def AnnotateSingleAb(self,inSeqID, inProteinSeq,inDNAseq):
if not inProteinSeq and not inDNAseq:
return ""
#initiate the FR1,CDR1,FR2,CDR2,FR3,CDR3,FR4 to emtry, just in case any can't be found
self._dict[inSeqID].update({'FR1-PRO':"",'CDR1-PRO':'','FR2-PRO':'','CDR2-PRO':'',"FR3-PRO":'','CDR3-PRO':'','FR4-PRO':'','FV-PRO':''})
self._dict[inSeqID].update({'FR1-DNA':"",'CDR1-DNA':'','FR2-DNA':'','CDR2-DNA':'',"FR3-DNA":'','CDR3-DNA':'','FR4-DNA':'','FV-DNA':''})
count_missing_fragment =0
for x in ("FR1","CDR1","FR2",'CDR2','FR3','CDR3'):
try:
#pdb.set_trace()
dna_frag= inDNAseq[self._dict[inSeqID][x+"head_pos"]-1:self._dict[inSeqID][x+'tail_pos']]
#print "DNA_frag : " + dna_frag
#print "PRO_Frag : " + translator.translate_dna_single(dna_frag)
self._dict[inSeqID].update({x+'-DNA': dna_frag})
self._dict[inSeqID].update({x+'-PRO':translator.translate_dna_single(dna_frag)})
except:
print "IgBlastn couldn't find: "+ inSeqID + ':' + x
count_missing_fragment += 1
if count_missing_fragment > 2:
print "Warining! missing the some fragmentation from IgBlastn in this sequence:"
print inDNAseq
return
FR1head=self.find_high_PMW_score(self._pwmFR1head,inProteinSeq)
FR1head_pos=inProteinSeq.find(FR1head)
#print "start to find FR2"
try :
FR1tail_pos=self._dict[inSeqID]["FR1tail_pos"]/3 -1
except:
FR1tail=self.find_high_PMW_score(self._pwmFR1tail,inProteinSeq[FR1head_pos:])
FR1tail_pos=inProteinSeq.find(FR1tail)+len(FR1tail)-1
new_FR1protein=inProteinSeq[FR1head_pos:FR1tail_pos+1]
new_FR1dna= translator.convertPROtoDNA(inDNAseq,FR1head_pos,FR1tail_pos+1)
if len(new_FR1dna)>=len(self._dict[inSeqID]['FR1-DNA']):
self._dict[inSeqID].update({'FR1-PRO':new_FR1protein})
self._dict[inSeqID].update({'FR1-DNA':new_FR1dna})
'''
try:
FR2head=self.find_high_PMW_score(self._pwmFR2head,inProteinSeq[FR1tail_pos:])
FR2head_pos=inProteinSeq.find(FR2head)
self._dict[inSeqID].update({'CDR1-PRO':inProteinSeq[FR1tail_pos+1:FR2head_pos]})
self._dict[inSeqID].update({'CDR1-DNA':translator.convertPROtoDNA(inDNAseq,FR1tail_pos+1,FR2head_pos)})
except:
return
'''
try :
FR2head_pos=(self._dict[inSeqID]["FR2head_pos"]-1)/3
except:
FR2head=self.find_high_PMW_score(self._pwmFR2head,inProteinSeq[FR1tail_pos:])
FR2head_pos=inProteinSeq.find(FR2head)
if self._dict[inSeqID]["FR2-DNA"] !='':
pass
elif FR1tail_pos and FR2head_pos :
self._dict[inSeqID].update({'CDR1-PRO':inProteinSeq[FR1tail_pos+1:FR2head_pos]})
self._dict[inSeqID].update({'CDR1-DNA':translator.convertPROtoDNA(inDNAseq,FR1tail_pos+1,FR2head_pos)})
try :
FR2tail_pos= (self._dict[inSeqID]["CDR2head_pos"]-1)/3 -1
except:
FR2tail=self.find_high_PMW_score(self._pwmFR2tail,inProteinSeq[FR2head_pos:])
FR2tail_pos=inProteinSeq.find(FR2tail)+len(FR2tail)-1
if self._dict[inSeqID]["FR2-DNA"] != '' :
pass
elif FR2head_pos and FR2tail_pos:
self._dict[inSeqID].update({'FR2-PRO':inProteinSeq[FR2head_pos:FR2tail_pos+1]})
self._dict[inSeqID].update({'FR2-DNA':translator.convertPROtoDNA(inDNAseq,FR2head_pos,FR2tail_pos+1)})
#print "FR2 tail:" + FR2tail
#print FR2tail_pos
try :
FR3head_pos= (self._dict[inSeqID]["FR3head_pos"]-1)/3 -1
except:
FR3head=self.find_high_PMW_score(self._pwmFR3head,inProteinSeq[FR2tail_pos:])
FR3head_pos=inProteinSeq.find(FR3head)
if self._dict[inSeqID]["CDR2-DNA"] !='' :
pass
elif FR2tail_pos and FR3head :
self._dict[inSeqID].update({'CDR2-PRO':inProteinSeq[FR2tail_pos+1:FR3head_pos]})
self._dict[inSeqID].update({'CDR2-DNA':translator.convertPROtoDNA(inDNAseq,FR2tail_pos+1,FR3head_pos)})
#print "FR3head :" + FR3head
#print FR3head_pos
try:
FR3tail_pos= (self._dict[inSeqID]["CDR3head_pos"]-1)/3 -1
except:
FR3tail=self.find_high_PMW_score(self._pwmFR3tail,inProteinSeq[FR3head_pos:])
FR3tail_pos=inProteinSeq.find(FR3tail)+len(FR3tail)-1
if self._dict[inSeqID]["FR3-DNA"] !='' !='':
pass
elif FR3head_pos and FR3tail_pos :
#new_FR3protein= inProteinSeq[FR3head_pos:FR3tail_pos]
#new_FR3dna = translator.convertPROtoDNA(inDNAseq,,FR3head_pos, FR3tail_pos])
self._dict[inSeqID].update({'FR3-PRO':inProteinSeq[FR3head_pos:FR3tail_pos+1]})
self._dict[inSeqID].update({'FR3-DNA':translator.convertPROtoDNA(inDNAseq,FR3head_pos,FR3tail_pos+1)})
try:
FR4head_pos = self._dict[inSeqID]["CD3tail_pos"]/3
except:
FR4head=self.find_high_PMW_score(self._pwmFR4head,inProteinSeq[FR3tail_pos:])
FR4head_pos=inProteinSeq.find(FR4head)
new_CDR3protein= inProteinSeq[FR3tail_pos+1:FR4head_pos]
new_FR3dna= translator.convertPROtoDNA(inDNAseq,FR3tail_pos+1,FR4head_pos)
if FR3tail_pos and FR4head_pos and len(new_FR3dna)> len(self._dict[inSeqID]["CDR3-DNA"]):
self._dict[inSeqID].update({'CDR3-PRO':inProteinSeq[FR3tail_pos+1:FR4head_pos]})
self._dict[inSeqID].update({'CDR3-DNA':translator.convertPROtoDNA(inDNAseq,FR3tail_pos+1,FR4head_pos)})
#pdb.set_trace()
FR4tail=self.find_high_PMW_score(self._pwmFR4head,inProteinSeq[FR3tail_pos:])
FR4tail_pos=inProteinSeq.find(FR4tail)+len(FR4tail)-1
if FR4head and FR4tail:
self._dict[inSeqID].update({'FR4-PRO':inProteinSeq[FR4head_pos:FR4tail_pos+1]})
self._dict[inSeqID].update({'FR4-DNA':translator.convertPROtoDNA(inDNAseq,FR4head_pos,FR4tail_pos+1)})
elif FR4head:
self._dict[inSeqID].update({'FR4-PRO':FR4head})
self._dict[inSeqID].update({'FR4-DNA':translator.convertPROtoDNA(inDNAseq,FR4head_pos,len(inProteinSeq))})
else:
self._dict[inSeqID].update({'FR4-PRO':''})
self._dict[inSeqID].update({'FR4-DNA':''})
FVpro =self._dict[inSeqID]["FR1-PRO"]+self._dict[inSeqID]["CDR1-PRO"]+self._dict[inSeqID]["FR2-PRO"]+self._dict[inSeqID]["CDR2-PRO"]+self._dict[inSeqID]["FR3-PRO"]+self._dict[inSeqID]["CDR3-PRO"]+self._dict[inSeqID]["FR4-PRO"]
self._dict[inSeqID].update({'FV-PRO': FVpro })
FVdna=self._dict[inSeqID]["FR1-DNA"]+self._dict[inSeqID]["CDR1-DNA"]+self._dict[inSeqID]["FR2-DNA"]+self._dict[inSeqID]["CDR2-DNA"]+self._dict[inSeqID]["FR3-DNA"]+self._dict[inSeqID]["CDR3-DNA"]+self._dict[inSeqID]["FR4-DNA"]
self._dict[inSeqID].update({'FV-DNA':FVdna})
uniqList.append(tmpList)
return uniqList
elemName=''
elemDNA=''
elemList=[]
for line in Infile1:
line = line.strip('\n')
if line.strip():
if (line.startswith(">") ):
line=line.lstrip('>')
sense_DNA=truncate(elemDNA)
if len(sense_DNA)<1:
sense_DNA=truncate(translator.reverse_complement(elemDNA))
if elemName:
output=[elemName,sense_DNA,translator.translate_dna_single(sense_DNA)]
elemList.append(output)
#add function to search for patten
elemName=line
elemDNA=""
else:
elemDNA=elemDNA+line
else:
sense_DNA=truncate(elemDNA)
if len(sense_DNA)<1:
sense_DNA=truncate(translator.reverse_complement(elemDNA))
output=[elemName,sense_DNA,translator.translate_dna_single(sense_DNA)]
elemList.append(output)
pos5=elemDNA.find(prime5)
pos3=elemDNA.find(prime3)+len(prime3)
return elemDNA[pos5:pos3]
elemName=""
elemDNA=""
for line in Infile1:
line = line.strip('\n')
if line.strip():
if (line.startswith(">") ):
line=line.lstrip('>')
elemDNA=truncate(elemDNA)
if elemName:
output=elemName+","+elemDNA+","+translator.translate_dna_single(elemDNA)+"\n"
Outfile1.write(output)
#add function to search for patten
elemName=line
elemDNA=""
else:
elemDNA=elemDNA+line
else:
elemDNA=truncate(elemDNA)
output=elemName+","+elemDNA+","+translator.translate_dna_single(elemDNA)+"\n"
Outfile1.write(output)
Infile1.close()
Outfile1.close()
