def run_enrichment(org_code, genes, reference, progress=None):
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
kegg_api = kegg.api.CachedKeggApi()
link_map = kegg_api.link(org_code,
"pathway") # [(pathway_id, kegg_gene_id)]
ncbi_gene_map = kegg_api.conv(
org_code, 'ncbi-geneid') # [(ncbi_gene_id, kegg_gene_id)]
ncbi_gene_map = [(_1.split(":", 1)[1], _2)
for _1, _2 in ncbi_gene_map]
link_map = relation_join(
link_map,
[(_2, _1)
for _1, _2 in ncbi_gene_map]) # [(pathway_id, ncbi_gene_id)]
kegg_sets = relation_list_to_multimap(
link_map) # {pathway_id -> [ncbi_gene_ids]}
# map kegg gene ids to ncbi_gene_ids.
kegg_sets = geneset.GeneSets(sets=[
geneset.GeneSet(gs_id=ddi, genes=set(genes))
for ddi, genes in kegg_sets.items()
])
pathways = pathway_enrichment(kegg_sets,
genes,
reference,
callback=progress)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(pathways.keys(),
progress_callback=progress)
return pathways, ncbi_gene_map
def run_enrichment(genes, reference, progress=None):
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
kegg_api = kegg.api.CachedKeggApi()
linkmap = kegg_api.link(self.org.org_code, "pathway")
converted_ids = kegg_api.conv(self.org.org_code, 'ncbi-geneid')
kegg_sets = relation_list_to_multimap(linkmap, {
gene.upper(): ncbi.split(':')[-1]
for ncbi, gene in converted_ids
})
kegg_sets = geneset.GeneSets(sets=[
geneset.GeneSet(gs_id=ddi, genes=set(genes))
for ddi, genes in kegg_sets.items()
])
pathways = pathway_enrichment(kegg_sets,
genes,
reference,
callback=progress)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(pathways.keys(),
progress_callback=progress)
return pathways
def run_enrichment(org_code, genes, reference=None, progress=None):
org = kegg.KEGGOrganism(org_code)
if reference is None:
reference = org.get_ncbi_ids()
# This is here just to keep widget working without any major changes.
# map not needed, geneMatcher will not work on widget level.
unique_genes = genes
unique_ref_genes = dict([(gene, gene) for gene in set(reference)])
taxid = kegg.to_taxid(org.org_code)
# Map the taxid back to standard 'common' taxids
# (as used by 'geneset') if applicable
r_tax_map = dict(
(v, k) for k, v in kegg.KEGGGenome.TAXID_MAP.items())
if taxid in r_tax_map:
taxid = r_tax_map[taxid]
# We use the kegg pathway gene sets provided by 'geneset' for
# the enrichment calculation.
kegg_api = kegg.api.CachedKeggApi()
linkmap = kegg_api.link(org.org_code, "pathway")
converted_ids = kegg_api.conv(org.org_code, 'ncbi-geneid')
kegg_sets = relation_list_to_multimap(
linkmap,
dict((gene.upper(), ncbi.split(':')[-1])
for ncbi, gene in converted_ids))
kegg_sets = geneset.GeneSets(sets=[
geneset.GeneSet(gs_id=ddi, genes=set(genes))
for ddi, genes in kegg_sets.items()
])
pathways = pathway_enrichment(kegg_sets,
unique_genes.values(),
unique_ref_genes.keys(),
callback=progress)
# Ensure that pathway entries are pre-cached for later use in the
# list/tree view
kegg_pathways = kegg.KEGGPathways()
kegg_pathways.pre_cache(pathways.keys(),
progress_callback=progress)
return pathways, org, unique_genes, unique_ref_genes
def UpdateListView(self):
self.bestPValueItem = None
self.listView.clear()
if not self.data:
return
allPathways = self.org.pathways()
allRefPathways = kegg.pathways("map")
items = []
kegg_pathways = kegg.KEGGPathways()
org_code = self.org.org_code
if self.showOrthology:
self.koOrthology = kegg.KEGGBrite("ko00001")
self.listView.setRootIsDecorated(True)
path_ids = {s[-5:] for s in self.pathways.keys()}
def _walkCollect(koEntry):
num = koEntry.title[:5] if koEntry.title else None
if num in path_ids:
return [koEntry] + reduce(
lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries], [])
else:
c = reduce(lambda li, c: li + _walkCollect(c),
[child for child in koEntry.entries], [])
return c + (c and [koEntry] or [])
allClasses = reduce(lambda li1, li2: li1 + li2,
[_walkCollect(c) for c in self.koOrthology],
[])
def _walkCreate(koEntry, lvItem):
item = QTreeWidgetItem(lvItem)
id = "path:" + org_code + koEntry.title[:5]
if koEntry.title[:5] in path_ids:
p = kegg_pathways.get_entry(id)
if p is None:
# In case the genesets still have obsolete entries
name = koEntry.title
else:
name = p.name
genes, p_value, ref = self.pathways[id]
item.setText(0, name)
item.setText(1, "%.5f" % p_value)
item.setText(
2, "%i of %i" % (len(genes), len(self.input_genes)))
item.setText(3, "%i of %i" % (ref, len(self.ref_genes)))
item.pathway_id = id if p is not None else None
else:
if id in allPathways:
text = kegg_pathways.get_entry(id).name
else:
text = koEntry.title
item.setText(0, text)
if id in allPathways:
item.pathway_id = id
elif "path:map" + koEntry.title[:5] in allRefPathways:
item.pathway_id = "path:map" + koEntry.title[:5]
else:
item.pathway_id = None
for child in koEntry.entries:
if child in allClasses:
_walkCreate(child, item)
for koEntry in self.koOrthology:
if koEntry in allClasses:
_walkCreate(koEntry, self.listView)
self.listView.update()
else:
self.listView.setRootIsDecorated(False)
pathways = self.pathways.items()
pathways = sorted(pathways, key=lambda item: item[1][1])
for id, (genes, p_value, ref) in pathways:
item = QTreeWidgetItem(self.listView)
item.setText(0, kegg_pathways.get_entry(id).name)
item.setText(1, "%.5f" % p_value)
item.setText(2,
"%i of %i" % (len(genes), len(self.input_genes)))
item.setText(3, "%i of %i" % (ref, len(self.ref_genes)))
item.pathway_id = id
items.append(item)
self.bestPValueItem = items and items[0] or None
self.listView.expandAll()
for i in range(4):
self.listView.resizeColumnToContents(i)
if self.bestPValueItem:
index = self.listView.indexFromItem(self.bestPValueItem)
self.listView.selectionModel().select(
index, QItemSelectionModel.ClearAndSelect)