def main():
args = get_args()
# load genes (accounting for linkage)
genes = col2dict(
args.genes,
value=(1 if args.linked else None),
headers=args.skip_headers,
)
genes = {g: (g if k is None else k) for g, k in genes.items()}
# load background (accounting for linkage)
background = None
if args.background is not None:
background = col2dict(
args.background,
value=(1 if args.linked else None),
headers=args.skip_headers,
)
background = {
g: (g if k is None else k)
for g, k in background.items()
}
# load gene sets
gene_sets = polymap(
args.gene_sets,
reverse=args.reversed_mapping,
)
# run analysis
results = fisher_enrich(
genes,
gene_sets,
depletions=not args.exclude_depletions,
background=background,
intersect_background=args.intersect_background,
intersect_annotated=args.intersect_annotated,
fdr=args.fdr,
min_expected_overlap=args.min_expected_overlap,
verbose=False,
)
# write results
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
writer = csv.writer(fh, dialect="excel-tab")
writer.writerow(c_fisher_fields)
for R in results:
writer.writerow(R.row())
# wrapup
if len(results) == 0:
say("# NO SIGNIFICANT ENRICHMENTS")
fh.close()
return None
def main():
args = get_args()
# load key values
def make_link(row):
key = row[1] if args.linked else row[0]
return Link(key, float(row[-1]))
values = col2dict(
args.values,
func=make_link,
headers=args.skip_headers,
)
# load key sets
gene_sets = polymap(
args.gene_sets,
reverse=args.reversed_mapping,
)
# perform analysis
results = rank_enrich(
values,
gene_sets,
depletions=not args.exclude_depletions,
intersect_annotated=args.intersect_annotated,
fdr=args.fdr,
min_overlap=args.min_overlap,
verbose=True,
)
# write results
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
writer = csv.writer(fh, dialect="excel-tab")
writer.writerow(c_rank_fields)
for R in results:
writer.writerow(R.row())
# wrapup
if len(results) == 0:
say("# NO SIGNIFICANT ENRICHMENTS")
fh.close()
return None
#! /usr/bin/env python
import os, sys, re, glob, argparse
from zopy.enrichments import fisher_enrich as fe
from zopy.dictation import polymap
with open(sys.argv[1]) as fh:
x = [k.strip() for k in fh.readlines()]
a = polymap(sys.argv[2])
for result in fe(x, a, ranked=True):
print result[:-1], len(result[-1]), len(x)
def main():
args = get_args()
# load obo / report rel type
obo = Ontology(args.obo)
warn("Summary of relationship types:")
for k in sorted(parentage_types):
warn(k, parentage_types[k])
# attach genes
if args.mapping is not None:
mapping = polymap(args.mapping, reverse=args.flip)
if args.allowed_genes is not None:
allowed = col2dict(args.allowed_genes)
mapping = {k: v for k, v in mapping.items() if k in allowed}
obo.attach_genes(mapping)
warn("# of attached genes:", len(obo.attached_genes))
# informative cut
if args.informative is not None:
threshold = float(args.informative)
if threshold < 1:
warn(
"Intepretting informative cutoff as fraction of annotated genes"
)
threshold *= len(obo.attached_genes)
threshold = int(threshold)
obo.set_informative(threshold)
for term in obo.iter_terms():
if not term.is_informative:
term.is_acceptable = False
# pruning cut
if args.prune is not None:
obo.prune(args.prune)
for term in obo.iter_terms():
if not term.is_pruned:
term.is_acceptable = False
# depth cut
if args.depth is not None:
for term in obo.iter_terms():
if term.depth != args.depth:
term.is_acceptable = False
# grep cut
if args.grep is not None:
for term in obo.iter_terms():
if not re.search(args.grep, term.name):
term.is_acceptable = False
# namespace cut
if args.namespace is not None:
for term in obo.iter_terms():
if term.namespace_short not in args.namespace:
term.is_acceptable = False
# output the new polymap
fh = open(args.outfile, "w") if args.outfile is not None else sys.stdout
for term in obo.iter_terms():
if term.is_acceptable:
outline = [str(term)]
if not args.terms_only:
outline += list(term.get_progeny_genes(
) if not args.ignore_progeny else term.genes)
print >> fh, "\t".join(outline)
fh.close()
def attach_genes(self, path):
"""assigns genes from a polymap to the tree"""
for gene, terms_dict in polymap(path).items():
self.attached_genes[gene] = 1
for term in terms_dict:
self.nodes[term].add_genes(gene)