def __init__(self, pairQ2, overlap_baseNumber=10):
self._merged = []
self._fastQ1 = pairQ2[0]
self._fastQ2 = translator.reverse_complement_FastQ(
pairQ2[1]) # from now on, fastQ are sense strand
self._overlapNumber = overlap_baseNumber
self._assemble_seq = ""
def concentrate2single(infilepath,outputfilename): #also reverse translate
#combinedfile_name = os.path.basename(infilepath)
raw_single_fasta_name =outputfilename.rstrip('.fastq')+'.fasta'
raw_single_fasta_file = open(raw_single_fasta_name, 'wb')
all_fastq = {}
count_file =0
#combinedfile_name =os.path.join(outputfilename,combinedfile_name+'.fastq')
combinedfile_name = outputfilename
print "concentrate2single name is" +combinedfile_name
combinedfile = open(combinedfile_name , 'wb')
print outputfilename
for filename in os.listdir(infilepath):
single_fastq = []
flag_reverse = False
if filename.endswith('.fastq'):
seq_name = filename.split(';')[0]
with open(os.path.join(infilepath,filename)) as f:
for row in f:
row = row.strip('\n')
if row.startswith("@"):
fasta_output = '\n>'+row.lstrip('@')+'\n'
# row = row.split(";")
if "QB6179" in row or "QB5506" in row or 'QB6178' in row or 'Rev' in row or 'rev' in row:
flag_reverse = True
IDs=re.search('\D(\d{4})\D',row) ###### Extract 4 numbers , return
ID=IDs.group(0) #####
#row= row[0]+"\n"
#print ID
row = "@"+ID
#ID=str(ID) +'\n'
combinedfile.write(row+'\n')
single_fastq.append(row.lstrip('@'))
single_fastq[-1] = covert_Qscore(single_fastq[-1])
fasta_output +=single_fastq[1] + '\n'
raw_single_fasta_file.write(fasta_output)
if flag_reverse == True:
try:
single_fastq =translator.reverse_complement_FastQ(single_fastq)
except:
print single_fastq
all_fastq[ID] = all_fastq.get(ID, [])
all_fastq[ID].append(single_fastq)
f.close()
combinedfile.close()
print "All the fastqs were concentrated into a single file ------%s. And the ID was extracted." +combinedfile_name
return all_fastq
def anneal_1direction(self, inputfastq1, inputfastq2):
print "$$$$$$"
print inputfastq1
print inputfastq2
firstSeq = inputfastq1[1]
secondSeq = inputfastq2[1]
fastQ1 = inputfastq1
fastQ2 = inputfastq2
print len(fastQ1[1])
print len(fastQ2[1])
if not firstSeq and not secondSeq:
print " firstSeq and not secondSeq empty"
return ' '
elif not firstSeq or len(
firstSeq) <= self._overlapNumber or firstSeq in secondSeq:
print "lif not firstSeq or len(firstSeq) <= self._overlapNumber"
return secondSeq
elif not secondSeq or len(
secondSeq) <= self._overlapNumber or secondSeq in firstSeq:
print "firtseq> 2"
return firstSeq
couple_list = []
print "-------- caculate assemb1--------"
(overlap_seq1, assembleSeq1) = self.find_overlap(fastQ1, fastQ2)
couple_list.append((overlap_seq1, assembleSeq1))
print "-------- caculate assemb2--------"
(overlap_seq2, assembleSeq2) = self.find_overlap(fastQ2, fastQ1)
couple_list.append((overlap_seq2, assembleSeq2))
print "-------- caculate assemb3--------"
antiSense_fastQ2 = translator.reverse_complement_FastQ(inputfastq2)
(overlap_seq3,
assembleSeq3) = self.find_overlap(fastQ1, antiSense_fastQ2)
couple_list.append((overlap_seq3, assembleSeq3))
longest_overlap = ('', '')
print couple_list
for tmp_couple in couple_list:
if len(tmp_couple[0]) > len(longest_overlap):
longest_overlap = tmp_couple
assembled_fasta = longest_overlap[1]
print "assembled_fasta: " + assembled_fasta
self._assemble_seq = assembled_fasta
return assembled_fasta
def anneal2fastq(self):
#print "$$$$$$"
couple_list = []
#for cut_off in [15, 20, 25, 30, 35, 40]:
fastQ1 = self._fastQ1
fastQ2 = self._fastQ2
firstSeq = fastQ1[1]
secondSeq = fastQ2[1]
for cut_off in [15, 20, 25, 30, 35, 40]:
object1 = TrimEnds.TrimEnds(fastQ1)
object1.trimEnds(minimum_quality=cut_off)
fastQ1 = object1.output_trimed_fastq()
firstSeq = fastQ1[1]
if not firstSeq and not secondSeq:
print " firstSeq and not secondSeq empty"
couple_list.append(('', '', 0))
continue
elif not firstSeq or len(
firstSeq) <= self._overlapNumber or firstSeq in secondSeq:
print "lif not firstSeq or len(firstSeq) <= self._overlapNumber"
couple_list.append((secondSeq, secondSeq, 0))
continue
elif not secondSeq or len(
secondSeq) <= self._overlapNumber or secondSeq in firstSeq:
print "firtseq> 2"
couple_list.append((firstSeq, firstSeq, 0))
continue
#print "-------- caculate assemb1--------"
(overlap_seq1, assembleSeq1,
mismatch1) = self.find_overlap(fastQ1, fastQ2, cut_off)
couple_list.append((overlap_seq1, assembleSeq1, mismatch1))
#print "-------- caculate assemb2--------"
(overlap_seq2, assembleSeq2,
mismatch2) = self.find_overlap(fastQ2, fastQ1, cut_off)
couple_list.append((overlap_seq2, assembleSeq2, mismatch2))
#print "-------- caculate assemb3--------"
antiSense_fastQ2 = translator.reverse_complement_FastQ(fastQ2)
(overlap_seq3, assembleSeq3,
mismatch3) = self.find_overlap(fastQ1, antiSense_fastQ2, cut_off)
couple_list.append((overlap_seq3, assembleSeq3, mismatch3))
#print "-------- caculate assemb4 reverse both A and B--------"
antiSense_fastQ1 = translator.reverse_complement_FastQ(fastQ1)
(overlap_seq4, assembleSeq4,
mismatch4) = self.find_overlap(antiSense_fastQ2, antiSense_fastQ1,
cut_off)
couple_list.append((overlap_seq4, assembleSeq4, mismatch4))
#print "-------- caculate assemb5 reverse both A and B--------"
(overlap_seq5, assembleSeq5,
mismatch5) = self.find_overlap(antiSense_fastQ1, antiSense_fastQ2,
cut_off)
couple_list.append((overlap_seq5, assembleSeq5, mismatch5))
longest_overlap = ('', '', 0)
#print couple_list
for tmp_couple in couple_list:
if len(tmp_couple[0]) > 200 and len(tmp_couple[1]) > len(
longest_overlap[1]):
longest_overlap = tmp_couple
'''
if longest_overlap[0] ==0:
better_fastq =['','','','']
better_fastq = choose_one_read(self._fastQ1, self._fastQ2)
if better_fastq:
longest_overlap=('1',better_fastq[1],1)
'''
# if len(assembled_fasta) > 100:
# print "assembled_fasta: "+ assembled_fasta
self._overlap_seq = longest_overlap[0]
self._assemble_seq = longest_overlap[1]
self._mismatch_count = longest_overlap[2]
return
def anneal2fastq(self):
#print "$$$$$$"
couple_list = []
#for cut_off in [15, 20, 25, 30, 35, 40]:
for cut_off in [20]:
object1 = TrimEnds.TrimEnds(self._fastQ1)
object1.trimEnds(minimum_quality=cut_off)
fastQ1 = object1.output_trimed_fastq()
firstSeq = fastQ1[1]
object2 = TrimEnds.TrimEnds(self._fastQ2)
object2.trimEnds(minimum_quality=cut_off)
fastQ2 = object2.output_trimed_fastq()
secondSeq = fastQ2[1]
if not firstSeq and not secondSeq:
print " firstSeq and not secondSeq empty"
couple_list.append(('', ''))
continue
elif not firstSeq or len(
firstSeq) <= self._overlapNumber or firstSeq in secondSeq:
print "lif not firstSeq or len(firstSeq) <= self._overlapNumber"
couple_list.append((secondSeq, secondSeq))
continue
elif not secondSeq or len(
secondSeq) <= self._overlapNumber or secondSeq in firstSeq:
print "firtseq> 2"
couple_list.append((firstSeq, firstSeq))
continue
#print "-------- caculate assemb1--------"
(overlap_seq1, assembleSeq1) = self.find_overlap(fastQ1, fastQ2)
couple_list.append((overlap_seq1, assembleSeq1))
#print "-------- caculate assemb2--------"
(overlap_seq2, assembleSeq2) = self.find_overlap(fastQ2, fastQ1)
couple_list.append((overlap_seq2, assembleSeq2))
#print "-------- caculate assemb3--------"
antiSense_fastQ2 = translator.reverse_complement_FastQ(fastQ2)
(overlap_seq3,
assembleSeq3) = self.find_overlap(fastQ1, antiSense_fastQ2)
couple_list.append((overlap_seq3, assembleSeq3))
#print "-------- caculate assemb4 reverse both A and B--------"
antiSense_fastQ1 = translator.reverse_complement_FastQ(fastQ1)
(overlap_seq4,
assembleSeq4) = self.find_overlap(antiSense_fastQ2,
antiSense_fastQ1)
couple_list.append((overlap_seq4, assembleSeq4))
#print "-------- caculate assemb5 reverse both A and B--------"
(overlap_seq5,
assembleSeq5) = self.find_overlap(antiSense_fastQ1,
antiSense_fastQ2)
couple_list.append((overlap_seq5, assembleSeq5))
longest_overlap = ('', '')
print couple_list
for tmp_couple in couple_list:
if len(tmp_couple[0]) > 200 and len(tmp_couple[1]) > len(
longest_overlap[1]):
longest_overlap = tmp_couple
assembled_fasta = longest_overlap[1]
# if len(assembled_fasta) > 100:
# print "assembled_fasta: "+ assembled_fasta
self._assemble_seq = assembled_fasta
return