def clean_fastqc_output(param,readfile):
"""
Function that delete unwanted FastQC output files.
Takes two arguments :
- param [dict] : dictionnary containing all parameters
- readfile [dict] : fastq file used by Fastqc
Returns one argument :
- file [dict] : containing quality control information about the readfile
"""
# Save the working directory
work_dir = os.getcwd()
# Delete unwanted files ----------------------------------------------------
# get prefix of readfile to delete unwanted files generated by FastQC
file_1 = ce.get_file_prefix(readfile)
# delete
os.remove('{0}/Fastqc/{1}_fastqc.zip'.format(param['output'], file_1))
os.chdir('{0}/Fastqc/{1}_fastqc'.format(param['output'], file_1))
os.system('mv ../{0}_fastqc.html .'.format(file_1))
os.system('rm -r fastqc_report.html fastqc.fo summary.txt Icons')
# Get Quality control information about readfile ---------------------------
# regex
filename_re = re.compile("^Filename\t(.*)")
encoding_re = re.compile("^Encoding\t(.*)")
total_seq_re = re.compile("^Total Sequences\t(.*)")
seq_length_re = re.compile("^Sequence length\t(.*)")
GC_perc_re = re.compile("^%GC\t(.*)")
# create a dict
file1 = {}
# get information
with open("fastqc_data.txt", "rt") as f:
for line in f:
# filename
match = filename_re.search(line)
if match:
file1['filename'] = match.group(1)
# encoding
match = encoding_re.search(line)
if match:
file1['encoding'] = match.group(1)
# total sequences
match = total_seq_re.search(line)
if match:
file1['total_sequence'] = match.group(1)
# sequence length
match = seq_length_re.search(line)
if match:
file1['sequence_length'] = match.group(1)
# percentage GC
match = GC_perc_re.search(line)
if match:
file1['GC_perc'] = match.group(1)
# go back to the working directory
os.chdir(work_dir)
return file1
def commandline_input_output(param, cmd, nb, inout):
"""
Function that add to 'cmd' the input and output files commandline depending
on if it's the first or second step of trimming (information given by nb)
Takes 4 arguments :
- param [dict] : dictionnary containing all parameters
- cmd [string] : base command line of the programme (trimmomatic)
- nb [integer] : number of executed trimming command
- inout [dict] : dictionnary containing all generated files on the
user's computer
Returns two arguments:
- cmd [string] : the command line with the input and output files
- inout [dict] : with new files names
"""
# SINGLE-END DATA ----------------------------------------------------------
if(param['layout'] == 'SE'):
cmd += ' SE'
cmd += ' -threads {0}'.format(param['threads'])
# Creating output filename(s) ------------------------------------------
# get input file prefix to create new filename(s)
prefix = ce.get_file_prefix(param['input'][0])
trimmed = "{0}/trimmed_{1}.fastq".format(param['output'],prefix)
# add the compression format if choosen
if 'compress' in param :
trimmed += "{0}".format(param['compress'])
# Generation of commandline --------------------------------------------
# if it's a the first trimming
if (nb == 0):
cmd += ' {0} {1}'.format(param['input'][0], trimmed)
# adding the input and output files to inout
inout['input'] = param['input']
inout['trimmed'] = trimmed
# else step 2 input files are the output files of step 1
elif (nb == 1):
cmd += ' {0} {1}'.format(inout['tmp'], trimmed)
# PAIRED-END DATA ----------------------------------------------------------
elif(param['layout'] == 'PE') :
cmd += ' PE'
cmd += ' -threads {0} '.format(param['threads'])
# Creating output filename(s) ------------------------------------------
# get input file prefix to create new filename(s)
prefix_1 = ce.get_file_prefix(param['input'][0])
prefix_2 = ce.get_file_prefix(param['input'][1])
trimmed_1 = "{0}/trimmed_{1}.fastq".format(param['output'],prefix_1)
trimmed_2 = "{0}/trimmed_{1}.fastq".format(param['output'],prefix_2)
single_1 = "{0}/single_{1}.fastq".format(param['output'],prefix_1)
single_2 = "{0}/single_{1}.fastq".format(param['output'],prefix_2)
# add the compression format if choosen
if 'compress' in param :
trimmed_1 += "{0}".format(param['compress'])
trimmed_2 += "{0}".format(param['compress'])
single_1 += "{0}".format(param['compress'])
single_2 += "{0}".format(param['compress'])
# Generation of commandline --------------------------------------------
# if it's a the first trimming
if(nb==0):
cmd += ' {0} {1} {2} {3} {4} {5}'.format(param['input'][0],
param['input'][1],
trimmed_1, single_1,
trimmed_2, single_2)
# adding the input and output files to inout
inout['input'] = param['input']
inout['trimmed'] = trimmed_1, trimmed_2
inout['single'] = single_1, single_2
# else step 2 input files are the output files of step 1
elif(nb==1):
cmd += '{0} {1} {2} {3} {4} {5}'.format(inout['tmp'][0],
inout['tmp'][1],
trimmed_1, single_1,
trimmed_2, single_2)
return cmd,inout
def change_output_as_input(inout, param):
"""
Function that change step1 output files into step2 input files.
Takes 2 arguments :
- inout [dict] : dictionnary containing all generated files on the
user's working directory
- param [dict] : dictionnary containing all parameters
Returns one argument:
inout [dict] : containing the new files names
"""
# SINGLE-END ---------------------------------------------------------------
if(param['layout'] == 'SE'):
# Creating temporary filename(s) ---------------------------------------
# get the prefix of the file
filename = ce.get_file_prefix(param['input'][0])
# new temporary filename
tmp = '{0}/tmp{1}.fastq'.format(param['output'], filename)
if 'compress' in param:
tmp += '{0}'.format(param['compress'])
# Rename step 1 trimming file in temporary -----------------------------
os.rename(inout['trimmed'], tmp)
# Add the temporary file in io -----------------------------------------
inout['tmp'] = tmp
# PAIRED-END ---------------------------------------------------------------
else :
# Creating temporary filename(s) ---------------------------------------
# get the prefix of files
filename_1 = ce.get_file_prefix(param['input'][0])
filename_2 = ce.get_file_prefix(param['input'][1])
# new temporary filenames
tmp_1 = '{0}/tmp{1}.fastq'.format(param['output'],filename_1)
tmp_2 = '{0}/tmp{1}.fastq'.format(param['output'],filename_2)
if 'compress' in param:
tmp_1 += '.{0}'.format(param['compress'])
tmp_2 += '.{0}'.format(param['compress'])
# Rename step 1 trimming file in temporary -----------------------------
os.rename(inout['trimmed'][0], tmp_1)
os.rename(inout['trimmed'][1], tmp_2)
# Add the temporary file in io -----------------------------------------
inout['tmp'] = tmp_1, tmp_2
# Delete step1 singleton read files ------------------------------------
os.remove(inout['single'][0])
os.remove(inout['single'][1])
return inout
