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 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()
#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))
