record.type == "PROTEIN" or record.type == "":
seqid = int(record.seqid)
start = int(record.start)
end = int(record.end)
if record.strand == "+":
record.seq = ygap_seq[seqid][start-1:end]
elif record.strand == "-":
record.seq = ygap_seq[seqid][start-1:end].reverse_complement()
else:
print "Check strand:%s"%record.type
ygap.append(record)
devin = []
for record in gff_parse.gffIterator(devin_gff):
if record.type == "CDS" or record.type == "ORF":
if REF:
#exclude dubious genes
flag = False
for h**o in record.attributes["SGD"]:
if h**o in dubious:
flag = True
if flag:
print "find %s is %s "%(record.attributes["Gene"],h**o)
continue
seqid = int(record.seqid)
record.seqid = scaf2seqid[record.seqid]
start = int(record.start)
end = int(record.end)
record.orth = "%s_%s"%(record.score,"|".join(record.attributes["SGD"]))
if record.strand == "+":
record.coord = "(%d..%d)"%(start,end)
record.seq = devin_seq[seqid][start-1:end]
elif record.strand == "-":
record.coord = "complement(%d..%d)"%(start,end)
record.seq = devin_seq[seqid][start-1:end].reverse_complement()
else:
print "Check strand:%s"%record.type
devin.append(record)
if REF:
write_fsa(ygap,devin,refs)
else:
write_fsa(ygap,devin)
run_blast()
return 0
if line.startswith("#"): continue
if not line: return
r= record()
(r.name,r.strand,r.start,r.end,r.ygob,r.seqid,r.shortname,\
r.coord,r.orth,r.type,r.pillar,r.tag,r.anno) = line.split("\t")
r.strand = "+" if r.strand == "1" else "-"
yield r
class list(list):
def __init__(self):
self.name = ""
deven = list()
deven.name = "deven"
for record in gff_parse.gffIterator(deven_gff):
deven.append(record)
augustus = list()
augustus.name = "augustus"
for record in gff_parse.gffIterator(augustus_gff):
record.seqid = record.seqid[5:]
augustus.append(record)
ygap = list()
ygap.name = "ygap"
for record in YGAPIterator(ygap_anno):
ygap.append(record)
def compare_gff(template,*gffs):
temp = [read.seqid+"_"+read.start+"_"+read.end+"_"+read.strand for \
out_put_file = "/Users/bingwang/zen/yeast_anno_pipe/%sONscer.txt"%(sp)
#Prepare: numid2scaf dict
numid2scaf = {}
scaffold_list = []
f = open(correspondances_file)
for line in f:
scaffold,numid,alpheid = line.strip().split("\t")
numid2scaf[numid] = scaffold
scaffold_list.append(scaffold)
#Prepare: scer_genes synteny list
#Prepare: scer2record dict
scer_genes = []
scer2record = {}
for record in gff_parse.gffIterator(open(ref_file)):
if record.type == "gene" and record.attributes["orf_classification"][0] == "Dubious":
#dubious.append(record.attributes["ID"][0])
continue
elif record.type == "gene" and not record.attributes["ID"][0].startswith("Q"):
seqid = record.seqid
start = int(record.start)
end = int(record.end)
record.id = record.attributes["ID"][0]
scer_genes.append(record.id)
scer2record[record.id] = record
#Prepare: scer2seub and seub2scer dicts
#Prepare: seub2record dict
scer2seub = {}
seub2scer = {}