print('{N} of {M:,} results were significant'.format(N=len(goea_quiet_sig),
M=len(goea_quiet_all)))
print('Significant results: {E} enriched, {P} purified'.format(
E=sum(1 for r in goea_quiet_sig if r.enrichment == 'e'),
P=sum(1 for r in goea_quiet_sig if r.enrichment == 'p')))
ctr = cx.Counter([r.NS for r in goea_quiet_sig])
print('Significant results[{TOTAL}] = {BP} BP + {MF} MF + {CC} CC'.format(
TOTAL=len(goea_quiet_sig),
BP=ctr['BP'], # biological_process
MF=ctr['MF'], # molecular_function
CC=ctr['CC'])) # cellular_component
#goeaobj.wr_xlsx("CDK1_test.xlsx", goea_quiet_sig)
goeaobj.wr_txt("CDK1_test.txt", goea_quiet_sig)
goid_subset = [
'GO:0003723', # MF D04 RNA binding (32 genes)
'GO:0044822', # MF D05 poly(A) RNA binding (86 genes)
'GO:0003729', # MF D06 mRNA binding (11 genes)
'GO:0019843', # MF D05 rRNA binding (6 genes)
'GO:0003746', # MF D06 translation elongation factor activity (5 genes)
]
plot_gos(
"nbt3102_MF_RNA_genecnt.png",
goid_subset, # Source GO ids
obodag,
goea_results=goea_quiet_all) # Use pvals for coloring
def pullGOenrichment(inputFile, project):
GeneID2nt_hum = genes_NCBI_9606_ProteinCoding.GENEID2NT
obo_fname = download_go_basic_obo()
fin_gene2go = download_ncbi_associations()
obodag = GODag("go-basic.obo")
# Read NCBI's gene2go. Store annotations in a list of namedtuples
objanno = Gene2GoReader(fin_gene2go, taxids=[9606])
# Get namespace2association where:
# namespace is:
# BP: biological_process
# MF: molecular_function
# CC: cellular_component
# assocation is a dict:
# key: NCBI GeneID
# value: A set of GO IDs associated with that gene
ns2assoc = objanno.get_ns2assc()
for nspc, id2gos in ns2assoc.items():
print("{NS} {N:,} annotated human genes".format(NS=nspc,
N=len(id2gos)))
print(len(GeneID2nt_hum))
goeaobj = GOEnrichmentStudyNS(
GeneID2nt_hum.keys(), # List of human protein-coding genes
ns2assoc, # geneid/GO associations
obodag, # Ontologies
propagate_counts=False,
alpha=0.05, # default significance cut-off
methods=['fdr_bh']) # defult multipletest correction method
geneid2symbol = {}
with open(inputFile, 'r') as infile:
input_genes = csv.reader(infile)
for line in input_genes:
geneid = line[0]
symbol = line[1]
if geneid:
geneid2symbol[int(geneid)] = symbol
infile.close()
geneids_study = geneid2symbol.keys()
goea_results_all = goeaobj.run_study(geneids_study)
goea_results_sig = [r for r in goea_results_all if r.p_fdr_bh < 0.05]
import collections as cx
ctr = cx.Counter([r.NS for r in goea_results_sig])
print('Significant results[{TOTAL}] = {BP} BP + {MF} MF + {CC} CC'.format(
TOTAL=len(goea_results_sig),
BP=ctr['BP'], # biological_process
MF=ctr['MF'], # molecular_function
CC=ctr['CC'])) # cellular_component
goeaobj.wr_xlsx("Data/go_enrichment" + project + ".csv", goea_results_sig)
goeaobj.wr_txt("Data/go_enrichment" + project + ".txt", goea_results_sig)