def main():
main_parser = argparse.ArgumentParser(description='run Gene Ontology')
subparsers = main_parser.add_subparsers(dest='which', help='type of enrichment analysis')
subparsers.required = True
parser = argparse.ArgumentParser(add_help=False)
required = parser.add_argument_group('required named arguments')
required.add_argument('-o', '--out', type=str, required=True, nargs = '+',
help='output file')
required.add_argument('-i', '--inp', type=str, required=True,
help='input gene list file')
required.add_argument('-a', '--assoc', type=str, required=True,
help='input associations file (.gaf)')
required.add_argument('-g', '--gograph', type=str, required=True,
help='input GO graph file (.obo)')
parser.add_argument('-f', '--outputformat', choices=["html","txt", "gml", "png", "tabular"], nargs = "+",
help='output file format', default = ["html"])
parser.add_argument('-c', '--corrections', choices=["bonferroni","bh_fdr", "bonferroni,bh_fdr", "bh_fdr,bonferroni"],
help='multiple hypothesis testing corrections', nargs='+', default=[])
parser1 = subparsers.add_parser("term-for-term", parents=[parser])
parser2 = subparsers.add_parser("parent-child", parents=[parser])
#Parent-child
parser2.add_argument('-m', '--method', choices=["union", "intersection"],
help='method used to compute probabilities', default = "union")
#validate args
if len(sys.argv) < 2:
main_parser.print_usage()
sys.exit(1)
args = main_parser.parse_args()
if len(args.out) != len(args.outputformat):
main_parser.error("Number of output files doesn't match numer of formats!")
check_file(main_parser, args.inp, 'r')
check_file(main_parser, args.assoc, 'r')
check_file(main_parser, args.gograph, 'r')
for f in args.out:
check_file(main_parser, f, 'w+')
cors = []
for cor in args.corrections:
if "," in cor:
cors += cor.split(",")
else:
cors.append(cor)
args.corrections = list(set(cors))
#Read inputs
gene_list = read_list(args.inp)
go_graph = OntoIO.read(args.gograph, "obo")
assocs = OntoIO.read(args.assoc, "gaf", assoc_format = "in_mem_sql")
result=None
if args.which == "term-for-term":
result = run_term(assocs, go_graph, gene_list, args.corrections)
elif args.which == "parent-child":
result = run_parent_child(assocs, go_graph, gene_list, args.corrections, args.method)
else:
parser.error("Method unimplemented!")
assert result!= None, "An error occured while computing result"
print result
for outfilename, outputformat in zip(args.out, args.outputformat):
with open(outfilename, 'w+') as outfile:
if outputformat == 'html':
OntoIO.pretty_print(result, go_graph, outfile, outputformat, go_to_url="http://amigo.geneontology.org/amigo/term/")
else:
OntoIO.pretty_print(result, go_graph, outfile, outputformat)
def main():
main_parser = argparse.ArgumentParser(description='run Ranked Gene Ontology on DESeq output')
subparsers = main_parser.add_subparsers(dest='which', help='type of enrichment analysis')
subparsers.required = True
parser = argparse.ArgumentParser(add_help=False)
required = parser.add_argument_group('required named arguments')
required.add_argument('-o', '--out', type=str, required=True, nargs = '+',
help='output file')
required.add_argument('-i', '--inp', type=str, required=True,
help='input gene list file')
required.add_argument('-a', '--assoc', type=str, required=True,
help='input associations file (.gaf)')
required.add_argument('-g', '--gograph', type=str, required=True,
help='input GO graph file (.obo)')
parser.add_argument('-f', '--outputformat', choices=["html","txt", "gml", "png", "tabular"], nargs = '+',
help='output file format', default = ["html"])
parser1 = subparsers.add_parser("GSEA", parents=[parser])
parser2 = subparsers.add_parser("parent-child", parents=[parser])
#GSEA params
parser1.add_argument('-p', '--perms', type=int, default=1000,
help='number of permutations to compute p-values')
parser1.add_argument('-n', '--minset', type=int, default=1,
help='minimal intersection between set of genes in rank and in studied set')
parser1.add_argument('-c', '--corrpower', type=float, default=1,
help='how strong correlation will affect enrichment')
parser1.add_argument('--seed', type=int, help=argparse.SUPPRESS)
#Ranked Parent-child
parser2.add_argument('-s', '--side', choices=["+","-", "+/-"],
help='from which side (highest or lowest) to start computation', default = "+")
parser2.add_argument('-c', '--corrections', choices=["bonferroni","bh_fdr", "bonferroni,bh_fdr", "bh_fdr,bonferroni"],
help='multiple hypothesis testing corrections', nargs='+', default=[])
parser2.add_argument('-r', '--rank-as-population', action='store_true',
help='only the rank should be used as population')
parser2.add_argument('-m', '--method', choices=["union", "intersection", "term"],
help='method used to compute probabilities', default = "union")
#validate args
if len(sys.argv) < 2:
main_parser.print_usage()
sys.exit(1)
args = main_parser.parse_args()
if len(args.out) != len(args.outputformat):
main_parser.error("Number of output files doesn't match numer of formats!")
check_file(main_parser, args.inp, 'r')
check_file(main_parser, args.assoc, 'r')
check_file(main_parser, args.gograph, 'r')
for f in args.out:
check_file(main_parser, f, 'w+')
if args.which == "parent-child":
cors = []
for cor in args.corrections:
if "," in cor:
cors += cor.split(",")
else:
cors.append(cor)
args.corrections = list(set(cors))
if args.which == "GSEA":
#check parameters
if args.perms < 1:
parser.error('wrong number of permutations: %d' % args.p)
#Load inputs
gene_rank = read_deseq_output(args.inp, 1)
go_graph = OntoIO.read(args.gograph, "obo")
#assocs = OntoIO.read(args.assoc, "gaf", assoc_format = "in_mem_sql")
assocs = OntoIO.read(args.assoc, "gaf")
result=None
if args.which == "GSEA":
result = run_gsea(assocs, go_graph, gene_rank, args.perms, args.minset, args.corrpower, args.seed)
elif args.which == "parent-child":
result = run_parent_child(assocs, go_graph, gene_rank, args.side, args.corrections, args.rank_as_population, args.method)
else:
parser.error("Method unimplemented!")
assert result!= None, "An error occured while computing result"
print result
for outfilename, outputformat in zip(args.out, args.outputformat):
with open(outfilename, 'w+') as outfile:
if outputformat == 'html':
OntoIO.pretty_print(result, go_graph, outfile, outputformat, go_to_url="http://amigo.geneontology.org/amigo/term/")
else:
OntoIO.pretty_print(result, go_graph, outfile, outputformat)
def main():
main_parser = argparse.ArgumentParser(description='run Ranked Gene Ontology on DESeq output')
subparsers = main_parser.add_subparsers(dest='which', help='type of enrichment analysis')
subparsers.required = True
parser = argparse.ArgumentParser(add_help=False)
required = parser.add_argument_group('required named arguments')
required.add_argument('-o', '--out', type=str, required=True, nargs = '+',
help='output file')
required.add_argument('-i', '--inp', type=str, required=True,
help='input gene list file')
required.add_argument('-a', '--assoc', type=str, required=True,
help='input associations file (.gaf)')
required.add_argument('-g', '--gograph', type=str, required=True,
help='input GO graph file (.obo)')
parser.add_argument('-f', '--outputformat', choices=["html","txt", "gml", "png", "tabular"], nargs = '+',
help='output file format', default = ["html"])
parser1 = subparsers.add_parser("GSEA", parents=[parser])
parser2 = subparsers.add_parser("parent-child", parents=[parser])
#GSEA params
parser1.add_argument('-p', '--perms', type=int, default=1000,
help='number of permutations to compute p-values')
parser1.add_argument('-n', '--minset', type=int, default=1,
help='minimal intersection between set of genes in rank and in studied set')
parser1.add_argument('-c', '--corrpower', type=float, default=1,
help='how strong correlation will affect enrichment')
parser1.add_argument('--seed', type=int, help=argparse.SUPPRESS)
#Ranked Parent-child
parser2.add_argument('-s', '--side', choices=["+","-", "+/-"],
help='from which side (highest or lowest) to start computation', default = "+")
parser2.add_argument('-c', '--corrections', choices=["bonferroni","bh_fdr", "bonferroni,bh_fdr", "bh_fdr,bonferroni"],
help='multiple hypothesis testing corrections', nargs='+', default=[])
parser2.add_argument('-r', '--rank-as-population', action='store_true',
help='only the rank should be used as population')
parser2.add_argument('-m', '--method', choices=["union", "intersection", "term"],
help='method used to compute probabilities', default = "union")
#validate args
if len(sys.argv) < 2:
main_parser.print_usage()
sys.exit(1)
args = main_parser.parse_args()
if len(args.out) != len(args.outputformat):
main_parser.error("Number of output files doesn't match numer of formats!")
check_file(main_parser, args.inp, 'r')
check_file(main_parser, args.assoc, 'r')
check_file(main_parser, args.gograph, 'r')
for f in args.out:
check_file(main_parser, f, 'w+')
if args.which == "parent-child":
cors = []
for cor in args.corrections:
if "," in cor:
cors += cor.split(",")
else:
cors.append(cor)
args.corrections = list(set(cors))
if args.which == "GSEA":
#check parameters
if args.perms < 1:
parser.error('wrong number of permutations: %d' % args.p)
#Load inputs
gene_rank = read_deseq_output(args.inp, 1)
go_graph = OntoIO.read(args.gograph, "obo")
assocs = OntoIO.read(args.assoc, "gaf", assoc_format = "in_mem_sql")
result=None
if args.which == "GSEA":
result = run_gsea(assocs, go_graph, gene_rank, args.perms, args.minset, args.corrpower, args.seed)
elif args.which = "parent-child":
result = run_parent_child(assocs, go_graph, gene_rank, args.side, args.corrections, args.rank_as_population, args.method)
result=None
if args.which == "GSEA":
result = run_gsea(assocs, go_graph, gene_rank, args.perms, args.minset, args.corrpower, args.seed)
elif args.which = "parent-child":
result = run_parent_child(assocs, go_graph, gene_rank, args.side, args.corrections, args.rank_as_population, args.method)
else:
parser.error("Method unimplemented!")
assert result!= None, "An error occured while computing result"
print result
for outfilename, outputformat in zip(args.out, args.outputformat):
with open(outfilename, 'w+') as outfile:
if outputformat == 'html':
OntoIO.pretty_print(result, go_graph, outfile, outputformat, go_to_url="http://amigo.geneontology.org/amigo/term/")
else:
OntoIO.pretty_print(result, go_graph, outfile, outputformat)
if __name__ == "__main__":
main()
def setUp(self):
self.go_graph = OntoIO.read("Ontology/go_test.obo", "obo")
self.assocs_iter = OntoIO.read("Ontology/ga_test.fb", "gaf")
def setUp(self):
self.go_graph = OntoIO.read("Ontology/go_test.obo", "obo")
self.assocs = OntoIO.read("Ontology/ga_test.fb", "gaf")
self.ef = TermForTermEnrichmentFinder(self.assocs, self.go_graph)
def main():
main_parser = argparse.ArgumentParser(description='run Gene Ontology')
subparsers = main_parser.add_subparsers(dest='which',
help='type of enrichment analysis')
subparsers.required = True
parser = argparse.ArgumentParser(add_help=False)
required = parser.add_argument_group('required named arguments')
required.add_argument('-o',
'--out',
type=str,
required=True,
nargs='+',
help='output file')
required.add_argument('-i',
'--inp',
type=str,
required=True,
help='input gene list file')
required.add_argument('-a',
'--assoc',
type=str,
required=True,
help='input associations file (.gaf)')
required.add_argument('-g',
'--gograph',
type=str,
required=True,
help='input GO graph file (.obo)')
parser.add_argument('-f',
'--outputformat',
choices=["html", "txt", "gml", "png", "tabular"],
nargs="+",
help='output file format',
default=["html"])
parser.add_argument('-c',
'--corrections',
choices=[
"bonferroni", "bh_fdr", "bonferroni,bh_fdr",
"bh_fdr,bonferroni"
],
help='multiple hypothesis testing corrections',
nargs='+',
default=[])
parser1 = subparsers.add_parser("term-for-term", parents=[parser])
parser2 = subparsers.add_parser("parent-child", parents=[parser])
#Parent-child
parser2.add_argument('-m',
'--method',
choices=["union", "intersection"],
help='method used to compute probabilities',
default="union")
#validate args
if len(sys.argv) < 2:
main_parser.print_usage()
sys.exit(1)
args = main_parser.parse_args()
if len(args.out) != len(args.outputformat):
main_parser.error(
"Number of output files doesn't match numer of formats!")
check_file(main_parser, args.inp, 'r')
check_file(main_parser, args.assoc, 'r')
check_file(main_parser, args.gograph, 'r')
for f in args.out:
check_file(main_parser, f, 'w+')
cors = []
for cor in args.corrections:
if "," in cor:
cors += cor.split(",")
else:
cors.append(cor)
args.corrections = list(set(cors))
#Read inputs
gene_list = read_list(args.inp)
go_graph = OntoIO.read(args.gograph, "obo")
assocs = OntoIO.read(args.assoc, "gaf", assoc_format="in_mem_sql")
result = None
if args.which == "term-for-term":
result = run_term(assocs, go_graph, gene_list, args.corrections)
elif args.which == "parent-child":
result = run_parent_child(assocs, go_graph, gene_list,
args.corrections, args.method)
else:
parser.error("Method unimplemented!")
assert result != None, "An error occured while computing result"
print result
for outfilename, outputformat in zip(args.out, args.outputformat):
with open(outfilename, 'w+') as outfile:
if outputformat == 'html':
OntoIO.pretty_print(
result,
go_graph,
outfile,
outputformat,
go_to_url="http://amigo.geneontology.org/amigo/term/")
else:
OntoIO.pretty_print(result, go_graph, outfile, outputformat)
