tog2 = open(gtffn + ".downstream_introns", 'w')
else:
fivesfn = gtffn + ".fives.%s_%s.fasta" % (offset[0], offset[1])
threesfn = gtffn + ".threes.%s_%s.fasta" % (offset[2], offset[3])
f5 = open(fivesfn, 'w')
f3 = open(threesfn, 'w')
for pieces in junctions:
if get_introns:
seqs = list()
for p in pieces:
if p[:3] == "chr": q = p[3:-2]
else: q = p[:-2]
seq = fastafile.fetch(region=q)
if p[-1] == '-':
seq = complementDNA(seq[::-1])
seqs += [seq]
else:
five, three = pieces
A = fastafile.fetch(region=five)
B = fastafile.fetch(region=three)
if five[-1] == '-':
A = complementDNA(A[::-1]) # reverse the string
if three[-1] == '-':
B = complementDNA(B[::-1])
if get_introns:
u5, u3, d5, d3 = pieces
print >> tog1, "\t".join(
[u5, u3] + [seqs[0][:offset[0]] + seqs[0][offset[0]:].lower()] +
[seqs[1][:offset[2]].lower() + seqs[1][offset[2]:]])
except IndexError:
print >> sys.stderr, "Usage: script.py <exon_fn> <gene_fn> <tabix_fn>"
sys.exit(0)
fastafile = pysam.Fastafile(fasta_fn)
keys = dict()
f = open(exon_fn)
for row in f:
keys[tuple(row.strip().split(':'))] = []
f.close()
f = open(gene_fn)
c = 0
for row in f:
if c > 5: break
l = row.strip().split('\t')
sd = l[5]
if (l[0], l[1]) in keys:
coord = l[2] + ":" + l[3] + "-" + l[4]
results = fastafile.fetch(region=coord)
print ">%s" % coord + ":" + sd
if sd == '+':
print results
elif sd == '-':
print complementDNA(results)[::-1]
c += 0
f.close()
fastafile.close()
#!/home/paulk/software/bin/python
from __future__ import division
from sys import argv,exit,stderr
import pysam
from key_functions import complementDNA
fastafile = pysam.Fastafile("resources/refs/hg19/Homo_sapiens.GRCh37.66.dna.fa")
f = open("u12_introns_all_norm_ps_details.txt")
for row in f:
if row[0] == 'i': continue
l = row.strip().split('\t')
c1 = map(str,[l[8][3:],int(l[11]),int(l[11])+1])
c2 = map(str,[l[8][3:],int(l[12])-1,int(l[12])])
reg1 = c1[0]+":"+c1[1]+"-"+c1[2]
reg2 = c2[0]+":"+c2[1]+"-"+c2[2]
if l[-6] == "U12-U2":
print l[4],
if l[14] == '-':
print complementDNA(fastafile.fetch(region=reg2))[::-1]+"-"+complementDNA(fastafile.fetch(region=reg1))[::-1]
else:
print fastafile.fetch(region=reg1)+"-"+fastafile.fetch(region=reg2)
f.close()
tog2 = open(gtffn+".downstream_introns",'w') else: fivesfn = gtffn+".fives.%s_%s.fasta"%(offset[0],offset[1]) threesfn = gtffn+".threes.%s_%s.fasta"%(offset[2],offset[3]) f5 = open(fivesfn,'w') f3 = open(threesfn,'w') for pieces in junctions: if get_introns: seqs = list() for p in pieces: if p[:3] == "chr": q = p[3:-2] else: q = p[:-2] seq = fastafile.fetch(region=q) if p[-1] == '-': seq = complementDNA(seq[::-1]) seqs += [seq] else: five,three = pieces A = fastafile.fetch(region=five) B = fastafile.fetch(region=three) if five[-1] == '-': A = complementDNA(A[::-1]) # reverse the string if three[-1] == '-': B = complementDNA(B[::-1]) if get_introns: u5,u3,d5,d3 = pieces print >> tog1,"\t".join([u5,u3]+[seqs[0][:offset[0]]+seqs[0][offset[0]:].lower()]+[seqs[1][:offset[2]].lower()+seqs[1][offset[2]:]]) print >> tog2,"\t".join([d5,d3]+[seqs[2][:offset[0]]+seqs[2][offset[0]:].lower()]+[seqs[3][:offset[2]].lower()+seqs[3][offset[2]:]]) else:
#!/home/paulk/software/bin/python
from __future__ import division
from sys import argv, exit, stderr
import pysam
from key_functions import complementDNA
fastafile = pysam.Fastafile(
"resources/refs/hg19/Homo_sapiens.GRCh37.66.dna.fa")
f = open("u12_introns_all_norm_ps_details.txt")
for row in f:
if row[0] == 'i': continue
l = row.strip().split('\t')
c1 = map(str, [l[8][3:], int(l[11]), int(l[11]) + 1])
c2 = map(str, [l[8][3:], int(l[12]) - 1, int(l[12])])
reg1 = c1[0] + ":" + c1[1] + "-" + c1[2]
reg2 = c2[0] + ":" + c2[1] + "-" + c2[2]
if l[-6] == "U12-U2":
print l[4],
if l[14] == '-':
print complementDNA(
fastafile.fetch(region=reg2))[::-1] + "-" + complementDNA(
fastafile.fetch(region=reg1))[::-1]
else:
print fastafile.fetch(region=reg1) + "-" + fastafile.fetch(
region=reg2)
f.close()
except IndexError:
print >> sys.stderr,"Usage: script.py <exon_fn> <gene_fn> <tabix_fn>"
sys.exit(0)
fastafile = pysam.Fastafile(fasta_fn)
keys = dict()
f = open(exon_fn)
for row in f:
keys[tuple(row.strip().split(':'))] = []
f.close()
f = open(gene_fn)
c = 0
for row in f:
if c > 5: break
l = row.strip().split('\t')
sd = l[5]
if (l[0],l[1]) in keys:
coord = l[2]+":"+l[3]+"-"+l[4]
results = fastafile.fetch(region=coord)
print ">%s" % coord+":"+sd
if sd == '+':
print results
elif sd == '-':
print complementDNA(results)[::-1]
c += 0
f.close()
fastafile.close()