def main():
# Option Parse
parser = argparse.ArgumentParser(description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser('index', help='Index all sequences in the database')
parser_index.add_argument("--db", dest='db', default=None, action="store", help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser('extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f', '--file', dest='file', action="store", help="A multifasta file",
required=False)
parser_extract.add_argument('-e','--end', type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s','--start', type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g','--gene', type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument('-l','--len', action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
parser_splice = subparsers.add_parser('splice',
help = 'Splices the gene in the specified positions')
parser_splice.add_argument('-f', '--file',
action='store',
help='A multifasta file')
parser_splice.add_argument('-r-', '--range',
action='store',
type=str,
required=True,
help='A list with the positions of the gene you wish to splice. Use the format "range1-range2, range3-range4", within quotation marks. Example: -r "10-20 30-40 50-60"')
parser_splice.add_argument('-g', '--gene',
action='store',
type=str,
help='The required gene.',
required=True)
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(args, 'start') and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
generator = searchgen.generat(fasta)
seq = ''.join(searchgen.search(fasta, generator, start, end, gene_name))
print('>{gene}:{start}-{end}'.format(gene=gene_name,start=start,end=end))
print(seq)
print()
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
searchgen.len(fasta, gene_name)
if hasattr(args, 'range'):
fasta = args.file
gene_name = args.gene
ranging = args.range
generator = splice.generat(fasta)
slices = ''.join(splice.slicer(fasta, generator, ranging, gene_name))
print('>{gene} sliced in {range}:'.format(gene=gene_name,range=ranging))
print(slices)
print()
def main():
# Option Parse
parser = argparse.ArgumentParser(description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser('index', help='Index all sequences in the database')
parser_index.add_argument("--db", dest='db', default=None, action="store", help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser('extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f', '--file', dest='file', action="store", help="A multifasta file",
required=False)
parser_extract.add_argument('-e','--end', type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s','--start', type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g','--gene', type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument('-l','--len', action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
parser_splice = subparsers.add_parser('splice', help='Extract sequence in a multifasta')
parser_splice.add_argument('-f', '--file', dest='file', action="store", help="A multifasta file",
required=False)
parser_splice.add_argument('-g','--gene', type=str,
help="A gene (or chromossome) name",
required=False)
#parser_splice.add_argument('-l','--len', action='store_true',
#help="Get the length of all genes. "
#"If --gene get the length of the provided gene",
#required=False)
parser_splice.add_argument('-r', '--range', action="store", nargs='+', required=False, help='Values in the form start-end space separated. 10-20 50-60 70-100')
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(args, 'start') and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
seq = search_fasta.search(fasta, start, end, gene_name)
print('>{gene}:{start}-{end}'.format(gene=gene_name,start=start,end=end))
for i in seq:
print(i, end='')
print()
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search_fasta.length(fasta, gene_name)
if hasattr(args, 'range') and args.range is not None: # arg.splice exists and has a value
fasta = args.file
intervals = args.range
gene_name = args.gene
print(f'{gene_name}:{intervals}:')
for interval in intervals:
start = int(interval.split('-')[0])
end = int(interval.split('-')[1])
seq = search_fasta.search(fasta, start, end, gene_name)
print(f'{start}-{end}: ', end='')
for i in seq:
print(i, end='')
print()
print()
def main():
# Criar um objeto do pacote argparser
parser = argparse.ArgumentParser(
description="A Tool to index and search large multifasta files")
# Para criar um subcomando, adicionar o metodo add_subparser
subparsers = parser.add_subparsers(
title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
######## INDEX
# Com o metodo add_parser, adicionar ao subcomando ao help do comando
parser_index = subparsers.add_parser(
'index', help='Index all sequences in the database')
# Adicionar os argumentos do subcomando
parser_index.add_argument("--db",
dest='db',
default=None,
action="store",
help="A multifasta DB to be indexed",
required=False)
######## EXTRACT
parser_extract = subparsers.add_parser(
'extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f',
'--file',
dest='file',
action="store",
help="A multifasta file",
required=False)
parser_extract.add_argument('-e',
'--end',
type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s',
'--start',
type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g',
'--gene',
type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument(
'-l',
'--len',
action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
######## SPLICE
parser_splice = subparsers.add_parser('splice',
help='Retrieve multiples intervals')
parser_splice.add_argument('-f',
'--file',
dest='file',
action="store",
help="A multifasta file",
required=False)
parser_splice.add_argument('-g',
'--gene',
type=str,
help="A gene (or chromossome) name",
required=False)
parser_splice.add_argument(
'-r',
'--range',
dest='rg',
action='store',
nargs='+',
required=False,
help='Values in the form start-end space separated. 10-20 50-60 70-100'
)
########
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(
args, 'start'
) and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
seq = search.search_seq(fasta, start, end, gene_name)
print('>{gene}:{start}-{end}'.format(gene=gene_name,
start=start,
end=end))
for i in seq:
print(i)
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search.length(fasta, gene_name)
if hasattr(
args,
'rg') and args.rg is not None: # args.start exists and has a value
fasta = args.file
gene_name = args.gene
for interval in args.rg:
gene_interval = interval.split('-')
print('\n>{gene}:{start}-{end}'.format(gene=gene_name,
start=gene_interval[0],
end=gene_interval[1]))
seq = search.search_seq(fasta, int(gene_interval[0]),
int(gene_interval[1]), gene_name)
for i in seq:
print(i)
def main():
# Option Parse
parser = argparse.ArgumentParser(description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser('index', help='Index all sequences in the database')
parser_index.add_argument("--db", dest='db', default=None, action="store", help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser('extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f', '--file', dest='file', action="store", help="A multifasta file",
required=False)
parser_extract.add_argument('-e','--end', type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s','--start', type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g','--gene', type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument('-l','--len', action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
parser_extract.add_argument('-r','--splice', nargs='+', action='store',
help="List of intervals to extract sequence",
required=False)
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
# Metodo de pegar subsequencia de um valor apenas
if hasattr(args, 'start') and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
seq = search_fasta.search(fasta, start, end, gene_name)
print('>{gene}:{start}-{end}'.format(gene=gene_name,start=start,end=end))
for i in seq:
print(i)
# print(seq)
print()
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
# Metodo de pegar subsequencia de varios intervalos
if hasattr(args, 'splice') and args.splice is not None: # args.start exists and has a value
fasta = args.file
splice = args.splice
gene_name = args.gene
print('>{gene}:{splice}'.format(gene=gene_name,splice=splice))
search_fasta.splice(fasta, splice, gene_name)
# print(seq)
# for i in my_seq:
# print(i)
print()
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search_fasta.len(fasta, gene_name)
def main():
# Option Parse
parser = argparse.ArgumentParser(
description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(
title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser(
'index', help='Index all sequences in the database')
parser_index.add_argument("--db",
dest='db',
default=None,
action="store",
help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser(
'extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f',
'--file',
dest='file',
action="store",
help="A multifasta file",
required=False)
parser_extract.add_argument('-e',
'--end',
type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s',
'--start',
type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g',
'--gene',
type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument(
'-l',
'--len',
action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
#________________________________SPLICE________________________________________#
parser_splice = subparsers.add_parser(
'splice', help='Extract multiple sequences in a multifasta')
parser_splice.add_argument('-f',
'--file',
dest='file',
action="store",
help="A multifasta file",
required=False)
parser_splice.add_argument(
'-r',
'--range',
type=pair,
nargs='+',
help="A values in the form start-end space separated",
required=False)
parser_splice.add_argument('-g',
'--gene',
type=str,
help="A gene (or chromossome) name",
required=False)
#______________________________________________________________________________#
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(
args, 'start'
) and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
##############Tempo inicial
tempo_inicial = time.clock()
seq = search_fasta.search(fasta, start, end, gene_name)
tempo_final = time.clock()
print('Tempo: ')
print(tempo_final - tempo_inicial)
print('>{gene}:{start}-{end}'.format(gene=gene_name,
start=start,
end=end))
for i in seq:
print(i, end='')
print()
#print(list(seq))
#print(seq)
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search_fasta.len(fasta, gene_name)
if hasattr(args, 'range') and args.range:
result = ''
fasta = args.file
gene_name = args.gene
#print (fasta)
print('>' + gene_name + ':', end='')
for i in args.range:
#print (i[0])
fasta = args.file
start = int(i[0])
end = int(i[1])
print("['" + str(i[0]) + '-' + str(i[1]) + "']", end='')
#print (i[0]+','+i[1])
seq = search_fasta.search(fasta, start, end, gene_name)
for i in seq:
#print (i)
result += i
#result += "\n"
#print (args.range)
print()
print(result)
print(len(result))
def main():
# Option Parse
parser = argparse.ArgumentParser(
description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(
title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser(
'index', help='Index all sequences in the database')
parser_index.add_argument("--db",
dest='db',
default=None,
action="store",
help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser(
'extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f',
'--file',
dest='file',
action="store",
help="A multifasta file",
required=False)
parser_extract.add_argument('-e',
'--end',
type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s',
'--start',
type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g',
'--gene',
type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument(
'-l',
'--len',
action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
parser_splicing = subparsers.add_parser(
'splicing', help='Gets splicing portions and retrieves toguether')
parser_splicing.add_argument('-f',
'--file',
action='store',
required=False,
help='insert multifasta file name')
parser_splicing.add_argument(
'-r',
'--range',
action='store',
nargs='+',
required=False,
help=
"Values should be writen as START-END separeted by space, example: 10-20 56-89"
)
parser_splicing.add_argument('-g',
'--gene',
action='store',
required=False,
help="A gene (or chromossome) name")
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(
args, 'start'
) and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
gene_seq = search_fasta_gen.search(fasta, start, end, gene_name)
# seq = search_fasta.search(fasta, start, end, gene_name)
print('>{gene}:{start}-{end}'.format(gene=gene_name,
start=start,
end=end))
for line in gene_seq:
print(line)
print(len(line))
print()
if hasattr(args, 'len'): # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search_fasta_gen.len(fasta, gene_name)
if hasattr(args, 'range'):
fasta = args.file
range = args.range
gene_name = args.gene
print('>{gene}:{range}'.format(gene=gene_name, range=range))
search_fasta_gen.splicing(fasta, range, gene_name)
def main():
# Option Parse
parser = argparse.ArgumentParser(description="A Tool to index and search large multifasta files")
subparsers = parser.add_subparsers(title='subcommands',
description='valid subcommands',
help='Use retrieve_seq.py {subcommand} -h for help with each subcommand'
)
parser_index = subparsers.add_parser('index', help='Index all sequences in the database')
parser_index.add_argument("--db", dest='db', default=None, action="store", help="A multifasta DB to be indexed",
required=False)
parser_extract = subparsers.add_parser('extract', help='Extract sequence in a multifasta')
parser_extract.add_argument('-f', '--file', dest='file', action="store", help="A multifasta file",
required=False)
parser_extract.add_argument('-e','--end', type=int,
help="end position on the fasta sequence",
required=False)
parser_extract.add_argument('-s','--start', type=int,
help="start position on the fasta sequence",
required=False)
parser_extract.add_argument('-g','--gene', type=str,
help="A gene (or chromossome) name",
required=False)
parser_extract.add_argument('-l','--len', action='store_true',
help="Get the length of all genes. "
"If --gene get the length of the provided gene",
required=False)
parser_splice = subparsers.add_parser('splice', help="Extract sequence splices from a multifasta")
parser_splice.add_argument('-f', '--file', action="store", help="A multifasta file", required=False)
parser_splice.add_argument('-r', '--range', action="store", nargs="+", required=False, help="Values in the form "
"start-end space "
"separated."
"e.g.: 10-20 50-60 "
"70-100")
parser_splice.add_argument('-g', '--gene', required=False, help="A gene (or chromossome) name")
args = parser.parse_args()
# function hasattr must be used because args may or may not have arg.db, and test it with just an
# if args.db does not work
if hasattr(args, 'db'):
db_index.create_index(args.db)
print("DB {db} has been indexed".format(db=args.db))
if hasattr(args, 'start') and args.start is not None: # args.start exists and has a value
fasta = args.file
start = args.start
end = args.end
gene_name = args.gene
seq = search_fasta.search(fasta, start, end, gene_name)
print('>{gene}:{start}-{end}'.format(gene=gene_name,start=start,end=end))
for line in seq:
print(line)
if hasattr(args, 'len') and args.len: # arg.len is True
fasta = args.file
gene_name = args.gene if args.gene else None
search_fasta.len(fasta, gene_name)
if hasattr(args, 'range') and args.range is not None:
fasta= args.file
ranges = args.range
gene_name = args.gene
print('>{gene}:{range_list}'.format(gene=gene_name,range_list=ranges))
search_fasta.splice(fasta, ranges, gene_name)