def parse_input(args):
def positive_int(num):
try:
val = int(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
parser = argparse.ArgumentParser(
prog="PolTools metaplot",
description=
"Compute the number of 5'/3'/whole prime reads at each position of the given region.\n"
+ "More information can be found at " +
"https://github.com/GeoffSCollins/PolTools/blob/master/docs/metaplot.rst"
)
parser.add_argument('read_type',
metavar='read type',
type=str,
choices=["five", "three", "whole"],
help='either five, three, or whole')
parser.add_argument(
'regions_file',
metavar='regions_file',
type=str,
help=
'Bed formatted file containing all the regions you want to average the sequences'
)
parser.add_argument(
'seq_files',
metavar='sequencing_files',
nargs='+',
type=str,
help='Bed formatted files from the sequencing experiment')
parser.add_argument('-t',
'--threads',
dest='threads',
metavar='threads',
type=positive_int,
nargs='?',
default=multiprocessing.cpu_count())
args = parser.parse_args(args)
regions_filename = args.regions_file
sequencing_files_list = args.seq_files
max_threads = args.threads
verify_bed_files(regions_filename)
region_length = determine_region_length(regions_filename)
verify_region_length_is_even(region_length)
return args.read_type, regions_filename, sequencing_files_list, region_length, max_threads
def parse_args(args):
def positive_int(num):
try:
val = int(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
parser = argparse.ArgumentParser(
prog='PolTools tps_distance_per_gene',
description=
'Determine the most common pausing distance from the max TSS for each gene.\n'
+ "More information can be found at " +
"https://geoffscollins.github.io/PolTools/tps_distance_per_gene.html")
parser.add_argument(
'regions_filename',
metavar='regions_filename',
type=str,
help=
'Bed formatted regions file with an even region length or a region length of one.'
)
parser.add_argument(
'seq_files',
metavar='sequencing_files',
nargs='+',
type=str,
help='Bed formatted files from the sequencing experiment')
parser.add_argument('-t',
'--threads',
dest='threads',
metavar='threads',
type=positive_int,
nargs='?',
default=multiprocessing.cpu_count())
args = parser.parse_args(args)
regions_filename = args.regions_filename
sequencing_files_list = args.seq_files
max_threads = args.threads
if len(sequencing_files_list) == 0:
sys.stderr.write("")
region_length = determine_region_length(regions_filename)
if region_length != 1:
verify_region_length_is_even(region_length)
return regions_filename, sequencing_files_list, region_length, max_threads
def parse_args(args):
# Argparse does not allow the input numbers to start with a -. So, we add a space to the input so it works.
for i, arg in enumerate(sys.argv):
if (arg[0] == '-') and arg[1].isdigit(): sys.argv[i] = ' ' + arg
parser = argparse.ArgumentParser(prog='PolTools sequence_from_region_around_max_tss',
description='Get the sequence from a certain region around the max TSS\n' +
"More information can be found at " +
"https://geoffscollins.github.io/PolTools/sequence_from_region_around_max_tss.html"
)
parser.add_argument('max_tss_file', metavar='max_tss_file', type=str,
help='Bed formatted file which has the base of the max TSS')
parser.add_argument('left', metavar='left', type=int,
help='Left end of the region to get the sequence.')
parser.add_argument('right', metavar='right', type=int,
help='Left end of the region to get the sequence.')
parser.add_argument('-u', '--underscore', action="store_true", dest='underscore',
default=False, help='Split the sequences by an underscore instead of a new line.')
args = parser.parse_args(args)
max_tss_file = args.max_tss_file
left = args.left
right = args.right
if 0 in [left, right]:
sys.stderr.write("There is no 0 nucleotide. Please try again.\n")
sys.exit(1)
region_length = determine_region_length(max_tss_file)
if region_length != 1:
sys.stderr.write("The maxTSS bed file must have regions of 1 bp.\n")
sys.exit(1)
# Convert search region syntax to a list
search_left = [
"+" if left > 0 else "-",
abs(left)
]
search_right = [
"+" if right > 0 else "-",
abs(right)
]
search = [search_left, search_right]
return args.underscore, max_tss_file, search
def parse_args(args):
def positive_int(num):
try:
val = int(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
parser = argparse.ArgumentParser(
prog='PolTools divergent_pileup_metaplot',
description='Generate a metaplot of the pileup reads.\n' +
'More information can be found at https://geoffscollins.github.io/PolTools/divergent_pileup_metaplot.html'
)
parser.add_argument(
'regions_file',
metavar='regions_file',
type=str,
help=
'Bed formatted file containing all the regions you want to average the sequences'
)
parser.add_argument(
'seq_files',
metavar='sequencing_files',
nargs='+',
type=str,
help='Bed formatted files from the sequencing experiment')
parser.add_argument('-t',
'--threads',
dest='threads',
metavar='threads',
type=positive_int,
nargs='?',
default=multiprocessing.cpu_count())
args = parser.parse_args(args)
regions_filename = args.regions_file
max_threads = args.threads
region_length = determine_region_length(regions_filename)
verify_region_length_is_even(region_length)
sequencing_files_list = args.seq_files
return regions_filename, sequencing_files_list, region_length, max_threads
def parse_args(args):
parser = argparse.ArgumentParser(
prog='PolTools base_distribution',
description=
'Compute the average base composition at each position of the given region.\n'
+ "More information can be found at " +
"https://geoffscollins.github.io/PolTools/base_distribution.html")
parser.add_argument(
'regions_file',
metavar='regions_file',
type=str,
help=
'Bed formatted file containing all the regions you want to average the sequences'
)
args = parser.parse_args(args)
regions_file = args.regions_file
verify_bed_files(regions_file)
region_length = determine_region_length(regions_file)
verify_region_length_is_even(region_length)
return args.regions_file, region_length
def parse_input(args):
parser = argparse.ArgumentParser(
prog='PolTools sequence_searches',
description=
'Determine if a sequence in present in a region around the max TSS\n' +
'More information can be found at ' +
'https://geoffscollins.github.io/PolTools/sequence_searches.html')
parser.add_argument(
'regions_filename',
metavar='regions_filename',
type=str,
help=
'Bed formatted regions file with an even region length or a region length of one.'
)
parser.add_argument(
'search',
metavar='search',
type=str,
nargs='+',
help=
'Search region formatted as follows: (Sequence),(-/+)left:(-/+)right. Ex: TATA,-30:-20'
)
args = parser.parse_args(args)
regions_file = args.regions_filename
searching_sequences = args.search
region_length = determine_region_length(regions_file)
verify_region_length_is_even(region_length)
# Max position can be either positive or negative
max_position = int(region_length / 2)
cleaned_search_sequences = []
for search in searching_sequences:
try:
sequence, search_region = search.split(",")
left, right = search_region.split(":")
left = int(left)
right = int(right)
except Exception as _:
raise InvalidSearchException(search)
if right < left:
raise InvalidSearchException(search)
# Check in the left and right positions are in the area
if left < (max_position * -1):
raise InvalidSearchException(search)
if right > max_position:
raise InvalidSearchException(search)
cleaned_search_sequences.append([sequence, left, right])
return regions_file, cleaned_search_sequences, region_length
def parse_input(args):
def positive_int(num):
try:
val = int(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
parser = argparse.ArgumentParser(
prog='PolTools pausing_distance_distribution_from_maxTSS',
description=
'Quantify the number of transcripts at each length originating from the max TSS\n'
+ "More information can be found at " +
"https://geoffscollins.github.io/PolTools/pausing_distance_distribution_from_maxTSS.html"
)
parser.add_argument(
'regions_filename',
metavar='regions_filename',
type=str,
help=
'Bed formatted regions file with an even region length or a region length of one.'
)
parser.add_argument(
'seq_files',
metavar='sequencing_files',
nargs='+',
type=str,
help='Bed formatted files from the sequencing experiment')
parser.add_argument(
'-m',
'--max_transcript_length',
dest='max_transcript_length',
metavar='max_transcript_length',
type=positive_int,
nargs='?',
help=
'Set the maximum transcript length to be outputted. Default is 100',
default=100)
parser.add_argument('-t',
'--threads',
dest='threads',
metavar='threads',
type=positive_int,
nargs='?',
default=multiprocessing.cpu_count())
args = parser.parse_args(args)
regions_filename = args.regions_filename
sequencing_files = args.seq_files
max_transcript_length = args.max_transcript_length
max_threads = args.threads
region_length = determine_region_length(regions_filename)
if region_length != 1:
verify_region_length_is_even(region_length)
return regions_filename, sequencing_files, max_transcript_length, max_threads
def parse_input(args):
def positive_float(num):
try:
val = float(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
def positive_int(num):
try:
val = int(num)
if val <= 0:
raise Exception("Go to the except")
except:
raise argparse.ArgumentTypeError(num + " must be positive")
return val
parser = argparse.ArgumentParser(prog='PolTools region_heatmap')
parser.add_argument('read_type',
metavar='read type',
type=str,
choices=["five", "three", "whole"],
help='either five, three, or whole')
parser.add_argument(
'regions_file',
metavar='regions_file',
type=str,
help=
'Bed formatted file containing all the regions you want to average the sequences'
)
parser.add_argument(
'-s',
'--seq_file',
action='append',
nargs=2,
metavar=('seq_file', 'spike_in'),
required=True,
help=
'Provide the sequencing file with its correction factor. You can supply '
'more than one sequencing file by adding multiple -s arguments.')
parser.add_argument('output_prefix',
metavar='output_prefix',
type=str,
help='Prefix for the output filename')
parser.add_argument(
'-m',
'--max_black',
metavar='max_black',
dest='max_black',
type=int,
default=None,
help=
'Max black value of the heatmap. Default is the maximum possible value'
)
parser.add_argument(
'-r',
'--repeat_amount',
metavar='repeat_amount',
dest='repeat_amount',
type=int,
default=1,
help=
'Each base will be shown in this number of pixels. Default is 1 -- no repeating'
)
parser.add_argument(
'-v',
'--vertical_averaging',
metavar='vertical_averaging',
dest='vertical_averaging',
type=int,
default=1,
help=
'Average this number of rows into one row. Default is 1 -- no vertical averaging'
)
parser.add_argument(
'-g',
'--gamma',
metavar='gamma',
dest='gamma',
type=positive_float,
default=2.2,
help=
'Gamma value of the heatmap. Default is 2.2, which is no gamma correction.'
)
parser.add_argument(
'--minor_ticks',
metavar='minor_ticks',
dest='minor_ticks',
type=positive_int,
default=None,
help='Distance between minor ticks (bp). Default is no ticks.')
parser.add_argument(
'--major_ticks',
metavar='major_ticks',
dest='major_ticks',
type=positive_int,
default=None,
help='Distance between major ticks (bp). Default is no ticks.')
parser.add_argument('-t',
'--threads',
dest='threads',
metavar='threads',
type=positive_int,
nargs='?',
default=multiprocessing.cpu_count())
args = parser.parse_args(args)
verify_bed_files(args.regions_file)
region_length = determine_region_length(args.regions_file)
verify_region_length_is_even(region_length)
filenames = args.regions_file, args.output_prefix
repeat_amounts = args.repeat_amount, args.vertical_averaging
heatmap_parameters = args.max_black, args.gamma
seq_files_data = []
for dataset in args.seq_file:
seq_file, corr_factor = dataset
corr_factor = positive_float(corr_factor)
seq_files_data.append((seq_file, corr_factor))
if not os.path.isfile(seq_file):
sys.stderr.write("File " + seq_file + " was not found.\n")
sys.exit(1)
if args.minor_ticks != None and args.major_ticks != None:
tick_parameters = (args.minor_ticks * args.repeat_amount,
args.major_ticks * args.repeat_amount)
else:
tick_parameters = (None, None)
return args.read_type, filenames, seq_files_data, heatmap_parameters, repeat_amounts, tick_parameters, args.threads