def run_align(inputs, paths_in, paths_out): # all arguments = dict
'''Bowtie align'''
run = inputs['run_bowtie']
files = inputs['files']
threads = inputs['cores'] # bowtie uses 1 core per instance
if not files:
print("There are no files")
return
ladder = []
tRNA = []
rRNA = []
chromosome = []
for fname in files:
if not run == 'yes':
if not os.path.exists(paths_out['path_chr'] + fname +
'_match.SAM'):
print "ERROR: " + fname + " has not been aligned, change run settings"
continue
else:
print fname + " has been aligned"
continue
if not os.path.exists(paths_out['path_filter'] + fname +
'-trimmed.fastq'):
print "ERROR: " + fname + " has no filtered file, has been removed from analysis"
inputs['files'].remove(fname)
continue
file_log = paths_out['path_log'] + fname + '_bowtie'
# bowtie_1 will rewrite log
bowtie_1 = '%s -v 2 -y -m 1 -a --best --strata -S -p 2 --un '
bowtie_1 += '%s%s_nomatch.fastq --max %s%s_multi.fastq --al %s%s_match.fastq %s '
bowtie_1 += '%s%s %s%s 1>>%s 2>%s'
# bowtie will only add info to log
bowtie = '%s -v 2 -y -m 1 -a --best --strata -S -p 2 --un '
bowtie += '%s%s_nomatch.fastq --max %s%s_multi.fastq --al %s%s_match.fastq %s '
bowtie += '%s%s %s%s 1>>%s 2>>%s'
# first, align to ladder index to subtract
bowtie_ladder = bowtie_1 % (
paths_in['path_bowtie'], paths_out['path_ladder'], fname,
paths_out['path_ladder'], fname, paths_out['path_ladder'], fname,
paths_in['btindex_ladder'], paths_out['path_filter'],
fname + '-trimmed.fastq', paths_out['path_temp'],
fname + '_ladder_match.SAM', file_log, file_log)
ladder.append(bowtie_ladder)
# second, align to ladder index to subtract
bowtie_tRNA = bowtie % (
paths_in['path_bowtie'], paths_out['path_trna'], fname,
paths_out['path_trna'], fname, paths_out['path_trna'], fname,
paths_in['btindex_trna'], paths_out['path_ladder'],
fname + '_nomatch.fastq', paths_out['path_temp'],
fname + '_tRNA_match.SAM', file_log, file_log)
tRNA.append(bowtie_tRNA)
# third, align to the rRNA index
bowtie_rRNA = bowtie % (
paths_in['path_bowtie'], paths_out['path_rrna'], fname,
paths_out['path_rrna'], fname, paths_out['path_rrna'], fname,
paths_in['btindex_rrna'], paths_out['path_trna'],
fname + '_nomatch.fastq', paths_out['path_temp'],
fname + '_rRNA_match.SAM', file_log, file_log)
rRNA.append(bowtie_rRNA)
# then align to the chr index
bowtie_chr = bowtie % (paths_in['path_bowtie'], paths_out['path_chr'],
fname, paths_out['path_chr'], fname,
paths_out['path_chr'], fname,
paths_in['btindex_chr'], paths_out['path_rrna'],
fname + '_nomatch.fastq', paths_out['path_chr'],
fname + '_match.SAM', file_log, file_log)
chromosome.append(bowtie_chr)
print "\n------ALIGN------"
print '\nFiles to align: ' + ', '.join(files)
print "\n\tStarted Bowtie alignment at " + str(datetime.now())
ribo_util.subprocess_wf(ladder, threads)
print "\tFinished ladder removal at " + str(datetime.now())
ribo_util.subprocess_wf(tRNA, threads)
print "\tFinished tRNA removal at " + str(datetime.now())
ribo_util.subprocess_wf(rRNA, threads)
print "\tFinished rRNA removal at " + str(datetime.now())
ribo_util.subprocess_wf(chromosome, threads)
print "\tFinished chromosome alignment at " + str(datetime.now())
print "\tCOMPLETED ALIGNING"
return
def run_filter(inputs, paths_in, paths_out): # all arguments = dict
'''
Filter reads using skewer
'''
files = inputs['files']
run = inputs['run_filtering']
minlength = inputs['minlength']
maxlength = inputs['maxlength']
phred_cutoff = inputs['phred_cutoff']
linker = inputs['linker']
threads = inputs['threads'] # filterreads has its own threading,
filtering = []
log_data = {}
if not files:
print("There are no files")
return
for fname in files:
file_in = paths_in['path_fastq'] + fname
file_out = paths_out['path_filter'] + fname
file_log = paths_out['path_log'] + fname + '_filter'
if not run == 'yes':
if not os.path.exists(file_out + '-trimmed.fastq'):
print "ERROR: " + fname + " has not been filtered, change run setting"
continue
else:
print fname + " has been filtered"
continue
if not os.path.exists(file_in):
print "ERROR: " + fname + " has no FASTQ file, has been removed from analysis"
inputs['files'].remove(fname)
continue
command_to_run = 'skewer -x %s -Q %d -l %d -L %d -o %s --quiet -t %d %s 1>>%s 2>%s' % (
linker, phred_cutoff, minlength, maxlength, file_out, threads,
file_in, file_log, file_log)
#Add filter parameters to log:
log_data['settings'] = {
'linker': linker,
'phred_cutoff': phred_cutoff,
'minlength': minlength,
'maxlength': maxlength
}
log_function = 'ribo_density'
ribo_util.analysis_log(fname, log_function, log_data, paths_in,
paths_out)
filtering.append(command_to_run)
print "-----FILTER-----"
print '\nFiles to filter: ' + ', '.join(files)
print "Filter parameters are: \nmin length = %s \nmax length = %s \nphred cutoff = %s " % (
minlength, maxlength, phred_cutoff)
print "\n\tStarted filtering at " + str(datetime.now())
ribo_util.subprocess_wf(filtering, 1)
print "\tFinished filtering at " + str(datetime.now())
print "\tCOMPLETED FILTERING"
return inputs
def run_filter(inputs, paths_in, paths_out): # all arguments = dict
'''
Filter reads using skewer
'''
files = inputs['files']
run = inputs['run_filtering']
minlength = inputs['minlength']
maxlength = inputs['maxlength']
phred_cutoff = inputs['phred_cutoff']
linker = inputs['linker']
threads = inputs['threads'] # filterreads has its own threading,
filtering = []
log_data = {}
# If using Unique Molecular Index (UMI) in library prep. Skewer will not remove UMI
# so we will do it manually after. skewer output file will have UMI naming to identify it:
if inputs['run_filter_UMI'] == 'yes':
# UMI adds 10 nt to read
minlength = minlength + 10
maxlength = maxlength + 10
# for naming: UMI
UMI = '_UMI'
else:
UMI = ''
# return error if file names not specified
if not files:
print("There are no files")
return
# loop through files to filter
for fname in files:
file_in = paths_in['path_fastq'] + fname
file_out = paths_out['path_filter'] + fname + UMI
file_log = paths_out['path_log'] + fname + '_filter'
# if skewer filtering isnt needed, skip
if not run == 'yes':
if not os.path.exists(file_out+'-trimmed.fastq'):
print "ERROR: " + fname + " has not been filtered, change run setting"
continue
else:
print fname + " has been filtered"
continue
# return error if input file missing, and continue to next file
if not os.path.exists(file_in):
print "ERROR: " + fname + " has no FASTQ file, has been removed from analysis"
inputs['files'].remove(fname)
continue
# make commmand string
command_to_run = 'skewer -x %s -Q %d -l %d -L %d -o %s --quiet -t %d %s 1>>%s 2>%s' % (
linker,
phred_cutoff,
minlength,
maxlength,
file_out,
threads,
file_in,
file_log,
file_log
)
#Add filter parameters to log:
log_data['settings'] = {'linker': linker, 'phred_cutoff': phred_cutoff,
'minlength': minlength, 'maxlength': maxlength}
log_function = 'ribo_density'
ribo_util.analysis_log(fname, log_function, log_data, paths_in, paths_out)
filtering.append(command_to_run)
#print start time and run skewer
print "-----FILTER-----"
print '\nFiles to filter: ' + ', '.join(files)
print "Filter parameters are: \nmin length = %s \nmax length = %s \nphred cutoff = %s " % (
minlength, maxlength, phred_cutoff)
print "\n\tStarted filtering at " + str(datetime.now())
ribo_util.subprocess_wf(filtering, 1)
print "\tFinished filtering at " + str(datetime.now())
print "\tCOMPLETED FILTERING"
return inputs