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 __init__(self):
super().__init__()
# commit
self.commit_button = None
# gene sets object
self.gene_sets_obj = geneset.GeneSets()
# progress bar
self.progress_bar = None
self.progress_bar_iterations = None
# data
self.input_data = None
self.input_genes = []
self.tax_id = None
self.use_attr_names = None
self.gene_id_attribute = None
self.gene_id_column = None
# custom gene sets
self.custom_data = None
self.feature_model = DomainModel(valid_types=(DiscreteVariable,
StringVariable))
self.gene_set_label = None
self.gs_label_combobox = None
self.custom_tax_id = None
self.custom_use_attr_names = None
self.custom_gene_id_attribute = None
self.custom_gene_id_column = None
# reference genes
self.reference_radio_box = None
self.reference_data = None
self.reference_genes = None
self.reference_tax_id = None
self.reference_attr_names = None
self.reference_gene_id_attribute = None
self.reference_gene_id_column = None
# info box
self.input_info = None
self.num_of_sel_genes = 0
# filter
self.line_edit_filter = None
self.search_pattern = ''
self.organism_select_combobox = None
# data model view
self.data_view = None
self.data_model = None
# gene matcher NCBI
self.gene_matcher = None
# filter proxy model
self.filter_proxy_model = None
# hierarchy widget
self.hierarchy_widget = None
self.hierarchy_state = None
# spinbox
self.spin_widget = None
# threads
self.threadpool = QThreadPool(self)
self.workers = None
self._task = None # type: Optional[Task]
self._executor = ThreadExecutor()
# gui
self.setup_gui()