def getGeneNamesFromGTF():
parser = OptionParser(usage="getGenesNames; type usage: %prog [options] -f filename")
files = OptionGroup(parser, "File input options")
files.add_option("-f", "--input_file", dest="gtf_file",
help="Provide the path to your gtf data file. Default is standard input.",
type="str", default=None)
files.add_option("-g", "--genes", dest="genes",
help="Which biotype of features to get: mRNA, tRNA, rRNA, snRNA, snoRNA",
type="str", default='tRNA')
files.add_option("-i", "--introns", dest="introns",
help="Introns? both - not discriminate; int_cont -only intron containing; int_less - only int less",
choices=["both", "int_cont", "int_less"], default="both"),
files.add_option("-o", "--output_file", dest="output_file",
help="Use this flag to provide an output file name. Default is standard output.", default=None)
parser.add_option_group(files)
(options, args) = parser.parse_args()
### By default, input and output are expected from the standard input or standard output.
signal(SIGPIPE,SIG_DFL)
outfile = sys.stdout
if options.output_file:
outfile = open(options.output_file, "w")
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
names_list = list()
### for loop extracting tRNA names
for line in open(gtm.getGTF(options.gtf_file), "r"):
if not line.startswith('#'):
line_elements = line.strip().split('\t')
# assert len(line_elements) == 10, 'Unexpected number of elements found in gtf line: ' + line
if str(line_elements[1]) == options.genes:
try:
name = re.search("gene_name\s\"(.*?)\"", str(line_elements[8])).group(1)
except:
pass
# name = re.search("gene_id\s\"(.*?)\"", str(line_elements[8])).group(1)
if options.introns == "both":
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
elif options.introns == "int_cont":
if gtf.intronCoordinates(name):
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
elif options.introns == "int_less":
if not gtf.intronCoordinates(name):
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
outfile.write('\n'.join(names_list)+'\n')
outfile.close()
def getFastaSeqs():
parser = OptionParser(usage="List of genes as std input and parameters")
parser.add_option("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type="str", default=None)
parser.add_option("-f", "--fasta_file", dest="fasta_file", help="Provide the path to your fasta file.",
type="str", default=None)
parser.add_option("-t", "--tab_file", dest="tab_file", help="Provide the path to your genom tab file.",
type="str", default=None)
parser.add_option("-r", "--ranges", dest="ranges",
help="Provide ranges(flanks) for genes.",
type="int", default=0)
parser.add_option("-a", "--5end", dest="five_end",
help="Set up 5` flank. If minus then print only 3` end. Python slicing [a:b] i.e. [200:401] - from 200 to 400; [-200:] - last 200; "
"[:-200] from begining till -200 before end",
type="int", default=None)
parser.add_option("-b", "--3end", dest="three_end",
help="Set up 5` flank. If minus then print only 5` end. Python slicing [a:b]",
type="int", default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE,SIG_DFL) # to manage with stdin and stdout
#crating gtf object
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
gtf.read_FASTA(gtm.getFASTA(options.fasta_file))
gtf.read_TAB(gtm.getTAB(options.tab_file))
for i in sys.stdin:
gene_name = str(i.strip())
genomic_seq = gtf.genomicSequence(gene_name, ranges=options.ranges)
print '>'+gene_name
print genomic_seq[options.five_end:options.three_end]+'\n'
def getNameFromId4Tab():
parser = OptionParser(usage="usage: List of genes as std input")
parser.add_option("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type="str",
default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE, SIG_DFL)
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
id_to_gene = dict()
for gene_name in gtf.genes:
gene_id = gtf.genes[gene_name]['gene_id']
id_to_gene[gene_id] = gene_name
for i in sys.stdin:
i_elem = i.strip().split("\t")
gene_id = i_elem[0]
seq = i_elem[1]
gene_name = id_to_gene[gene_id]
print gene_name + '\t' + seq
def mRNA():
usage = "Usage: To create input concat file run novo2concat.py"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type=str, default=None)
files.add_argument("-i", "--input_file", dest="input_file", help="Provide the path to your concat file. REQUIRED.",
metavar="FILE", default=None, required=True)
files.add_argument("--5flank", dest="five_prime_flank", type=int, help="Set up 5 prime flank in pileup file. Default = 0", default=0)
files.add_argument("--3flank", dest="three_prime_flank", type=int, help="Set up 3 prime flank in pileup file. Default = 0", default=0)
universal = parser.add_argument_group('Universal options')
universal.add_argument("-t", "--hits_threshold", dest="hits_threshold", type=int, help="Set up threshold for pileup. Default 0 reads",
default=0)
universal.add_argument("-n", "--normalized", dest="normalized", action="store_true", help="Use when you want to work on data normalized 'reads per Milion'. Default: False", default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument("-p", "--prefix", dest="out_prefix", type=str, help="Prefix for output files. Default to standard output. Not supported for -o ratio.", default=None)
output.add_argument("-o", dest="output_files", choices=['bind'], help="Select from following options:"
"(1) Print binding windows in fasta file", default="bind")
output.add_argument("--peaks", dest="print_peaks", action="store_true", help="print peaks on plots. Default: False", default=False)
output.add_argument("--valleys", dest="print_valleys", action="store_true", help="print valleys on plots. Default: False", default=False)
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument("--lookahead", dest="lookahead", type=int, help="Set up lookahead parameter for pypeaks function. Default = 20", default=20)
special.add_argument("-w", "--window", dest="window", type=int, help="Set up size of window for bind calculation (-o bind). Default: 10",
default=10)
special.add_argument("-e", dest="experiment_to_use", type=str, help="For -o bind, which experiment to use.")
# special.add_argument("--ntotal", dest="ntotal", action="store_true", help="Normalize data to sum of all reads (sum = 1). Default: False", default=False)
# special.add_argument("--nmax", dest="nmax", action="store_true", help="Normalize data to maximal value (max = 1). Default: False", default=False)
# special.add_argument("-a", dest="to_divide", type=str, help="experiment to divide by -b (-o fig_ratio)",
# default=None)
# special.add_argument("-b", dest="divisor", type=str, help="experiment being divisor for -a (-o fig_ratio)",
# default=None)
options = parser.parse_args()
#checking input
input_file = options.input_file
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix+'_'
else:
prefix = str()
if options.normalized == True:
prefix = 'normalized_'+prefix
data = mRNAFromConcat(gtf_file=gtm.getGTF(options.gtf_file), five_prime_flank=options.five_prime_flank, three_prime_flank=options.three_prime_flank,
hits_threshold=options.hits_threshold, lookahead=options.lookahead, prefix=prefix, npM=options.normalized)
if options.output_files == "bind":
#reading csv file
data.read_csv(input_file, use='deletions')
#calculating readthrough, details, normalize
# data.calculate(details=options.details, ntotal=options.ntotal, nmax=options.nmax)
data.bind(exp_to_use=options.experiment_to_use, window=options.window)
print '# Done.'
def getFastaSeqs():
parser = OptionParser(usage="List of genes as std input and parameters")
parser.add_option("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type="str",
default=None)
parser.add_option("-f",
"--fasta_file",
dest="fasta_file",
help="Provide the path to your fasta file.",
type="str",
default=None)
parser.add_option("-t",
"--tab_file",
dest="tab_file",
help="Provide the path to your genom tab file.",
type="str",
default=None)
parser.add_option("-r",
"--ranges",
dest="ranges",
help="Provide ranges(flanks) for genes.",
type="int",
default=0)
parser.add_option(
"-a",
"--5end",
dest="five_end",
help=
"Set up 5` flank. If minus then print only 3` end. Python slicing [a:b] i.e. [200:401] - from 200 to 400; [-200:] - last 200; "
"[:-200] from begining till -200 before end",
type="int",
default=None)
parser.add_option(
"-b",
"--3end",
dest="three_end",
help=
"Set up 5` flank. If minus then print only 5` end. Python slicing [a:b]",
type="int",
default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE, SIG_DFL) # to manage with stdin and stdout
#crating gtf object
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
gtf.read_FASTA(gtm.getFASTA(options.fasta_file))
gtf.read_TAB(gtm.getTAB(options.tab_file))
for i in sys.stdin:
gene_name = str(i.strip())
genomic_seq = gtf.genomicSequence(gene_name, ranges=options.ranges)
print '>' + gene_name
print genomic_seq[options.five_end:options.three_end] + '\n'
gtf.codingSequence()
def rRNA():
usage = "Usage: create pileups with pyPileup (pyCRAC package) then in directory containing pileup files type run i.e.:"+"\n"+ \
"cat file.concat | gwiderRNA.py or gwiderRNA.py -i file.concat"
parser = OptionParser(usage=usage)
parser.add_option("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
metavar="FILE", default=None)
parser.add_option("-i", dest="input_file", help="Provide the path to your concat file.",
metavar="FILE", default=None)
parser.add_option("--5flank", dest="five_prime_flank", type="int", help="Set up 5 prime flank in pileup file. Default = 1000", default=1000)
parser.add_option("--3flank", dest="three_prime_flank", type="int", help="Set up 3 prime flank in pileup file. Default = 1000", default=1000)
parser.add_option("-l", "--lookahead", dest="lookahead", type="int", help="Set up lookahead parameter for pypeaks function. Default = 20", default=20)
parser.add_option("-t", "--hits_threshold", dest="hits_threshold", type="int", help="Set up threshold for pileup. Default 100 reads",
default=100)
# parser.add_option("-r", "--readthrough", dest="readthrough", type="int", help="Set up when readthrough should start countin. Default: 0",
# default=0)
parser.add_option("-p", "--prefix", dest="out_prefix", type="str", help="Prefix for output files. Default to standard output", default=None)
parser.add_option("--peaks", dest="print_peaks", action="store_true", help="Add into command line if you want to print peaks on plots. Default: False",
default=False)
parser.add_option("-o", "--output", dest="output_files", choices=["std", "ratio", "single", "correlations", "ratio_smooth"], help="Select from following options: (1) std - RDN37-1; experiment after experimen ;"+'\n'
"(2)ratio - ratio for -a divided by -b; (3)single - plot RDN37-1 plots 1 per page; (4) correlations - calculate correlations for different experiments; (5)ratio_smooth - ratio for -a divided by -b", default="std")
parser.add_option("-a", dest="to_divide", type="str", help="experiment to divide by -b", default=None)
parser.add_option("-b", dest="divisor", type="str", help="experiment being divisor for -a", default=None)
parser.add_option("-n", "--normalized", dest="normalized", action="store_true", help="Use when you want to work on data normalized reads per Milion? Default: False", default=False)
(options, args) = parser.parse_args()
gtf_file = gtm.getGTF(options.gtf_file)
if options.out_prefix:
prefix = options.out_prefix+'_'
else:
prefix = str()
if options.output_files == "ratio":
options.normalized = True
data = rRNAFromConcat(gtf_file=gtf_file, five_prime_flank=options.five_prime_flank, print_peaks=options.print_peaks,
three_prime_flank=options.three_prime_flank, hits_threshold=options.hits_threshold, lookahead=options.lookahead, prefix=prefix, normalized=options.normalized)
data.read_csv(options.input_file)
data.slice_data()
if options.print_peaks == True:
data.find_peaks()
if options.output_files == "std":
data.print_rRNA() # RDN37 should be prepared with 1000 nt flanks
if options.output_files == "single":
data.single_rRNA() # RDN37 should be prepared with 1000 nt flanks
if options.output_files == "ratio":
# data.fig_ratio(options.to_divide, options.divisor) # plots ratio to_divide/divisor
data.fig_log2ratio(options.to_divide, options.divisor) # plots log2 ratio to_divide/divisor
if options.output_files == "ratio_smooth":
data.fig_smoothlog2ratio(options.to_divide, options.divisor) # plots log2 ratio to_divide/divisor using smoothed data
if options.output_files == "correlations":
data.correlations()
print '# Done.'
def getGeneLength():
parser = OptionParser(usage="usage: List of genes as std input")
parser.add_option("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type="str", default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE,SIG_DFL)
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
for i in sys.stdin:
gene_name = str(i.strip())
gene_length = gtf.geneLength(gene_name)
print gene_name+"\t"+str(gene_length)
def getGeneLength():
parser = OptionParser(usage="usage: List of genes as std input")
parser.add_option("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type="str",
default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE, SIG_DFL)
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
for i in sys.stdin:
gene_name = str(i.strip())
gene_length = gtf.geneLength(gene_name)
print gene_name + "\t" + str(gene_length)
def getNameFromId():
parser = OptionParser(usage="usage: List of genes as std input")
parser.add_option("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type="str", default=None)
(options, args) = parser.parse_args()
signal(SIGPIPE,SIG_DFL)
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
id_to_gene = dict()
for gene_name in gtf.genes:
gene_id = gtf.genes[gene_name]['gene_id']
id_to_gene[gene_id] = gene_name
for i in sys.stdin:
gene_id = str(i.strip())
gene_name = id_to_gene[gene_id]
print gene_name
def hittable():
## option parser
usage = "For more options type -h"
description = "Downstream analysis on hittables crated by pyReadCounter. Chose type of analysys Usage: create hittables using pyReadCounter then run script in the folder containing hittables"
parser = argparse.ArgumentParser(usage=usage, description=description)
#functions
parser.add_argument('--output', required=True, dest="function", choices=['correlation', 'count', 'piechart'], help='REQUIRED, Calculate "correlations"; '
'"count" hittables for further analysis. Ideal to work with multiple experiments; '
'Plot "piechart"s for hittable classes')
# parser for input files options
files = parser.add_argument_group('Input file options')
files.add_argument("-g", dest="gtf_file", help="Provide the path to your gtf file.", type=str, default=None)
files.add_argument("--stdin", dest="stdin", action="store_true", help="Use standard input instead ./*hittable* Default: False", default=False)
# universal options
universal = parser.add_argument_group('universal options')
universal.add_argument("-n", dest="normalized", action="store_true", help="Use when you want to work on data normalized 'reads per Milion'. Default: False", default=False)
universal.add_argument("-w", dest="whole_name", action="store_true", help="As defauls scripts takes 'a_b_c' from a_b_c_hittable_reads.txt as experiment name. Use this option if your file names do not suit to this pattern. Default: False", default=False)
universal.add_argument("-p", dest="out_prefix", type=str, help="Prefix for output files.", default=None)
# parser specific for counts
corr_group = parser.add_argument_group("counts options")
corr_group.add_argument("--rpkm", dest="rpkm", action="store_true", help="Use RPKM instead of hits. Default: False", default=False)
# parser specific for correlations
corr_group = parser.add_argument_group("correlation options")
corr_group.add_argument("-c", dest="gene_class", action="store_true", help="Calculate Pearson coefficient for different classes separately. Default: False", default=False)
corr_group.add_argument("-o", dest="output", choices=["p", "s", "k", "a"], help="Select from following options: p - Pearson (standard correlation coefficient); s - Spearman rank correlation; k - Kendall Tau correlation coefficient; a - all at once", default="p")
#parser specific for piecharts
piechart_group = parser.add_argument_group("piechart options")
piechart_group.add_argument("-s", "--single", dest="print_single", help="Print hittables in single files",
action="store_true", default=False)
options = parser.parse_args()
## Creating HittableClass object
data = ghc.HittableClass(gtf=gtm.getGTF(options.gtf_file), whole_name=options.whole_name, n_rpM=options.normalized, out_prefix=options.out_prefix, read_stdin=options.stdin)
#running chosen function
if options.function == 'correlation':
data.correlation(output=options.output, gene_class=options.gene_class)
elif options.function == 'count':
data.count(normalize=options.normalized, use_RPKM=options.rpkm)
elif options.function == 'piechart':
data.plot(print_single=options.print_single)
print "Done."
def rRNA():
usage = "Usage: create pileups with pyPileup (pyCRAC package) then in directory containing pileup files type run i.e.:"+"\n"+ \
"cat file.concat | gwiderRNA.py or gwiderRNA.py -i file.concat"
parser = OptionParser(usage=usage)
parser.add_option("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
metavar="FILE",
default=None)
parser.add_option("-i",
dest="input_file",
help="Provide the path to your concat file.",
metavar="FILE",
default=None)
parser.add_option(
"--5flank",
dest="five_prime_flank",
type="int",
help="Set up 5 prime flank in pileup file. Default = 1000",
default=1000)
parser.add_option(
"--3flank",
dest="three_prime_flank",
type="int",
help="Set up 3 prime flank in pileup file. Default = 1000",
default=1000)
parser.add_option(
"-l",
"--lookahead",
dest="lookahead",
type="int",
help="Set up lookahead parameter for pypeaks function. Default = 20",
default=20)
parser.add_option("-t",
"--hits_threshold",
dest="hits_threshold",
type="int",
help="Set up threshold for pileup. Default 100 reads",
default=100)
# parser.add_option("-r", "--readthrough", dest="readthrough", type="int", help="Set up when readthrough should start countin. Default: 0",
# default=0)
parser.add_option(
"-p",
"--prefix",
dest="out_prefix",
type="str",
help="Prefix for output files. Default to standard output",
default=None)
parser.add_option(
"--peaks",
dest="print_peaks",
action="store_true",
help=
"Add into command line if you want to print peaks on plots. Default: False",
default=False)
parser.add_option(
"-o",
"--output",
dest="output_files",
choices=["std", "ratio", "single", "correlations", "ratio_smooth"],
help=
"Select from following options: (1) std - RDN37-1; experiment after experimen ;"
+ '\n'
"(2)ratio - ratio for -a divided by -b; (3)single - plot RDN37-1 plots 1 per page; (4) correlations - calculate correlations for different experiments; (5)ratio_smooth - ratio for -a divided by -b",
default="std")
parser.add_option("-a",
dest="to_divide",
type="str",
help="experiment to divide by -b",
default=None)
parser.add_option("-b",
dest="divisor",
type="str",
help="experiment being divisor for -a",
default=None)
parser.add_option(
"-n",
"--normalized",
dest="normalized",
action="store_true",
help=
"Use when you want to work on data normalized reads per Milion? Default: False",
default=False)
(options, args) = parser.parse_args()
gtf_file = gtm.getGTF(options.gtf_file)
if options.out_prefix:
prefix = options.out_prefix + '_'
else:
prefix = str()
if options.output_files == "ratio":
options.normalized = True
data = rRNAFromConcat(gtf_file=gtf_file,
five_prime_flank=options.five_prime_flank,
print_peaks=options.print_peaks,
three_prime_flank=options.three_prime_flank,
hits_threshold=options.hits_threshold,
lookahead=options.lookahead,
prefix=prefix,
normalized=options.normalized)
data.read_csv(options.input_file)
data.slice_data()
if options.print_peaks == True:
data.find_peaks()
if options.output_files == "std":
data.print_rRNA() # RDN37 should be prepared with 1000 nt flanks
if options.output_files == "single":
data.single_rRNA() # RDN37 should be prepared with 1000 nt flanks
if options.output_files == "ratio":
# data.fig_ratio(options.to_divide, options.divisor) # plots ratio to_divide/divisor
data.fig_log2ratio(
options.to_divide,
options.divisor) # plots log2 ratio to_divide/divisor
if options.output_files == "ratio_smooth":
data.fig_smoothlog2ratio(
options.to_divide, options.divisor
) # plots log2 ratio to_divide/divisor using smoothed data
if options.output_files == "correlations":
data.correlations()
print '# Done.'
def hittable():
## option parser
usage = "For more options type -h"
description = "Downstream analysis on hittables crated by pyReadCounter. Chose type of analysys Usage: create hittables using pyReadCounter then run script in the folder containing hittables"
parser = argparse.ArgumentParser(usage=usage, description=description)
#functions
parser.add_argument(
'--output',
required=True,
dest="function",
choices=['correlation', 'count', 'piechart', 'classes'],
help='REQUIRED, Calculate "correlations"; '
'"count" hittables for further analysis. Ideal to work with multiple experiments; '
'Plot "piechart"s for hittable classes')
# parser for input files options
files = parser.add_argument_group('Input file options')
files.add_argument("-g",
dest="gtf_file",
help="Provide the path to your gtf file.",
type=str,
default=None)
files.add_argument(
"--stdin",
dest="stdin",
action="store_true",
help="Use standard input instead ./*hittable* Default: False",
default=False)
# universal options
universal = parser.add_argument_group('universal options')
universal.add_argument(
"-n",
dest="normalized",
action="store_true",
help=
"Use when you want to work on data normalized 'reads per Milion'. Default: False",
default=False)
universal.add_argument(
"-w",
dest="whole_name",
action="store_true",
help=
"As defauls scripts takes 'a_b_c' from a_b_c_hittable_reads.txt as experiment name. Use this option if your file names do not suit to this pattern. Default: False",
default=False)
universal.add_argument("-p",
dest="out_prefix",
type=str,
help="Prefix for output files.",
default=None)
# parser specific for counts
corr_group = parser.add_argument_group("counts options")
corr_group.add_argument("--rpkm",
dest="rpkm",
action="store_true",
help="Use RPKM instead of hits. Default: False",
default=False)
# parser specific for correlations
corr_group = parser.add_argument_group("correlation options")
corr_group.add_argument(
"-c",
dest="gene_class",
action="store_true",
help=
"Calculate Pearson coefficient for different classes separately. Default: False",
default=False)
corr_group.add_argument(
"-o",
dest="output",
choices=["p", "s", "k", "a"],
help=
"Select from following options: p - Pearson (standard correlation coefficient); s - Spearman rank correlation; k - Kendall Tau correlation coefficient; a - all at once",
default="p")
#parser specific for piecharts
piechart_group = parser.add_argument_group("piechart options")
piechart_group.add_argument("-s",
"--single",
dest="print_single",
help="Print hittables in single files",
action="store_true",
default=False)
options = parser.parse_args()
## Creating HittableClass object
data = ghc.HittableClass(gtf=gtm.getGTF(options.gtf_file),
whole_name=options.whole_name,
n_rpM=options.normalized,
out_prefix=options.out_prefix,
read_stdin=options.stdin)
#running chosen function
if options.function == 'correlation':
data.correlation(output=options.output, gene_class=options.gene_class)
elif options.function == 'count':
data.count(normalize=options.normalized, use_RPKM=options.rpkm)
elif options.function == 'piechart':
data.plot(print_single=options.print_single)
elif options.function == 'classes':
data.classes_to_tab()
print "Done."
def tRNA():
usage = "Usage: UNDER CONSTRUCTION - not all functions are available. To create concat file run novo2concat"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type=str,
default=None)
files.add_argument("-i",
"--input_file",
dest="input_file",
help="Provide the path to your concat file. REQUIRED.",
metavar="FILE",
default=None,
required=True)
files.add_argument(
"--5flank",
dest="five_prime_flank",
type=int,
help="Set up 5 prime flank in pileup file. Default = 250",
default=250)
files.add_argument(
"--3flank",
dest="three_prime_flank",
type=int,
help="Set up 3 prime flank in pileup file. Default = 250",
default=250)
universal = parser.add_argument_group('Universal options')
universal.add_argument("-t",
"--hits_threshold",
dest="hits_threshold",
type=int,
help="Set up threshold for pileup. Default 0 reads",
default=0)
universal.add_argument("-r",
"--readthrough",
dest="readthrough",
type=int,
help="Set up when readthrough starts. Default: 15",
default=15)
universal.add_argument(
"-n",
"--normalized",
dest="normalized",
action="store_true",
help=
"Use when you want to work on data normalized 'reads per Milion'. Default: False",
default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument(
"-p",
"--prefix",
dest="out_prefix",
type=str,
help=
"Prefix for output files. Default to standard output. Not supported for -o ratio.",
default=None)
output.add_argument(
"-d",
"--details",
dest="details",
action="store_true",
help=
"Print details in text file. WARNING: works only with one experiment.",
default=False)
output.add_argument(
"-o",
dest="output_files",
choices=[
"fig", "fig_std", "fig_tight", "fig_ratio", "fig_boxes", "nuc3",
"nuc5", "nuc_gene", "nuc_energy", "termination_valleys",
"termination", "termination_text", "stat_text", "both"
],
help="Select from following options:"
"(1) fig - plot tRNA genes coverage; (2) figstd - plot gene after gene; (3) fig_tight; (4) fig_ratio - log2 for -a divided by -b, uses normalized data"
"(5) fig_boxes - mark A and B boxes (provide path to boxes position file)"
"(6) nuc3 - for nucleotide 3' end resolution; (7) nuc_gene - for nucleotide resolution of gene only"
"(8) nuc_energy - plots 3' end under nucleotide resolution with energy plots"
"(9) termination_valleys - for each valley calculate termination efficiency"
"(10) termination - calculate termination efficiency for last 20 nt"
"(11) termination_text - calculate termination efficiency for first 20 nt of 3' end and print text file"
"(12) stat_text - tab-deliminated; (13) both - fig and stat_text; (14) - nuc5 - for nucleotide 5' end resolution",
default="both")
output.add_argument("--peaks",
dest="print_peaks",
action="store_true",
help="print peaks on plots. Default: False",
default=False)
output.add_argument("--valleys",
dest="print_valleys",
action="store_true",
help="print valleys on plots. Default: False",
default=False)
output.add_argument("--mark",
dest="mark",
choices=["A", "T", "C", "G"],
help="mark nucleotide on plots. Default: None",
default=None)
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument(
"--lookahead",
dest="lookahead",
type=int,
help="Set up lookahead parameter for pypeaks function. Default = 20",
default=20)
special.add_argument(
"-w",
"--window",
dest="window",
type=int,
help=
"Set up size of window for energy calculation (-o nuc_energy). Default: 5",
default=5)
special.add_argument(
"--ntotal",
dest="ntotal",
action="store_true",
help="Normalize data to sum of all reads (sum = 1). Default: False",
default=False)
special.add_argument(
"--nmax",
dest="nmax",
action="store_true",
help="Normalize data to maximal value (max = 1). Default: False",
default=False)
special.add_argument("-a",
dest="to_divide",
type=str,
help="experiment to divide by -b (-o fig_ratio)",
default=None)
special.add_argument("-b",
dest="divisor",
type=str,
help="experiment being divisor for -a (-o fig_ratio)",
default=None)
special.add_argument(
"--abox",
dest="abox_file",
help="Provide the path to your tab file with A box start.",
metavar="FILE",
default=None)
special.add_argument(
"--bbox",
dest="bbox_file",
help="Provide the path to your tab file with B box start.",
metavar="FILE",
default=None)
options = parser.parse_args()
#checking input
input_file = options.input_file
if options.output_files == 'fig_boxes' and (options.abox_file == None
or options.bbox_file == None):
exit(
'Please provide path to both box.tab files using options --abox and --bbox.'
)
if options.output_files == 'fig_ratio' and (options.to_divide == None
or options.divisor == None):
exit('Please provide experiments names using options -a and -b.')
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix + '_'
filename = options.out_prefix + '_rt' + str(
options.readthrough) + '_l' + str(options.lookahead) + '_t' + str(
options.hits_threshold) + '.list'
else:
prefix = str()
filename = 'rt' + str(options.readthrough) + '_l' + str(
options.lookahead) + '_t' + str(options.hits_threshold) + '.list'
if options.print_peaks == True:
prefix = prefix + 'peaks_'
if options.print_valleys == True:
prefix = prefix + 'valleys_'
if options.normalized == True:
prefix = 'normalized_' + prefix
#setting up dependencies
if options.output_files == "fig_ratio":
options.normalized = True
if options.output_files == 'termination_valleys':
options.print_peaks = True
options.print_valleys = True
data = tRNAFromConcatv2(gtf_file=gtm.getGTF(options.gtf_file),
five_prime_flank=options.five_prime_flank,
print_valleys=options.print_valleys,
print_peaks=options.print_peaks,
readthrough_start=options.readthrough,
three_prime_flank=options.three_prime_flank,
hits_threshold=options.hits_threshold,
lookahead=options.lookahead,
prefix=prefix,
normalized=options.normalized)
#reading csv file
if options.output_files != "fig_ratio":
data.read_csv(input_file, null_substitution=False)
# elif options.output_files == "fig_ratio":
# data.read_csv(input_file, null_substitution=True) ## makes all 0 as 1 in hittable
#finding peaks
if (options.print_peaks == True or options.print_valleys
== True) and options.output_files != "fig_ratio":
data.find_peaks()
#calculating readthrough, details, normalize
if options.output_files != "fig_ratio":
data.calculate(details=options.details,
ntotal=options.ntotal,
nmax=options.nmax)
elif options.output_files == "fig_ratio":
data.calculate(details=options.details,
ntotal=options.ntotal,
nmax=options.nmax,
pscounts=True)
#making text files
if options.output_files == "stat_text" or options.output_files == "both":
text_file = open(filename, "w")
data.make_text_file(text_file,
details=options.details,
ntotal=options.ntotal,
nmax=options.nmax)
if options.output_files == "fig" or options.output_files == "both":
data.slice_dataframe()
data.fig_gene_pp()
if options.output_files == "fig_tight":
data.slice_dataframe()
data.fig_gene_pp_tight()
#marks all T on the plots
if options.output_files == "markT":
data.slice_dataframe()
data.mark_T()
#marks all T and CG on the plots
if options.output_files == "markTCG":
data.slice_dataframe()
data.mark_T(anti_plot=True)
if options.output_files == "fig_ratio":
data.slice_dataframe()
data.fig_ratio(options.to_divide, options.divisor)
if options.output_files == "nuc3":
data.fig_3end_nucleotide_resolution()
if options.output_files == "nuc5":
data.fig_5end_nucleotide_resolution()
if options.output_files == "nuc_gene":
print 'Needs update. Talk to Tomasz.'
# data.fig_nucleotide_gene()
# if options.output_files == "nuc_energy":
# data.fig_energy(options.window)
if options.output_files == "fig_std":
data.slice_dataframe()
data.fig_gene_after_gene()
if options.output_files == "fig_boxes":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.fig_boxes(open(options.abox_file), open(options.bbox_file))
#
if options.output_files == "termination_valleys":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.termination_efficency_valleys()
#
if options.output_files == "termination":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.termination_efficency()
if options.output_files == "termination_text":
data.calculate_dG()
text_file = open(filename, "w")
data.make_text_file(text_file, print_dG=True)
print '# Done.'
def tRNA():
usage = "Usage: UNDER CONSTRUCTION - not all functions are available. To create concat file run novo2concat"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type=str, default=None)
files.add_argument("-i", "--input_file", dest="input_file", help="Provide the path to your concat file. REQUIRED.",
metavar="FILE", default=None, required=True)
files.add_argument("--5flank", dest="five_prime_flank", type=int, help="Set up 5 prime flank in pileup file. Default = 250", default=250)
files.add_argument("--3flank", dest="three_prime_flank", type=int, help="Set up 3 prime flank in pileup file. Default = 250", default=250)
universal = parser.add_argument_group('Universal options')
universal.add_argument("-t", "--hits_threshold", dest="hits_threshold", type=int, help="Set up threshold for pileup. Default 0 reads",
default=0)
universal.add_argument("-r", "--readthrough", dest="readthrough", type=int, help="Set up when readthrough starts. Default: 15",
default=15)
universal.add_argument("-n", "--normalized", dest="normalized", action="store_true", help="Use when you want to work on data normalized 'reads per Milion'. Default: False", default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument("-p", "--prefix", dest="out_prefix", type=str, help="Prefix for output files. Default to standard output. Not supported for -o ratio.", default=None)
output.add_argument("-d", "--details", dest="details", action="store_true", help="Print details in text file. WARNING: works only with one experiment.", default=False)
output.add_argument("-o", dest="output_files", choices=["fig", "fig_std", "fig_tight", "fig_ratio", "fig_boxes", "nuc3", "nuc5", "nuc_gene", "nuc_energy", "termination_valleys", "termination", "termination_text", "stat_text", "both"], help="Select from following options:"
"(1) fig - plot tRNA genes coverage; (2) figstd - plot gene after gene; (3) fig_tight; (4) fig_ratio - log2 for -a divided by -b, uses normalized data"
"(5) fig_boxes - mark A and B boxes (provide path to boxes position file)"
"(6) nuc3 - for nucleotide 3' end resolution; (7) nuc_gene - for nucleotide resolution of gene only"
"(8) nuc_energy - plots 3' end under nucleotide resolution with energy plots"
"(9) termination_valleys - for each valley calculate termination efficiency"
"(10) termination - calculate termination efficiency for last 20 nt"
"(11) termination_text - calculate termination efficiency for first 20 nt of 3' end and print text file"
"(12) stat_text - tab-deliminated; (13) both - fig and stat_text; (14) - nuc5 - for nucleotide 5' end resolution", default="both")
output.add_argument("--peaks", dest="print_peaks", action="store_true", help="print peaks on plots. Default: False", default=False)
output.add_argument("--valleys", dest="print_valleys", action="store_true", help="print valleys on plots. Default: False", default=False)
output.add_argument("--mark", dest="mark", choices=["A","T","C","G"], help="mark nucleotide on plots. Default: None", default=None)
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument("--lookahead", dest="lookahead", type=int, help="Set up lookahead parameter for pypeaks function. Default = 20", default=20)
special.add_argument("-w", "--window", dest="window", type=int, help="Set up size of window for energy calculation (-o nuc_energy). Default: 5",
default=5)
special.add_argument("--ntotal", dest="ntotal", action="store_true", help="Normalize data to sum of all reads (sum = 1). Default: False", default=False)
special.add_argument("--nmax", dest="nmax", action="store_true", help="Normalize data to maximal value (max = 1). Default: False", default=False)
special.add_argument("-a", dest="to_divide", type=str, help="experiment to divide by -b (-o fig_ratio)",
default=None)
special.add_argument("-b", dest="divisor", type=str, help="experiment being divisor for -a (-o fig_ratio)",
default=None)
special.add_argument("--abox", dest="abox_file", help="Provide the path to your tab file with A box start.",
metavar="FILE", default=None)
special.add_argument("--bbox", dest="bbox_file", help="Provide the path to your tab file with B box start.",
metavar="FILE", default=None)
options = parser.parse_args()
#checking input
input_file = options.input_file
if options.output_files == 'fig_boxes' and ( options.abox_file == None or options.bbox_file == None ):
exit('Please provide path to both box.tab files using options --abox and --bbox.')
if options.output_files == 'fig_ratio' and ( options.to_divide == None or options.divisor == None ):
exit('Please provide experiments names using options -a and -b.')
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix+'_'
filename = options.out_prefix+'_rt'+str(options.readthrough)+'_l'+str(options.lookahead)+'_t'+str(options.hits_threshold)+'.list'
else:
prefix = str()
filename = 'rt'+str(options.readthrough)+'_l'+str(options.lookahead)+'_t'+str(options.hits_threshold)+'.list'
if options.print_peaks == True:
prefix = prefix+'peaks_'
if options.print_valleys == True:
prefix = prefix+'valleys_'
if options.normalized == True:
prefix = 'normalized_'+prefix
#setting up dependencies
if options.output_files == "fig_ratio":
options.normalized = True
if options.output_files == 'termination_valleys':
options.print_peaks = True
options.print_valleys = True
data = tRNAFromConcatv2(gtf_file=gtm.getGTF(options.gtf_file), five_prime_flank=options.five_prime_flank, print_valleys=options.print_valleys, print_peaks=options.print_peaks, readthrough_start=options.readthrough,
three_prime_flank=options.three_prime_flank, hits_threshold=options.hits_threshold, lookahead=options.lookahead, prefix=prefix, normalized=options.normalized)
#reading csv file
if options.output_files != "fig_ratio":
data.read_csv(input_file, null_substitution=False)
# elif options.output_files == "fig_ratio":
# data.read_csv(input_file, null_substitution=True) ## makes all 0 as 1 in hittable
#finding peaks
if (options.print_peaks == True or options.print_valleys == True ) and options.output_files != "fig_ratio":
data.find_peaks()
#calculating readthrough, details, normalize
if options.output_files != "fig_ratio":
data.calculate(details=options.details, ntotal=options.ntotal, nmax=options.nmax)
elif options.output_files == "fig_ratio":
data.calculate(details=options.details, ntotal=options.ntotal, nmax=options.nmax, pscounts=True)
#making text files
if options.output_files == "stat_text" or options.output_files == "both":
text_file = open(filename, "w")
data.make_text_file(text_file, details=options.details, ntotal=options.ntotal, nmax=options.nmax)
if options.output_files == "fig" or options.output_files == "both":
data.slice_dataframe()
data.fig_gene_pp()
if options.output_files == "fig_tight":
data.slice_dataframe()
data.fig_gene_pp_tight()
#marks all T on the plots
if options.output_files == "markT":
data.slice_dataframe()
data.mark_T()
#marks all T and CG on the plots
if options.output_files == "markTCG":
data.slice_dataframe()
data.mark_T(anti_plot=True)
if options.output_files == "fig_ratio":
data.slice_dataframe()
data.fig_ratio(options.to_divide, options.divisor)
if options.output_files == "nuc3":
data.fig_3end_nucleotide_resolution()
if options.output_files == "nuc5":
data.fig_5end_nucleotide_resolution()
if options.output_files == "nuc_gene":
print 'Needs update. Talk to Tomasz.'
# data.fig_nucleotide_gene()
# if options.output_files == "nuc_energy":
# data.fig_energy(options.window)
if options.output_files == "fig_std":
data.slice_dataframe()
data.fig_gene_after_gene()
if options.output_files == "fig_boxes":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.fig_boxes(open(options.abox_file), open(options.bbox_file))
#
if options.output_files == "termination_valleys":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.termination_efficency_valleys()
#
if options.output_files == "termination":
print 'Needs update. Talk to Tomasz.'
data.slice_dataframe()
# data.termination_efficency()
if options.output_files == "termination_text":
data.calculate_dG()
text_file = open(filename, "w")
data.make_text_file(text_file, print_dG=True)
print '# Done.'
def plot():
""" Script working with concat file generated by pileupsToConcat.py script. Read concat file and according to options.
Can plot intron, and peaks found by pypeaks script."""
#setup option parser
usage = "Usage: gwide function -i input -o output [options]"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type=str,
default=None)
files.add_argument("-i",
"--input_file",
dest="input_file",
help="Provide the path to your input file. Required.",
metavar="FILE",
default=None,
required=True)
# files.add_argument("--input_type", dest="input_type", choices=['concat'], help="Type of input file. Default: concat",
# type=str, default='concat')
files.add_argument("--5flank",
dest="five_prime_flank",
type=int,
help="Set up 5 prime flank. Default = 250",
default=250)
files.add_argument("--3flank",
dest="three_prime_flank",
type=int,
help="Set up 3 prime flank. Default = 250",
default=250)
files.add_argument(
"-l",
"--list_file",
dest="list_file",
help=
"Provide the path to your (tab) file genes.list. Only listed genes will be plotted. Can be aligned as second column",
type=str)
peaks = parser.add_argument_group('Option for peaks finder (pypeaks')
peaks.add_argument(
"--lookahead",
dest="lookahead",
type=int,
help="Set up lookahead parameter for pypeaks function. Default = 20",
default=20)
universal = parser.add_argument_group('Universal options')
universal.add_argument(
"-t",
"--hits_threshold",
dest="hits_threshold",
type=int,
help=
"Set up threshold for pileup. Default 100 reads. Genes with highest peak below are not included",
default=0)
universal.add_argument(
"-r",
"--readthrough",
dest="readthrough",
type=int,
help="Set up nt when readthrough should start countin. Default: 15",
default=15)
universal.add_argument(
"-n",
"--normalized",
dest="normalized",
action="store_true",
help="to work on data normalized 'reads per Milion'. Default: False",
default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument(
"-p",
"--prefix",
dest="out_prefix",
type=str,
help=
"Prefix for output files. Default to standard output. Not supported for -o ratio.",
default=None)
output.add_argument(
"-o",
"--output",
dest="output",
choices=[
"std", "ratio", "aligner", "RTendalign", "table", "Tdensity",
"makeGTF", "transcript_length", "makeRTGTF"
],
help="Select from following options:" + '\n'
"(1) std - 5` and 3` end aligned only; (2) ratio - plot gwide ratio a exp / b exp"
+ '\n'
"(3) aligner - std plus chosen aligner from file (-l option)" + '\n'
"(4) RTendalign - std and aligned to 3` end of read-through (-l option). -e works to choose experiment to align and filter"
+ '\n'
"(5) table - make *.csv file to plot heatmaps; (6) Tdensity - calculate p-value for non-canonical termination"
+ '\n'
"(7) makeGTF - make GTF file with transcripts length ; (8) transcript_length - save *.txt file with trancripts length for all experiment; "
"(9) makeRTGTF - make GTF with tRNA extensions only",
default="std")
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument(
"--ntotal",
dest="ntotal",
action="store_true",
help="Normalize to sum of all reads (sum = 1). Default: False",
default=False)
special.add_argument(
"--nmax",
dest="nmax",
action="store_true",
help="Normalize to maximal value (max = 1). Default: False",
default=False)
special.add_argument(
"--publish",
dest="publish",
action="store_true",
help=
"Print plots as separate figures in publication quality. Works with -o ratio and std",
default=False)
special.add_argument(
"--LRR",
dest="left_right_ratio",
action="store_true",
help=
"Print ratio between left and right part of the metaprofiles (before and after aligning line)",
default=False)
special.add_argument(
"-f",
dest="filter",
type=str,
help=
"Filter in results factor_above_value; type i.e. RT_above_0.25 or a_below_1.5. To chose: RT, a, b, i, e, f, intron",
default=None)
special.add_argument(
"-e",
dest="experiment",
type=str,
help="Filter according to values from one experiment only",
default=None)
special.add_argument("-a",
dest="to_divide",
type=str,
help="experiment to divide by -b (-o ratio)",
default=None)
special.add_argument("-b",
dest="divisor",
type=str,
help="experiment being divisor for -a (-o ratio)",
default=None)
special.add_argument(
"--select",
dest="select",
type=str,
help=
"To print additional plot with selecter area and no titles keep form 200_300 (range from 200 to 300)",
default=None)
special.add_argument(
"--peak_min",
dest="peak_min",
type=int,
help="minimum of peak average for -o Tdensity. Default = 300",
default=300)
special.add_argument("--peak_size",
dest="peak_size",
type=int,
help="peak size for -o Tdensity. Default = 20",
default=20)
options = parser.parse_args()
gtf_file = gtm.getGTF(options.gtf_file)
list_file = options.list_file
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix + '_'
filename = options.out_prefix + '_rt' + str(
options.readthrough) + '_l' + str(options.lookahead) + '_t' + str(
options.hits_threshold) + '.list'
else:
prefix = str()
filename = 'rt' + str(options.readthrough) + '_l' + str(
options.lookahead) + '_t' + str(options.hits_threshold) + '.list'
if options.normalized == True:
prefix = 'nRpM_' + prefix
data = GenomeWidePlot(gtf_file=gtf_file,
five_prime_flank=options.five_prime_flank,
readthrough_start=options.readthrough,
three_prime_flank=options.three_prime_flank,
hits_threshold=options.hits_threshold,
lookahead=options.lookahead,
prefix=prefix,
normalized=options.normalized,
publish=options.publish,
left_right_ratio=options.left_right_ratio)
#setting up dependencies
if options.output == "ratio":
options.normalized = True
#reading csv file
data.read_csv(options.input_file, skip_nucleotide=True)
#plotting
if options.output == 'std':
data.calculate(details=False, ntotal=True, nmax=True)
data.std(filter=options.filter,
experiment_to_filter=options.experiment)
if options.ntotal == True:
data.std(filter=options.filter,
experiment_to_filter=options.experiment,
exp_to_use='_ntotal')
if options.nmax == True:
data.std(filter=options.filter,
experiment_to_filter=options.experiment,
exp_to_use='_nmax')
if options.output == 'aligner':
if not list_file:
print "Please provide path how to align files using -l file.list"
else:
data.calculate(details=True, ntotal=False, nmax=False)
data.read_list(list_file)
data.aligner(file=os.path.basename(list_file),
filter=options.filter,
experiment_to_filter=options.experiment)
if options.output == 'RTendalign':
data.calculate(details=True, ntotal=False, nmax=False)
data.RT_aligner(filter=options.filter,
experiment_to_align=options.experiment)
if options.output == "ratio":
data.calculate(details=False, ntotal=True, nmax=True, pscounts=True)
if options.ntotal == True:
data.ratio(to_divide=options.to_divide,
divisor=options.divisor,
exp_to_use='_ntotal',
filter=options.filter)
if options.select:
data.ratio(to_divide=options.to_divide,
divisor=options.divisor,
exp_to_use='_ntotal',
select=options.select,
filter=options.filter)
if options.nmax == True:
data.ratio(to_divide=options.to_divide,
divisor=options.divisor,
exp_to_use='_nmax',
filter=options.filter)
data.ratio(to_divide=options.to_divide,
divisor=options.divisor,
filter=options.filter)
if options.output == "makeRTGTF":
data.find_peaks()
data.makeRTGTF()
if options.output == "table":
data.table(filter=options.filter,
experiment_to_filter=options.experiment)
if options.output == "Tdensity":
data.find_peaks()
# data.calculate()
data.Tdensity(peak_min=options.peak_min, size=options.peak_size)
if options.output == "makeGTF":
data.find_peaks()
data.maketranscriptGTF()
if options.output == "transcript_length":
data.find_peaks()
data.printTrancriptLength()
print '# Done.'
def plot():
""" Script working with concat file generated by pileupsToConcat.py script. Read concat file and according to options.
Can plot intron, and peaks found by pypeaks script."""
#setup option parser
usage = "Usage: gwide function -i input -o output [options]"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type=str, default=None)
files.add_argument("-i", "--input_file", dest="input_file", help="Provide the path to your input file. Required.",
metavar="FILE", default=None, required=True)
# files.add_argument("--input_type", dest="input_type", choices=['concat'], help="Type of input file. Default: concat",
# type=str, default='concat')
files.add_argument("--5flank", dest="five_prime_flank", type=int, help="Set up 5 prime flank. Default = 250", default=250)
files.add_argument("--3flank", dest="three_prime_flank", type=int, help="Set up 3 prime flank. Default = 250", default=250)
files.add_argument("-l", "--list_file", dest="list_file", help="Provide the path to your (tab) file genes.list. Only listed genes will be plotted. Can be aligned as second column",
type=str)
peaks = parser.add_argument_group('Option for peaks finder (pypeaks')
peaks.add_argument("--lookahead", dest="lookahead", type=int, help="Set up lookahead parameter for pypeaks function. Default = 20", default=20)
universal = parser.add_argument_group('Universal options')
universal.add_argument("-t", "--hits_threshold", dest="hits_threshold", type=int, help="Set up threshold for pileup. Default 100 reads. Genes with highest peak below are not included",
default=0)
universal.add_argument("-r", "--readthrough", dest="readthrough", type=int, help="Set up nt when readthrough should start countin. Default: 15",
default=15)
universal.add_argument("-n", "--normalized", dest="normalized", action="store_true", help="to work on data normalized 'reads per Milion'. Default: False", default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument("-p", "--prefix", dest="out_prefix", type=str, help="Prefix for output files. Default to standard output. Not supported for -o ratio.", default=None)
output.add_argument("-o", "--output", dest="output", choices=["std", "ratio", "aligner", "RTendalign", "table", "Tdensity", "makeGTF", "transcript_length", "makeRTGTF"], help="Select from following options:"+'\n'
"(1) std - 5` and 3` end aligned only; (2) ratio - plot gwide ratio a exp / b exp"+'\n'
"(3) aligner - std plus chosen aligner from file (-l option)"+'\n'
"(4) RTendalign - std and aligned to 3` end of read-through (-l option). -e works to choose experiment to align and filter"+'\n'
"(5) table - make *.csv file to plot heatmaps; (6) Tdensity - calculate p-value for non-canonical termination"+'\n'
"(7) makeGTF - make GTF file with transcripts length ; (8) transcript_length - save *.txt file with trancripts length for all experiment; "
"(9) makeRTGTF - make GTF with tRNA extensions only", default="std")
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument("--ntotal", dest="ntotal", action="store_true", help="Normalize to sum of all reads (sum = 1). Default: False", default=False)
special.add_argument("--nmax", dest="nmax", action="store_true", help="Normalize to maximal value (max = 1). Default: False", default=False)
special.add_argument("--publish", dest="publish", action="store_true", help="Print plots as separate figures in publication quality. Works with -o ratio and std", default=False)
special.add_argument("--LRR", dest="left_right_ratio", action="store_true", help="Print ratio between left and right part of the metaprofiles (before and after aligning line)", default=False)
special.add_argument("-f", dest="filter", type=str, help="Filter in results factor_above_value; type i.e. RT_above_0.25 or a_below_1.5. To chose: RT, a, b, i, e, f, intron", default=None)
special.add_argument("-e", dest="experiment", type=str, help="Filter according to values from one experiment only", default=None)
special.add_argument("-a", dest="to_divide", type=str, help="experiment to divide by -b (-o ratio)",
default=None)
special.add_argument("-b", dest="divisor", type=str, help="experiment being divisor for -a (-o ratio)", default=None)
special.add_argument("--select", dest="select", type=str, help="To print additional plot with selecter area and no titles keep form 200_300 (range from 200 to 300)", default=None)
special.add_argument("--peak_min", dest="peak_min", type=int, help="minimum of peak average for -o Tdensity. Default = 300", default=300)
special.add_argument("--peak_size", dest="peak_size", type=int, help="peak size for -o Tdensity. Default = 20", default=20)
options = parser.parse_args()
gtf_file = gtm.getGTF(options.gtf_file)
list_file = options.list_file
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix+'_'
filename = options.out_prefix+'_rt'+str(options.readthrough)+'_l'+str(options.lookahead)+'_t'+str(options.hits_threshold)+'.list'
else:
prefix = str()
filename = 'rt'+str(options.readthrough)+'_l'+str(options.lookahead)+'_t'+str(options.hits_threshold)+'.list'
if options.normalized == True:
prefix = 'nRpM_'+prefix
data = GenomeWidePlot(gtf_file=gtf_file, five_prime_flank=options.five_prime_flank, readthrough_start=options.readthrough,
three_prime_flank=options.three_prime_flank, hits_threshold=options.hits_threshold, lookahead=options.lookahead,
prefix=prefix, normalized=options.normalized, publish=options.publish, left_right_ratio=options.left_right_ratio)
#setting up dependencies
if options.output == "ratio":
options.normalized = True
#reading csv file
data.read_csv(options.input_file, skip_nucleotide=True)
#plotting
if options.output == 'std':
data.calculate(details=False, ntotal=True, nmax=True)
data.std(filter=options.filter, experiment_to_filter=options.experiment)
if options.ntotal == True:
data.std(filter=options.filter, experiment_to_filter=options.experiment, exp_to_use='_ntotal')
if options.nmax == True:
data.std(filter=options.filter, experiment_to_filter=options.experiment, exp_to_use='_nmax')
if options.output == 'aligner':
if not list_file:
print "Please provide path how to align files using -l file.list"
else:
data.calculate(details=True, ntotal=False, nmax=False)
data.read_list(list_file)
data.aligner(file=os.path.basename(list_file), filter=options.filter, experiment_to_filter=options.experiment)
if options.output == 'RTendalign':
data.calculate(details=True, ntotal=False, nmax=False)
data.RT_aligner(filter=options.filter, experiment_to_align=options.experiment)
if options.output == "ratio":
data.calculate(details=False, ntotal=True, nmax=True, pscounts=True)
if options.ntotal == True:
data.ratio(to_divide=options.to_divide, divisor=options.divisor, exp_to_use='_ntotal', filter=options.filter)
if options.select:
data.ratio(to_divide=options.to_divide, divisor=options.divisor, exp_to_use='_ntotal', select=options.select, filter=options.filter)
if options.nmax == True:
data.ratio(to_divide=options.to_divide, divisor=options.divisor, exp_to_use='_nmax', filter=options.filter)
data.ratio(to_divide=options.to_divide, divisor=options.divisor, filter=options.filter)
if options.output == "makeRTGTF":
data.find_peaks()
data.makeRTGTF()
if options.output == "table":
data.table(filter=options.filter, experiment_to_filter=options.experiment)
if options.output == "Tdensity":
data.find_peaks()
# data.calculate()
data.Tdensity(peak_min=options.peak_min, size=options.peak_size)
if options.output == "makeGTF":
data.find_peaks()
data.maketranscriptGTF()
if options.output == "transcript_length":
data.find_peaks()
data.printTrancriptLength()
print '# Done.'
metavar="FILE", default=None)
files.add_argument("-w", dest="window", help="size of sliding window. Default = 10",
type=int, default=10)
files.add_argument("-a", dest="aa_type", help="Type of filter applied i.e. b_a_70 = basic aminoacides above or equal 70% within window "
"or ar_b_20 = aromatic aminoacids below 20% within window. Option for position 1: positive, negative, charged, polar, hydrophobic, aromatic"
"Options for position 2: a - above or equal. Position 3 is percent within sliding window i.e 20 = 2/10 or 3/15"
"Not used when -c used",
type=str, default=None)
files.add_argument("-c", dest="config_list", help="Config.list. Default=False",
metavar="FILE", default=None)
files.add_argument("--id", dest="id_given", help="gene ID given instead of gene names", action="store_true", default=False)
args = parser.parse_args()
#reading GTF file to GTF parser and creating id_to_gene list
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(args.gtf_file))
id_to_gene = dict()
for gene_name in gtf.genes:
gene_id = gtf.genes[gene_name]['gene_id']
id_to_gene[gene_id] = gene_name
#reading fasta file
in_seq_handle = open(args.fasta_file)
seq_dict = SeqIO.to_dict(SeqIO.parse(in_seq_handle, "fasta")) #dictionary with
in_seq_handle.close()
seq_dict_keys = seq_dict.keys()
#function to check -a or config.list syntax
def filter_parser(input_str):
#checks
#seting up option parser
parser = argparse.ArgumentParser(description='Usage: ruffus scirpt designed to make concat file from *.novo files. Make new folder, cp or ln into all novofiles and run novo2concat. IMPORTANT: name of novo file should be name of experiment')
parser.add_argument("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
type=str, default=None)
parser.add_argument("-t", "--tab_file", dest="tab_file", help="Provide the path to your tab genome file.",
type=str, default=None)
parser.add_argument("-r", dest="ranges", help="Set up ranges for pyPileup. Default = 250", default=250)
parser.add_argument("--3end", dest="three_end", help="Use pyPileup option --3end to only report counts for the 3' end of the reads. Default = False",
action="store_true", default=False)
parser.add_argument("-l", dest="list_file", help="Provide the FULL path to your gene_names.list file.", type=str, default=None, required=True)
parser.add_argument("--tree", dest="tree", help="If you want to leave tree of catalogs including pilups within. Default = None.",
action="store_true", default=False)
parser.add_argument("-p", dest="prefix", help="Prefix for concat file name", type=str, default="")
args = parser.parse_args()
gtf, tab, ranges = gtm.getGTF(args.gtf_file), gtm.getTAB(args.tab_file), str(args.ranges)
print "Using GTF file: " + gtf
print "Using TAB genome file: " + tab
#listing novo files
files = [f for f in os.listdir('.') if os.path.isfile(f) and f.endswith('.novo')] #gives list of files in current directory
directories = [re.sub(r'.novo$', '', d) for d in files]
links = []
root_dir = os.getcwd()
#making directories
for f, d in zip(files, directories):
os.mkdir(d)
os.chdir(d)
subprocess.call('ln -s ../' + f + ' ' + f, shell=True)
links.append(os.path.abspath('./'+f))
parser.add_argument("-r", dest="ranges", help="Set up ranges for pyPileup. Default = 250", default=250)
parser.add_argument("--3end", dest="three_end",
help="Use pyPileup option --3end to only report counts for the 3' end of the reads. Default = False",
action="store_true", default=False)
parser.add_argument("--5end", dest="five_end",
help="Use pyPileup option --5end to only report counts for the 5' end of the reads. Default = False",
action="store_true", default=False)
parser.add_argument("-l", dest="list_file", help="Provide the FULL path to your gene_names.list file.", type=str, default=None, required=True)
parser.add_argument("--tree", dest="tree", help="If you want to leave tree of catalogs including pilups within. Default = None.",
action="store_true", default=False)
parser.add_argument("--anti", dest="anti", help="Create additional concat file with antisense reads Default = None.",
action="store_true", default=False)
parser.add_argument("-p", dest="prefix", help="Prefix for concat file name", type=str, default="")
args = parser.parse_args()
gtf, tab, ranges = gtm.getGTF(args.gtf_file), gtm.getTAB(args.tab_file), str(args.ranges)
print "Using GTF file: " + gtf
print "Using TAB genome file: " + tab
#listing novo files
files = [f for f in os.listdir('.') if os.path.isfile(f) and f.endswith('.novo')] #gives list of files in current directory
directories = [re.sub(r'.novo$', '', d) for d in files]
links = []
root_dir = os.getcwd()
#making directories
for f, d in zip(files, directories):
os.mkdir(d)
os.chdir(d)
subprocess.call('ln -s ../' + f + ' ' + f, shell=True)
links.append(os.path.abspath('./'+f))
parser = argparse.ArgumentParser(usage=usage, formatter_class=RawTextHelpFormatter)
files = parser.add_argument_group('Options for input files')
files.add_argument("-f", dest="fasta_file", help="Provide the path to your fasta file",
metavar="FILE", default=None)
files.add_argument("-g", "--gtf_file", dest="gtf_file", help="Provide the path to your gtf file.",
metavar="FILE", default=None)
files.add_argument("-c", dest="codone", help="codone that want to count",
type=str, default='CGA')
files.add_argument("--all", dest="save_matrix", help="Saves number of all codones as a matrix. Default=False",
action="store_true", default=False)
files.add_argument("--id", dest="id_given", help="gene ID given instead of gene names", action="store_true", default=False)
args = parser.parse_args()
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(args.gtf_file))
id_to_gene = dict()
for gene_name in gtf.genes:
gene_id = gtf.genes[gene_name]['gene_id']
id_to_gene[gene_id] = gene_name
gene_name = id_to_gene[gene_id]
in_seq_handle = open(args.fasta_file)
seq_dict = SeqIO.to_dict(SeqIO.parse(in_seq_handle, "fasta"))
in_seq_handle.close()
seq_dict_keys = seq_dict.keys()
matrix = pd.DataFrame()
def mRNA():
usage = "Usage: To create input concat file run novo2concat.py"
parser = argparse.ArgumentParser(usage=usage)
files = parser.add_argument_group('Options for input files')
files.add_argument("-g",
"--gtf_file",
dest="gtf_file",
help="Provide the path to your gtf file.",
type=str,
default=None)
files.add_argument("-i",
"--input_file",
dest="input_file",
help="Provide the path to your concat file. REQUIRED.",
metavar="FILE",
default=None,
required=True)
files.add_argument("--5flank",
dest="five_prime_flank",
type=int,
help="Set up 5 prime flank in pileup file. Default = 0",
default=0)
files.add_argument("--3flank",
dest="three_prime_flank",
type=int,
help="Set up 3 prime flank in pileup file. Default = 0",
default=0)
universal = parser.add_argument_group('Universal options')
universal.add_argument("-t",
"--hits_threshold",
dest="hits_threshold",
type=int,
help="Set up threshold for pileup. Default 0 reads",
default=0)
universal.add_argument(
"-n",
"--normalized",
dest="normalized",
action="store_true",
help=
"Use when you want to work on data normalized 'reads per Milion'. Default: False",
default=False)
output = parser.add_argument_group('Options for output files')
output.add_argument(
"-p",
"--prefix",
dest="out_prefix",
type=str,
help=
"Prefix for output files. Default to standard output. Not supported for -o ratio.",
default=None)
output.add_argument("-o",
dest="output_files",
choices=['bind'],
help="Select from following options:"
"(1) Print binding windows in fasta file",
default="bind")
output.add_argument("--peaks",
dest="print_peaks",
action="store_true",
help="print peaks on plots. Default: False",
default=False)
output.add_argument("--valleys",
dest="print_valleys",
action="store_true",
help="print valleys on plots. Default: False",
default=False)
special = parser.add_argument_group('Special options for some -o choices')
special.add_argument(
"--lookahead",
dest="lookahead",
type=int,
help="Set up lookahead parameter for pypeaks function. Default = 20",
default=20)
special.add_argument(
"-w",
"--window",
dest="window",
type=int,
help=
"Set up size of window for bind calculation (-o bind). Default: 10",
default=10)
special.add_argument("-e",
dest="experiment_to_use",
type=str,
help="For -o bind, which experiment to use.")
# special.add_argument("--ntotal", dest="ntotal", action="store_true", help="Normalize data to sum of all reads (sum = 1). Default: False", default=False)
# special.add_argument("--nmax", dest="nmax", action="store_true", help="Normalize data to maximal value (max = 1). Default: False", default=False)
# special.add_argument("-a", dest="to_divide", type=str, help="experiment to divide by -b (-o fig_ratio)",
# default=None)
# special.add_argument("-b", dest="divisor", type=str, help="experiment being divisor for -a (-o fig_ratio)",
# default=None)
options = parser.parse_args()
#checking input
input_file = options.input_file
#preparing naming of output files
if options.out_prefix:
prefix = options.out_prefix + '_'
else:
prefix = str()
if options.normalized == True:
prefix = 'normalized_' + prefix
data = mRNAFromConcat(gtf_file=gtm.getGTF(options.gtf_file),
five_prime_flank=options.five_prime_flank,
three_prime_flank=options.three_prime_flank,
hits_threshold=options.hits_threshold,
lookahead=options.lookahead,
prefix=prefix,
npM=options.normalized)
if options.output_files == "bind":
#reading csv file
data.read_csv(input_file, use='deletions')
#calculating readthrough, details, normalize
# data.calculate(details=options.details, ntotal=options.ntotal, nmax=options.nmax)
data.bind(exp_to_use=options.experiment_to_use, window=options.window)
print '# Done.'
def getGeneNamesFromGTF():
parser = OptionParser(
usage="getGenesNames; type usage: %prog [options] -f filename")
files = OptionGroup(parser, "File input options")
files.add_option(
"-f",
"--input_file",
dest="gtf_file",
help=
"Provide the path to your gtf data file. Default is standard input.",
type="str",
default=None)
files.add_option(
"-g",
"--genes",
dest="genes",
help=
"Which biotype of features to get: mRNA, tRNA, rRNA, snRNA, snoRNA",
type="str",
default='tRNA')
files.add_option(
"-i",
"--introns",
dest="introns",
help=
"Introns? both - not discriminate; int_cont -only intron containing; int_less - only int less",
choices=["both", "int_cont", "int_less"],
default="both"),
files.add_option(
"-o",
"--output_file",
dest="output_file",
help=
"Use this flag to provide an output file name. Default is standard output.",
default=None)
parser.add_option_group(files)
(options, args) = parser.parse_args()
### By default, input and output are expected from the standard input or standard output.
signal(SIGPIPE, SIG_DFL)
outfile = sys.stdout
if options.output_file:
outfile = open(options.output_file, "w")
gtf = GTF2.Parse_GTF()
gtf.read_GTF(gtm.getGTF(options.gtf_file))
names_list = list()
### for loop extracting tRNA names
for line in open(gtm.getGTF(options.gtf_file), "r"):
if not line.startswith('#'):
line_elements = line.strip().split('\t')
# assert len(line_elements) == 10, 'Unexpected number of elements found in gtf line: ' + line
if str(line_elements[1]) == options.genes:
try:
name = re.search("gene_name\s\"(.*?)\"",
str(line_elements[8])).group(1)
except:
pass
# name = re.search("gene_id\s\"(.*?)\"", str(line_elements[8])).group(1)
if options.introns == "both":
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
elif options.introns == "int_cont":
if gtf.intronCoordinates(name):
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
elif options.introns == "int_less":
if not gtf.intronCoordinates(name):
if name not in names_list:
names_list.append(name)
# outfile.write(str(name) + '\n')
outfile.write('\n'.join(names_list) + '\n')
outfile.close()
