def write_clean_abundance_file(self):
"""
Writes the abundance file from the new names file and new unique file.
These files have already had their ids checked from the deleted file
"""
for lane_key in self.lane_keys:
original_abundance_file = os.path.join(self.trim_dir,
lane_key + ".abund.fa")
new_abundance_file = os.path.join(self.trim_dir,
lane_key + ".newabund.fa")
new_names_file = os.path.join(self.trim_dir, lane_key + ".names")
new_unique_file = os.path.join(self.trim_dir,
lane_key + ".unique.fa")
names = {}
uniques = {}
deleted_id_list = self.deleted_ids[lane_key]
if len(deleted_id_list) == 0:
continue
newnames_fh = open(new_names_file, "r")
for line in newnames_fh.readlines():
lst = line.strip().split()
names[lst[0]] = lst[1].split(',')
#print(names)
fasta = fa.SequenceSource(new_unique_file)
while fasta.next():
fasta.id
uniques[fasta.seq] = fasta.id
#print(uniques)
sorted_uniques = mysort(uniques, names)
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size=" + str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(new_abundance_file, 'a')
# rename to newuniques => uniques
os.rename(
original_abundance_file,
os.path.join(self.trim_dir, lane_key + ".abund_dirty.fa"))
os.rename(new_abundance_file, original_abundance_file)
def write_clean_abundance_file(self):
"""
Writes the abundance file from the new names file and new unique file.
Thes file have already had their ids checked from the deleted file
"""
for lane_key in self.lane_keys:
original_abundance_file = os.path.join(self.outputdir, lane_key + ".abund.fa" )
new_abundance_file = os.path.join(self.outputdir, lane_key + ".newabund.fa")
new_names_file = os.path.join(self.outputdir, lane_key + ".names")
new_unique_file = os.path.join(self.outputdir, lane_key + ".unique.fa")
names = {}
uniques = {}
deleted_id_list = self.deleted_ids[lane_key]
if len(deleted_id_list) == 0:
continue
newnames_fh = open( new_names_file, "r" )
for line in newnames_fh.readlines():
lst = line.strip().split()
names[lst[0]] = lst[1].split(',')
#print names
fasta = SequenceSource(new_unique_file)
while fasta.next():
fasta.id
uniques[fasta.seq] = fasta.id
#print uniques
sorted_uniques = mysort( uniques, names )
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size="+str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(new_abundance_file,'a')
# rename to newuniques => uniques
os.rename(original_abundance_file, os.path.join(self.outputdir, lane_key + ".abund_dirty.fa" ))
os.rename(new_abundance_file, original_abundance_file )
def write_clean_abundance_file(self):
"""
Writes the abundance file from the new names file and new unique file.
Thes file have already had their ids checked from the deleted file
"""
for lane_key in self.lane_keys:
original_abundance_file = self.outputdir + "/" + lane_key + ".abund.fa"
new_abundance_file = self.outputdir + "/" + lane_key + ".newabund.fa"
new_names_file = self.outputdir + "/" + lane_key + ".names"
new_unique_file = self.outputdir + "/" + lane_key + ".unique.fa"
deleted_file = self.outputdir + "/" + lane_key + ".deleted.txt"
names = {}
uniques = {}
if not (os.path.exists(deleted_file)
and os.path.getsize(deleted_file) > 0):
continue
newnames_fh = open(new_names_file, "r")
for line in newnames_fh.readlines():
lst = line.strip().split()
names[lst[0]] = lst[1].split(',')
#print names
fasta = SequenceSource(new_unique_file)
while fasta.next():
fasta.id
uniques[fasta.seq] = fasta.id
#print uniques
sorted_uniques = mysort(uniques, names)
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size=" + str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(new_abundance_file, 'a')
# rename to newuniques => uniques
os.rename(original_abundance_file,
self.outputdir + "/" + lane_key + ".abund_dirty.fa")
os.rename(new_abundance_file, original_abundance_file)
def write_data_files(self, lane_keys):
###################################################################
#
# 10-print out files of unique trimmed sequence
# and deleted ids
# for each amplification:
# fasta file is this needed?
# names file (just like mothur)
# uniques fasta file (just like mothur)
# abundance fasta file -formated for usearch (-uc): sorted most abund first
# deleted read_ids file
# Also there should be one file each for rawaseq, trimseq, primers and runkeys
# Not divided by amplification for rapidly puting in db.
# These are printed in out directory: './out'+rundate
#
###################################################################
#rawseqFileName = self.outdir + '/rawseq_file.txt'
#trimseqFileName = self.outdir + '/trimseq_file.txt'
#f_rawseq = open(rawseqFileName, "w")
#f_trimseq = open(trimseqFileName,"w")
for lane_key in self.run.run_keys:
self.fa[lane_key].close()
base_file_name = os.path.join(self.outdir,lane_key)
uniquesFileName = base_file_name + ".unique.fa"
abundFileName = base_file_name + ".abund.fa"
namesFileName = base_file_name + ".names"
delFileName = base_file_name + ".deleted.txt"
f_names = open(namesFileName,"w")
# if we order the uniques by length of self.uniques[lane_key][seq] then we have abundance file
# Write abund.fa file
# mysort returns a list of tuples: (read_id, count, seq) sorted highest to lowest freq
try:
sorted_uniques = mysort( self.uniques[lane_key], self.names[lane_key] )
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size="+str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(abundFileName,'a')
except:
print "**********fail abund **************"
success_code = ('FAIL','abund',lane_key)
# Write uniques.fa file
try:
for seq in self.uniques[lane_key]:
read_id = self.uniques[lane_key][seq]
uniquefa = sfasta(read_id, seq)
uniquefa.write(uniquesFileName,'a')
logger.debug("\nwrote uniques file " + uniquesFileName)
except:
success_code = ('FAIL','unique',lane_key)
# Write names file
try:
for id in self.names[lane_key]:
others = ','.join(self.names[lane_key][id])
f_names.write(id+"\t"+others+"\n")
f_names.close()
logger.debug("wrote names file " + namesFileName)
except:
success_code = ('FAIL','names',lane_key)
# Write deleted.txt file
if lane_key in self.deleted_ids and self.deleted_ids[lane_key]:
f_del = open(delFileName, "w")
reason_counts = {}
for id in self.deleted_ids[lane_key]:
reason = self.deleted_ids[lane_key][id]
f_del.write(id+"\t"+reason+"\n")
current_count = reason_counts.get(reason, 0)
reason_counts[reason] = current_count + 1
# now write out some stats
f_del.write("\nTotal Passed Reads in this lane/key: " + str(len(self.names[lane_key])) + "\n")
if(len(self.names[lane_key]) > 0):
for key,value in reason_counts.items():
f_del.write(" " + key + ": " + str(value) + " " + str(float(value*100.0)/float(len(self.names[lane_key]))) + "% of total \n")
else:
pass
f_del.close()
logger.debug("wrote deleted file: " + delFileName)
# print out readids that failed the key test: one file only
if 'nokey' in self.deleted_ids and self.deleted_ids['nokey']:
nokeyFileName = os.path.join(self.outdir,'nokey.deleted.txt')
f_del = open(nokeyFileName,"w")
for id in self.deleted_ids['nokey']:
f_del.write(id+"\tnokey\n")
f_del.close()
if True:
print
print 'Output Directory:', './'+self.outdir
print self.number_of_raw_sequences, "raw sequences read"
pct = '%.1f' % ((float(self.number_of_good_sequences)/self.number_of_raw_sequences) *100)
print self.number_of_good_sequences, "sequences passed" ,pct+'%'
print "Unique Counts:"
count_uniques = 0
good_lane_keys = []
for lane_key in self.run.run_keys:
count = len(self.uniques[lane_key])
if count > 0:
good_lane_keys.append(lane_key)
count_uniques = count_uniques + count
print " ",lane_key,self.dna_regions[lane_key],count
print " Total Uniques:",count_uniques
#####
#
# Write to stats file for this run
#
self.stats_fp.write("Run: "+self.rundate+"\n")
self.stats_fp.write("Unique Counts:\n")
#stats_fp.write("Run: "+self.rundate)
count_uniques = 0
for lane_key in self.run.run_keys:
count = len(self.uniques[lane_key])
count_uniques = count_uniques + count
self.stats_fp.write(" " + str(count)+"\t"+lane_key+"\n")
self.stats_fp.write("Total Uniques: "+str(count_uniques)+"\n")
self.stats_fp.write("\nDeleted Counts (before chimera check):\n")
self.stats_fp.write(" deleted_count_for_nokey:\t" + str(self.deleted_count_for_nokey) + "\n")
self.stats_fp.write(" deleted_count_for_proximal:\t" + str(self.deleted_count_for_proximal)+ "\n")
self.stats_fp.write(" deleted_count_for_distal:\t" + str(self.deleted_count_for_distal)+ "\n")
self.stats_fp.write(" deleted_count_for_n:\t" + str(self.deleted_count_for_n)+ "\n")
self.stats_fp.write(" deleted_count_for_quality:\t" + str(self.deleted_count_for_quality)+ "\n")
self.stats_fp.write(" deleted_count_for_no_insert:\t" + str(self.deleted_count_for_no_insert)+ "\n")
self.stats_fp.write(" deleted_count_for_minimum_length:\t" + str(self.deleted_count_for_minimum_length)+ "\n")
self.stats_fp.write(" deleted_count_for_unknown_lane_runkey:\t" + str(self.deleted_count_for_unknown_lane_runkey)+ "\n")
self.stats_fp.write("Total Deleted: "+str(self.number_of_raw_sequences-self.number_of_good_sequences)+"\n")
self.stats_fp.close()
success_code=''
if not success_code:
success_code = ('SUCCESS ' + str(good_lane_keys))
return success_code
def write_data_files(self, lane_keys):
###################################################################
#
# 10-print out files of unique trimmed sequence
# and deleted ids
# for each amplification:
# fasta file is this needed?
# names file (just like mothur)
# uniques fasta file (just like mothur)
# abundance fasta file -formated for usearch (-uc): sorted most abund first
# deleted read_ids file
# Also there should be one file each for rawaseq, trimseq, primers and runkeys
# Not divided by amplification for rapidly puting in db.
# These are printed in out directory: './out'+rundate
#
###################################################################
#rawseqFileName = self.outdir + '/rawseq_file.txt'
#trimseqFileName = self.outdir + '/trimseq_file.txt'
#f_rawseq = open(rawseqFileName, "w")
#f_trimseq = open(trimseqFileName,"w")
for lane_key in self.run.run_keys:
self.fa[lane_key].close()
uniquesFileName = self.outdir + '/' + lane_key + ".unique.fa"
abundFileName = self.outdir + '/' + lane_key + ".abund.fa"
namesFileName = self.outdir + '/' + lane_key + ".names"
delFileName = self.outdir + '/' + lane_key + ".deleted.txt"
f_names = open(namesFileName, "w")
# if we order the uniques by length of self.uniques[lane_key][seq] then we have abundance file
# Write abund.fa file
# mysort returns a list of tuples: (read_id, count, seq) sorted highest to lowest freq
try:
sorted_uniques = mysort(self.uniques[lane_key],
self.names[lane_key])
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size=" + str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(abundFileName, 'a')
except:
success_code = ('FAIL', 'abund', lane_key)
# Write uniques.fa file
try:
for seq in self.uniques[lane_key]:
read_id = self.uniques[lane_key][seq]
uniquefa = sfasta(read_id, seq)
uniquefa.write(uniquesFileName, 'a')
if self.VERBOSE: print "\nwrote uniques file", uniquesFileName
except:
success_code = ('FAIL', 'unique', lane_key)
# Write names file
try:
for id in self.names[lane_key]:
others = ','.join(self.names[lane_key][id])
f_names.write(id + "\t" + others + "\n")
f_names.close()
if self.VERBOSE: print "wrote names file", namesFileName
except:
success_code = ('FAIL', 'names', lane_key)
# Write deleted.txt file
if lane_key in self.deleted_ids and self.deleted_ids[lane_key]:
f_del = open(delFileName, "w")
for id in self.deleted_ids[lane_key]:
reason = self.deleted_ids[lane_key][id]
f_del.write(id + "\t" + reason + "\n")
f_del.close()
if self.VERBOSE: print "wrote deleted file", delFileName
# print out readids that failed the key test: one file only
if 'nokey' in self.deleted_ids and self.deleted_ids['nokey']:
delfileName = self.outdir + '/nokey.deleted.txt'
f_del = open(delfileName, "w")
for id in self.deleted_ids['nokey']:
f_del.write(id + "\tnokey\n")
f_del.close()
if not self.QUIET:
print
print 'Output Directory:', './' + self.outdir
print self.number_of_raw_sequences, "raw sequences read"
pct = '%.1f' % ((float(self.number_of_good_sequences) /
self.number_of_raw_sequences) * 100)
print self.number_of_good_sequences, "sequences passed", pct + '%'
print "Unique Counts:"
count_uniques = 0
good_lane_keys = []
for lane_key in self.run.run_keys:
count = count_keys(self.uniques[lane_key])
if count > 0:
good_lane_keys.append(lane_key)
count_uniques = count_uniques + count
print " ", lane_key, self.dna_regions[lane_key], count
print " Total Uniques:", count_uniques
#####
#
# Write to stats file for this run
#
self.stats_fp.write("Run: " + self.rundate + "\n")
self.stats_fp.write("Unique Counts:\n")
#stats_fp.write("Run: "+self.rundate)
count_uniques = 0
for lane_key in self.run.run_keys:
count = count_keys(self.uniques[lane_key])
count_uniques = count_uniques + count
self.stats_fp.write(" " + str(count) + "\t" + lane_key + "\n")
self.stats_fp.write("Total Uniques: " + str(count_uniques) + "\n")
self.stats_fp.write("\nDeleted Counts (before chimera check):\n")
for reason in self.deleted_count:
self.stats_fp.write(" " + str(self.deleted_count[reason]) +
"\t" + reason + "\n")
self.stats_fp.write("Total Deleted: " +
str(self.number_of_raw_sequences -
self.number_of_good_sequences) + "\n")
self.stats_fp.close()
success_code = ''
if not success_code:
success_code = ('SUCCESS', '', good_lane_keys)
return success_code
def write_data_files(self, lane_keys):
###################################################################
#
# 10-print out files of unique trimmed sequence
# and deleted ids
# for each amplification:
# fasta file is this needed?
# names file (just like mothur)
# uniques fasta file (just like mothur)
# abundance fasta file -formated for usearch (-uc): sorted most abund first
# deleted read_ids file
# Also there should be one file each for rawaseq, trimseq, primers and runkeys
# Not divided by amplification for rapidly puting in db.
# These are printed in out directory: './out'+rundate
#
###################################################################
#rawseqFileName = self.outdir + '/rawseq_file.txt'
#trimseqFileName = self.outdir + '/trimseq_file.txt'
#f_rawseq = open(rawseqFileName, "w")
#f_trimseq = open(trimseqFileName,"w")
for lane_key in self.run.run_keys:
self.fa[lane_key].close()
uniquesFileName = self.outdir + '/' + lane_key + ".unique.fa"
abundFileName = self.outdir + '/' + lane_key + ".abund.fa"
namesFileName = self.outdir + '/' + lane_key + ".names"
delFileName = self.outdir + '/' + lane_key + ".deleted.txt"
f_names = open(namesFileName,"w")
# if we order the uniques by length of self.uniques[lane_key][seq] then we have abundance file
# Write abund.fa file
# mysort returns a list of tuples: (read_id, count, seq) sorted highest to lowest freq
try:
sorted_uniques = mysort( self.uniques[lane_key], self.names[lane_key] )
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size="+str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(abundFileName,'a')
except:
success_code = ('FAIL','abund',lane_key)
# Write uniques.fa file
try:
for seq in self.uniques[lane_key]:
read_id = self.uniques[lane_key][seq]
uniquefa = sfasta(read_id, seq)
uniquefa.write(uniquesFileName,'a')
if self.VERBOSE: print "\nwrote uniques file",uniquesFileName
except:
success_code = ('FAIL','unique',lane_key)
# Write names file
try:
for id in self.names[lane_key]:
others = ','.join(self.names[lane_key][id])
f_names.write(id+"\t"+others+"\n")
f_names.close()
if self.VERBOSE: print "wrote names file",namesFileName
except:
success_code = ('FAIL','names',lane_key)
# Write deleted.txt file
if lane_key in self.deleted_ids and self.deleted_ids[lane_key]:
f_del = open(delFileName, "w")
for id in self.deleted_ids[lane_key]:
reason = self.deleted_ids[lane_key][id]
f_del.write(id+"\t"+reason+"\n")
f_del.close()
if self.VERBOSE: print "wrote deleted file",delFileName
# print out readids that failed the key test: one file only
if 'nokey' in self.deleted_ids and self.deleted_ids['nokey']:
delfileName = self.outdir + '/nokey.deleted.txt'
f_del = open(delfileName,"w")
for id in self.deleted_ids['nokey']:
f_del.write(id+"\tnokey\n")
f_del.close()
if not self.QUIET:
print
print 'Output Directory:', './'+self.outdir
print self.number_of_raw_sequences, "raw sequences read"
pct = '%.1f' % ((float(self.number_of_good_sequences)/self.number_of_raw_sequences) *100)
print self.number_of_good_sequences, "sequences passed" ,pct+'%'
print "Unique Counts:"
count_uniques = 0
good_lane_keys = []
for lane_key in self.run.run_keys:
count = count_keys(self.uniques[lane_key])
if count > 0:
good_lane_keys.append(lane_key)
count_uniques = count_uniques + count
print " ",lane_key,self.dna_regions[lane_key],count
print " Total Uniques:",count_uniques
#####
#
# Write to stats file for this run
#
self.stats_fp.write("Run: "+self.rundate+"\n")
self.stats_fp.write("Unique Counts:\n")
#stats_fp.write("Run: "+self.rundate)
count_uniques = 0
for lane_key in self.run.run_keys:
count = count_keys(self.uniques[lane_key])
count_uniques = count_uniques + count
self.stats_fp.write(" " + str(count)+"\t"+lane_key+"\n")
self.stats_fp.write("Total Uniques: "+str(count_uniques)+"\n")
self.stats_fp.write("\nDeleted Counts (before chimera check):\n")
for reason in self.deleted_count:
self.stats_fp.write(" " + str(self.deleted_count[reason]) +"\t"+reason+"\n")
self.stats_fp.write("Total Deleted: "+str(self.number_of_raw_sequences-self.number_of_good_sequences)+"\n")
self.stats_fp.close()
success_code=''
if not success_code:
success_code = ('SUCCESS','',good_lane_keys)
return success_code
def write_data_files(self, idx_keys):
###################################################################
#
# 10-print(out files of unique trimmed sequence)
# and deleted ids
# for each amplification:
# fasta file is this needed?
# names file (just like mothur)
# uniques fasta file (just like mothur)
# abundance fasta file -formated for usearch (-uc): sorted most abund first
# deleted read_ids file
# Also there should be one file each for rawaseq, trimseq, primers and runkeys
# Not divided by amplification for rapidly puting in db.
# These are printed in out directory: './out'+rundate
#
###################################################################
#rawseqFileName = self.outdir + '/rawseq_file.txt'
#trimseqFileName = self.outdir + '/trimseq_file.txt'
#f_rawseq = open(rawseqFileName, "w")
#f_trimseq = open(trimseqFileName,"w")
if self.runobj.platform == 'illumina':
return
for idx_key in self.runobj.run_keys:
self.fa[idx_key].close()
base_file_name = os.path.join(self.trimming_dir, idx_key)
uniquesFileName = base_file_name + ".unique.fa"
abundFileName = base_file_name + ".abund.fa"
namesFileName = base_file_name + ".names"
delFileName = base_file_name + ".deleted.txt"
# clean out old files if they exists
remove_file(uniquesFileName)
remove_file(abundFileName)
remove_file(namesFileName)
remove_file(delFileName)
f_names = open(namesFileName, "w")
# if we order the uniques by length of self.uniques[idx_key][seq] then we have abundance file
# Write abund.fa file
# mysort returns a list of tuples: (read_id, count, seq) sorted highest to lowest freq
try:
sorted_uniques = mysort(self.uniques[idx_key],
self.names[idx_key])
for item in sorted_uniques:
read_id = item[0]
count = item[1]
seq = item[2]
sfastaRead = read_id + ";size=" + str(count)
abundfa = sfasta(sfastaRead, seq)
abundfa.write(abundFileName, 'a')
except:
print("**********fail abund **************")
success_code = ('FAIL', 'abund', idx_key)
# Write uniques.fa file
#print('UNIQUES',self.uniques)
try:
for seq in self.uniques[idx_key]:
read_id = self.uniques[idx_key][seq]
print(uniquesFileName, read_id, seq)
uniquefa = sfasta(read_id, seq)
uniquefa.write(uniquesFileName, 'a')
logger.debug("\nwrote uniques file " + uniquesFileName)
except:
success_code = ('FAIL', 'unique', idx_key)
# Write names file
try:
for id in self.names[idx_key]:
others = ','.join(self.names[idx_key][id])
f_names.write(id + "\t" + others + "\n")
f_names.close()
logger.debug("wrote names file " + namesFileName)
except:
success_code = ('FAIL', 'names', idx_key)
# Write deleted.txt file
if idx_key in self.deleted_ids and self.deleted_ids[idx_key]:
f_del = open(delFileName, "w")
reason_counts = {}
for id in self.deleted_ids[idx_key]:
reason = self.deleted_ids[idx_key][id]
f_del.write(id + "\t" + reason + "\n")
current_count = reason_counts.get(reason, 0)
reason_counts[reason] = current_count + 1
# now write out some stats
# f_del.write("\nTotal Passed Reads in this lane/key: " + str(len(self.names[idx_key])) + "\n")
# if(len(self.names[idx_key]) > 0):
# for key,value in reason_counts.items():
# f_del.write(" " + key + ": " + str(value) + " " + str(float(value*100.0)/float(len(self.names[idx_key]))) + "% of total \n")
# else:
# pass
f_del.close()
logger.debug("wrote deleted file: " + delFileName)
# print(out readids that failed the key test: one file only)
if 'nokey' in self.deleted_ids and self.deleted_ids['nokey']:
nokeyFileName = os.path.join(self.trimming_dir,
'nokey.deleted.txt')
f_del = open(nokeyFileName, "w")
for id in self.deleted_ids['nokey']:
f_del.write(id + "\tnokey\n")
f_del.close()
if True:
print
print('Output Directory:', './' + self.outdir)
print(self.number_of_raw_sequences, "raw sequences read")
pct = '%.1f' % ((float(self.number_of_good_sequences) /
self.number_of_raw_sequences) * 100)
print(self.number_of_good_sequences, "sequences passed", pct + '%')
print("Unique Counts:")
count_uniques = 0
good_idx_keys = []
for idx_key in self.runobj.run_keys:
count = len(self.uniques[idx_key])
if count > 0:
good_idx_keys.append(idx_key)
count_uniques = count_uniques + count
print(" ", idx_key, self.dna_regions[idx_key], count)
print(" Total Uniques:", count_uniques)
#####
#
# Write to stats file for this run
#
self.stats_fp.write("Run_code: " + self.run + "\n")
self.stats_fp.write(
"========================================================\n")
self.stats_fp.write(
"Deleted Counts (before chimera check if performed):\n")
self.stats_fp.write(
" deleted_count_for_nokey:......................" +
str(self.deleted_count_for_nokey) + "\n")
self.stats_fp.write(
" deleted_count_for_proximal:..................." +
str(self.deleted_count_for_proximal) + "\n")
self.stats_fp.write(
" deleted_count_for_distal:....................." +
str(self.deleted_count_for_distal) + "\n")
self.stats_fp.write(
" deleted_count_for_N:.........................." +
str(self.deleted_count_for_n) + "\n")
self.stats_fp.write(
" deleted_count_for_quality:...................." +
str(self.deleted_count_for_quality) + "\n")
self.stats_fp.write(
" deleted_count_for_no_insert:.................." +
str(self.deleted_count_for_no_insert) + "\n")
self.stats_fp.write(" deleted_count_for_minimum_length(" +
str(self.runobj.minimumLength) + "bp):......." +
str(self.deleted_count_for_minimum_length) + "\n")
self.stats_fp.write(" deleted_count_for_maximum_length(" +
str(self.runobj.maximumLength) + "bp):........." +
str(self.deleted_count_for_maximum_length) + "\n")
self.stats_fp.write(
" deleted_count_for_unknown_lane_runkey:........" +
str(self.deleted_count_for_unknown_lane_runkey) + "\n")
self.stats_fp.write("Total Raw Sequences:...." +
str(self.number_of_raw_sequences) + "\n")
self.stats_fp.write("Total Good Sequences:..." +
str(self.number_of_good_sequences) + "\n")
self.stats_fp.write("Total Deleted:.........." +
str(self.number_of_raw_sequences -
self.number_of_good_sequences) + "\n")
self.stats_fp.write("Total Uniques:.........." + str(count_uniques) +
"\n")
self.stats_fp.write("\nUnique Counts per Dataset:\n")
#stats_fp.write("Run: "+self.run)
count_uniques = 0
for idx_key in self.runobj.run_keys:
count = len(self.uniques[idx_key])
count_uniques = count_uniques + count
self.stats_fp.write(" " + str(count) + "\t" + idx_key + "\t" +
self.runobj.samples[idx_key].dataset + "\n")
self.stats_fp.write(
"\n========================================================\n")
self.stats_fp.close()
success_code = ''
if not success_code:
success_code = ('SUCCESS ' + str(good_idx_keys))
return success_code
