def main():
num = 0
file = sys.argv[1]
set = 0
for line in open(file,'r'):
genename = file.split('.')[0]
if line[:13] == "Primer Pair: " :
set += 1
prim = {}
prim['f'] = []
prim['r'] = []
num += 1
spl = line.strip().split("revOligo")
for i in range(0,len(spl)):
oli = spl[i].split("seq=")
snum = 0
for j in range(1,len(oli)):
snum += 1
oneoli = oli[j].split("}")
if( i == 0):
#print ">F:"+file+"_"+str(num)+"_"+str(snum)
prim['f'].append(oneoli[0])
else:
#print ">R:"+file+"_"+str(num)+"_"+str(snum)
prim['r'].append(oneoli[0])
#print oneoli[0]
#print prim
for i in range(0,len(prim['f'])):
r = reverse_complement.get_rc(prim['r'][i])
print genename+"\t"+str(set)+"_"+str(i+1)+"\t"+prim['f'][i]+"\t"+ r
def get_target(fpri, rpri, ori):
target = ""
rev = reverse_complement.get_rc(rpri)
for item in ori.items():
if fpri in item[1] and rev in item[1]:
target = item[1]
return target
def get_primers(i, con, iter, rc):
k = 1
fprim = []
rprim = []
fp = []
rp = []
for j in range(0, iter * 2 + 1):
line = con[i + j]
if line[2:25] == "Primer Pair: PrimerPair" or line[3:26] == "Primer Pair: PrimerPair":
spl = line.split("Oligo{seq=")
loc = line.split("[")[1].split(", ")
fp.append(loc[0])
rp.append(loc[1].split("]")[0])
fw = spl[1].split("}")[0]
rev = spl[2].split("}")[0]
if rc == 1:
revrc = reverse_complement.get_rc(rev)
else:
revrc = rev
fprim.append(fw)
rprim.append(revrc)
k += 1
elif line.strip() == "":
break
return fprim, rprim, fp, rp
def get_target(tempseq,fprimer,rprimer):
seq = ''.join(tempseq)
rprimer = reverse_complement.get_rc(rprimer)
if(fprimer in seq and rprimer in seq and seq.find(fprimer) < seq.find(rprimer)):
return 1
else:
return 0
def read_trad_primer(filename):
fpri = []
rpri = []
flag = 0
for line in open(filename, "r"):
if line.strip() == "":
continue
if line[:2] == ">F":
flag = 0
elif line[:2] == ">R":
flag = 1
else:
if flag == 0:
fpri.append(line.strip())
else:
seq = reverse_complement.get_rc(line.strip())
rpri.append(seq)
return fpri, rpri
def show_list(gene,target,map,match):
org = map[target]
prod = []
for item in match.items():
if(target in item[0]):
prod = item[1]
for x in prod:
spl = x.split(' ')
fpri = spl[0]
rpri = ''
exp = spl[2]
if(sys.argv[4] == "truseq"):
rpri = reverse_complement.get_rc(spl[1])
else:
rpri = spl[1]
if(int(exp) > 200):
result = [gene,org,fpri,rpri,exp]
print '\t'.join(result)
def get_primers(i,con,iter,fname,rc):
k=1
for j in range(0,iter*2+1):
line = con[i+j]
if (line[2:14]=="Primer Pair:"):
spl = line.split("Oligo{seq=")
fw = spl[1].split('}')[0]
rev = spl[2].split('}')[0]
if (rc == 1):
revrc = reverse_complement.get_rc(rev)
else:
revrc = rev
print ">F:"+fname.split('.')[0]+'_'+str(k)
print fw
print ">R:"+fname.split('.')[0]+'_'+str(k)
print revrc
k += 1
elif(line.strip() == ""):
break
def read_primer(file):
prim = open(file,'r')
swi = 0
fpri = {}
rpri = {}
name = ""
for line in prim:
if(line[:1] == ">"):
name = line.strip()[1:]
else:
seq = line.strip()
rseq = reverse_complement.get_rc(seq)
if fpri.has_key(seq):
temp = fpri[seq] + ','+name
fpri[seq] = temp
temp = rpri[rseq] + ',' +name
rpri[rseq] = temp
else:
fpri[seq] = name
rpri[rseq] = name
prim.close()
return fpri,rpri
def main():
min = 200
max = 370
#parameters that used
mis = 0
#read primer
fpri, rpri = utils.read_trad_primer(sys.argv[1])
lfile = sys.argv[2]
num = 0
seq = utils.read_fasta(sys.argv[2])
for item in seq.items():
se = item[1]
for f in fpri:
for i in range(0, len(se)-len(f)):
str1 = se[i:len(f)+i]
#print str1, f
#print mismatch(str1,f,mis)
if mismatch(str1,f,mis):
#print "match"
num += 1
output = ">F:"+lfile+"_"+str(num)+"\n"+f+'\n'
#print output
#print ">F:",f, i
for r in rpri:
rp = r
for j in range(0, len(se)-len(rp)):
str2 = se[j:len(rp)+j]
if mismatch(str2,rp,mis):
#print "match"
frp = reverse_complement.get_rc(rp)
#print ">R:",frp,j+len(rp), j+len(rp)-i
flen = j+len(rp)-i
#print flen
if(flen >min and flen<max):
output = output + ">R:"+lfile+"_"+str(num)+"\n"+frp+'\n'
print output
def get_product(fpri,rpri,se,name):
product = ''
psize = 0
pfpri = ''
prpri = ''
for x in fpri.items():
ma = [m.start() for m in re.finditer(x[0], se)]
if len(ma) > 0:
for st in ma:
tempseq = se[st:st+400]
for y in rpri.items():
rma = [m.start() for m in re.finditer(y[0],tempseq)]
if len(rma) > 0 :
for rst in rma:
product = tempseq[:rst+len(y[0])]
psize = len(product)
pfpri = x[0]
prpri = y[0]
print ">%s %s(%s) %s %s(%s) %s %s\n%s" %(name, pfpri,fpri[pfpri],st, reverse_complement.get_rc(prpri),rpri[prpri],st+rst+len(y[0]),len(product), product)
return 0
import sys
import reverse_complement
for line in open(sys.argv[1],'r'):
if(line[:1]==">"):
print line.strip()+"_rc"
else:
rc = reverse_complement.get_rc(line.strip())
print rc
#!/usr/bin/python
import sys
sys.path.append('./utils')
import reverse_complement
seq = "ATGCTat"
print seq
print reverse_complement.get_rc(seq)
seq_url = ">name\nATGTatn"
print seq_url
print reverse_complement.get_from_url(seq_url)