def poisson_clones(mean, line_num):
"""Given the mean, finds number of times to clone the line using poisson dist.
:param float mean: the mean of the data
:param int line_num: the number of lines in the file
:return int: number of times to clone the line using poisson dist.
"""
print yellow("[STATUS] List created.")
return np.random.poisson(mean, line_num)
def poisson_clones(mean, line_num):
"""Given the mean, finds number of times to clone the line using poisson dist.
:param float mean: the mean of the data
:param int line_num: the number of lines in the file
:return int: number of times to clone the line using poisson dist.
"""
print yellow("[STATUS] List created.")
return np.random.poisson(mean, line_num)
def fastq_clones(opts, line_num):
"""Finds the number of times to clone based on actual fastq dist.
:param args opts: user-inputted args parsed by argparse
:param int line_num: the number of lines in the file
:return list data_list: the list of numbers selected from the file's distribution
"""
data_list = give_clone_list(opts, line_num)
print yellow("[STATUS] List created.")
return data_list
def nb_clones(mean, variance, line_num):
"""Given mean and variance, gives the number of times to clone using n.b. distribution
:param float mean: the mean of the data
:param float variance: the standard deviation
:param int line_num: the number of lines in the file
:return int: number of times to clone the line using neg. binomial distribution
"""
print yellow("[STATUS] List created.")
return np.random.negative_binomial(mean, variance, line_num)
def fastq_clones(opts, line_num):
"""Finds the number of times to clone based on actual fastq dist.
:param args opts: user-inputted args parsed by argparse
:param int line_num: the number of lines in the file
:return list data_list: the list of numbers selected from the file's distribution
"""
data_list = give_clone_list(opts, line_num)
print yellow("[STATUS] List created.")
return data_list
def nb_clones(mean, variance, line_num):
"""Given mean and variance, gives the number of times to clone using n.b. distribution
:param float mean: the mean of the data
:param float variance: the standard deviation
:param int line_num: the number of lines in the file
:return int: number of times to clone the line using neg. binomial distribution
"""
print yellow("[STATUS] List created.")
return np.random.negative_binomial(mean, variance, line_num)
def find_line_nums(opts):
"""Finds the number of lines in the file to be used later
:param args opts: the user-inputted args parsed by argparse
:return int line_num: the number of sequences in the file from opts
"""
line_num = 0
for line in opts.fastq:
if '@' in line:
line_num += 1
print yellow("[STATUS] Found number of lines.")
return line_num
def find_line_nums(opts):
"""Finds the number of lines in the file to be used later
:param args opts: the user-inputted args parsed by argparse
:return int line_num: the number of sequences in the file from opts
"""
line_num = 0
for line in opts.fastq:
if '@' in line:
line_num += 1
print yellow("[STATUS] Found number of lines.")
return line_num
def main(args):
"""Main method
:param args: arguments
:return: None
"""
print green('Running...')
opts = parse_cmdline_params(args[1:])
infile = opts.fastq
fastq_dict = create_fastq_dict(infile, opts)
error_dict = decide_if_error(fastq_dict)
print yellow("[STATUS] Error dict created.")
if raw_input(blue('Would you like results printed to the terminal? Answer y or n: ')) is 'y':
print_results(fastq_dict, error_dict)
if raw_input(blue('Would you like to write the results to a file? Answer y or n: ')) is 'y':
write_results_to_file(fastq_dict, error_dict, opts)
print green('Done')
def create_fastq_dict(infile, opts):
"""Creates a defaultdict from a fastq file with name and sequence and clones based on cloned
Cloned defaults to 0 for no cloning, 1 for poisson, 2 for negative binomial, 3 for fastq dist.
:param infile: the file to create the fastq from
:param args opts: options parsed from command line
:return: defaultdict of sequences and names
"""
line_num = find_line_nums(opts)
infile.seek(0)
cloned = opts.cloning
if cloned == 1:
clones = poisson_clones(opts.mean, line_num)
elif cloned == 2:
clones = nb_clones(opts.mean, opts.variance, line_num)
elif cloned == 3:
clones = fastq_clones(opts, line_num)
else:
clones = [0] * line_num
print clones
infile.seek(0)
sequences = defaultdict(str)
line_counter = 1
for line in infile:
line = line.rstrip()
if line[0] == '@':
next_line = next(infile).rstrip()
sequences[line[1:].rstrip()] = next_line
#print line_num
#print clones[line_counter - 1]
for clone_num in range(1, clones[line_counter - 1]):
clone_num = str(clone_num)
sequences[line[1:].rstrip() + ' (' + clone_num +
')'] = next_line
#print sequences.keys()
line_counter += 1
print yellow(("[STATUS] It's still going! {}".format(
('.' * ((line_counter % 2) + 1)))))
print yellow("[STATUS] Dictionary created.")
return sequences
def create_fastq_dict(infile, opts):
"""Creates a defaultdict from a fastq file with name and sequence and clones based on cloned
Cloned defaults to 0 for no cloning, 1 for poisson, 2 for negative binomial, 3 for fastq dist.
:param infile: the file to create the fastq from
:param args opts: options parsed from command line
:return: defaultdict of sequences and names
"""
line_num = find_line_nums(opts)
infile.seek(0)
cloned = opts.cloning
if cloned == 1:
clones = poisson_clones(opts.mean, line_num)
elif cloned == 2:
clones = nb_clones(opts.mean, opts.variance, line_num)
elif cloned == 3:
clones = fastq_clones(opts, line_num)
else:
clones = [0] * line_num
print clones
infile.seek(0)
sequences = defaultdict(str)
line_counter = 1
for line in infile:
line = line.rstrip()
if line[0] == '@':
next_line = next(infile).rstrip()
sequences[line[1:].rstrip()] = next_line
#print line_num
#print clones[line_counter - 1]
for clone_num in range(1, clones[line_counter - 1]):
clone_num = str(clone_num)
sequences[line[1:].rstrip() + ' (' + clone_num + ')'] = next_line
#print sequences.keys()
line_counter += 1
print yellow(("[STATUS] It's still going! {}".format(('.' * ((line_counter % 2) + 1)))))
print yellow("[STATUS] Dictionary created.")
return sequences
def main(args):
"""Main method
:param args: arguments
:return: None
"""
print green('Running...')
opts = parse_cmdline_params(args[1:])
infile = opts.fastq
fastq_dict = create_fastq_dict(infile, opts)
error_dict = decide_if_error(fastq_dict)
print yellow("[STATUS] Error dict created.")
if raw_input(
blue(
'Would you like results printed to the terminal? Answer y or n: '
)) is 'y':
print_results(fastq_dict, error_dict)
if raw_input(
blue(
'Would you like to write the results to a file? Answer y or n: '
)) is 'y':
write_results_to_file(fastq_dict, error_dict, opts)
print green('Done')