def plotGO(clusterIDs, clusters, outdir, base):
obodag = GODag("../../obo/go.obo")
for id in clusterIDs:
geneset = clusters[id]['geneset']
goIDs = clusters[id]['go']['terms']
for category in goIDs.keys():
success = False
ids = goIDs[category]
while not success:
try:
plot_gos(
"{}/{}_{}_{}.png".format(outdir, base, id, category),
ids, obodag)
success = True
except KeyError as e:
value = str(e).replace("'", '')
goIDs.remove(value)
def test_example(log=sys.stdout):
"""Run Gene Ontology Enrichment Analysis (GOEA) on Nature data."""
# --------------------------------------------------------------------
# --------------------------------------------------------------------
# Gene Ontology Enrichment Analysis (GOEA)
# --------------------------------------------------------------------
# --------------------------------------------------------------------
taxid = 10090 # Mouse study
# Load ontologies, associations, and population ids
geneids_pop = GeneID2nt_mus.keys()
geneids_study = get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx")
goeaobj = get_goeaobj("fdr_bh", geneids_pop, taxid)
# Run GOEA on study
#keep_if = lambda nt: getattr(nt, "p_fdr_bh" ) < 0.05 # keep if results are significant
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]
compare_results(goea_results_all)
geneids = get_study_items(goea_results_sig)
# Print GOEA results to files
goeaobj.wr_xlsx("nbt3102.xlsx", goea_results_sig)
goeaobj.wr_txt("nbt3102_sig.txt", goea_results_sig)
goeaobj.wr_txt("nbt3102_all.txt", goea_results_all)
# Plot all significant GO terms w/annotated study info (large plots)
#plot_results("nbt3102_{NS}.png", goea_results_sig)
#plot_results("nbt3102_{NS}_sym.png", goea_results_sig, study_items=5, items_p_line=2, id2symbol=geneids_study)
# --------------------------------------------------------------------
# --------------------------------------------------------------------
# Further examination of GOEA results...
# --------------------------------------------------------------------
# --------------------------------------------------------------------
obo = goeaobj.obo_dag
dpi = 150 # For review: Figures can be saved in .jpg, .gif, .tif or .eps, at 150 dpi
# --------------------------------------------------------------------
# Item 1) Words in GO names associated with large numbers of study genes
# --------------------------------------------------------------------
# What GO term words are associated with the largest number of study genes?
prt_word2genecnt("nbt3102_genecnt_GOword.txt", goea_results_sig, log)
# Curated selection of GO words associated with large numbers of study genes
freq_seen = ['RNA', 'translation', 'mitochondr', 'ribosom', # 'ribosomal', 'ribosome',
'adhesion', 'endoplasmic', 'nucleotide', 'apoptotic', 'myelin']
# Collect the GOs which contains the chosen frequently seen words
word2NS2gos = get_word2NS2gos(freq_seen, goea_results_sig)
go2res = {nt.GO:nt for nt in goea_results_sig}
# Print words of interest, the sig GO terms which contain that word, and study genes.
prt_word_GO_genes("nbt3102_GO_word_genes.txt", word2NS2gos, go2res, geneids_study, log)
# Plot each set of GOs along w/study gene info
for word, NS2gos in word2NS2gos.items():
for NS in ['BP', 'MF', 'CC']:
if NS in NS2gos:
gos = NS2gos[NS]
goid2goobj = {go:go2res[go].goterm for go in gos}
# dpi: 150 for review, 1200 for publication
#dpis = [150, 1200] if word == "RNA" else [150]
dpis = [150]
for dpi in dpis:
fmts = ['png', 'tif', 'eps'] if word == "RNA" else ['png']
for fmt in fmts:
plot_goid2goobj(
"nbt3102_{WORD}_{NS}_dpi{DPI}.{FMT}".format(WORD=word, NS=NS, DPI=dpi, FMT=fmt),
goid2goobj, # source GOs and their GOTerm object
items_p_line=3,
study_items=6, # Max number of gene symbols to print in each GO term
id2symbol=geneids_study, # Contains GeneID-to-Symbol
goea_results=goea_results_all, # pvals used for GO Term coloring
dpi=dpi)
# --------------------------------------------------------------------
# Item 2) Explore findings of Nature paper:
#
# Gene Ontology (GO) enrichment analysis showed that the
# differentially expressed genes contained statistically
# significant enrichments of genes involved in
# glycolysis,
# cellular response to IL-4 stimulation and
# positive regulation of B-cell proliferation
# --------------------------------------------------------------------
goid_subset = [
'GO:0006096', # BP 4.24e-12 10 glycolytic process
'GO:0071353', # BP 7.45e-06 5 cellular response to interleukin-4
'GO:0030890', # BP 8.22e-07 7 positive regulation of B cell proliferation
]
plot_gos("nbt3102_GOs.png", goid_subset, obo, dpi=dpi)
plot_gos("nbt3102_GOs_genecnt.png", goid_subset, obo, goea_results=goea_results_all, dpi=dpi)
plot_gos("nbt3102_GOs_genelst.png", goid_subset, obo,
study_items=True, goea_results=goea_results_all, dpi=dpi)
plot_gos("nbt3102_GOs_symlst.png", goid_subset, obo,
study_items=True, id2symbol=geneids_study, goea_results=goea_results_all, dpi=dpi)
plot_gos("nbt3102_GOs_symlst_trunc.png", goid_subset, obo,
study_items=5, id2symbol=geneids_study, goea_results=goea_results_all, dpi=dpi)
plot_gos("nbt3102_GOs_GO0005743.png", ["GO:0005743"], obo,
items_p_line=2, study_items=6,
id2symbol=geneids_study, goea_results=goea_results_all, dpi=dpi)
# --------------------------------------------------------------------
# Item 3) Create one GO sub-plot per significant GO term from study
# --------------------------------------------------------------------
for rec in goea_results_sig:
png = "nbt3102_{NS}_{GO}.png".format(GO=rec.GO.replace(':', '_'), NS=rec.NS)
goid2goobj = {rec.GO:rec.goterm}
plot_goid2goobj(png,
goid2goobj, # source GOs and their GOTerm object
study_items=15, # Max number of gene symbols to print in each GO term
id2symbol=geneids_study, # Contains GeneID-to-Symbol
goea_results=goea_results_all, # pvals used for GO Term coloring
dpi=dpi)
# --------------------------------------------------------------------
# Item 4) Explore using manually curated lists of GO terms
# --------------------------------------------------------------------
goid_subset = [
'GO:0030529', # CC D03 intracellular ribonucleoprotein complex (42 genes)
'GO:0015934', # CC D05 large ribosomal subunit (4 genes)
'GO:0015935', # CC D05 small ribosomal subunit (13 genes)
'GO:0022625', # CC D06 cytosolic large ribosomal subunit (16 genes)
'GO:0022627', # CC D06 cytosolic small ribosomal subunit (19 genes)
'GO:0036464', # CC D06 cytoplasmic ribonucleoprotein granule (4 genes)
'GO:0005840', # CC D05 ribosome (35 genes)
'GO:0005844', # CC D04 polysome (6 genes)
]
plot_gos("nbt3102_CC_ribosome.png", goid_subset, obo,
study_items=6, id2symbol=geneids_study, items_p_line=3,
goea_results=goea_results_sig, dpi=dpi)
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,
obo,
goea_results=goea_results_all, dpi=150)
for dpi in [150, 1200]: # 150 for review, 1200 for publication
plot_gos("nbt3102_MF_RNA_dpi{DPI}.png".format(DPI=dpi),
goid_subset,
obo,
study_items=6, id2symbol=geneids_study, items_p_line=3,
goea_results=goea_results_all, dpi=dpi)
# --------------------------------------------------------------------
# Item 5) Are any significant geneids related to cell cycle?
# --------------------------------------------------------------------
import test_genes_cell_cycle as CC
genes_cell_cycle = CC.get_genes_cell_cycle(taxid, log=log)
genes_cell_cycle_sig = genes_cell_cycle.intersection(geneids)
CC.prt_genes("nbt3102_cell_cycle.txt", genes_cell_cycle_sig, taxid, log=None)
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 test_example(log=sys.stdout):
"""Run Gene Ontology Enrichment Analysis (GOEA) on Nature data."""
# --------------------------------------------------------------------
# --------------------------------------------------------------------
# Gene Ontology Enrichment Analysis (GOEA)
# --------------------------------------------------------------------
# --------------------------------------------------------------------
taxid = 10090 # Mouse study
# Load ontologies, associations, and population ids
geneids_pop = GeneID2nt_mus.keys()
geneids_study = get_geneid2symbol("nbt.3102-S4_GeneIDs.xlsx")
goeaobj = get_goeaobj("fdr_bh", geneids_pop, taxid)
# Run GOEA on study
#keep_if = lambda nt: getattr(nt, "p_fdr_bh" ) < 0.05 # keep if results are significant
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]
compare_results(goea_results_all)
geneids = get_study_items(goea_results_sig)
# Print GOEA results to files
goeaobj.wr_xlsx("nbt3102.xlsx", goea_results_sig)
goeaobj.wr_txt("nbt3102_sig.txt", goea_results_sig)
goeaobj.wr_txt("nbt3102_all.txt", goea_results_all)
# Plot all significant GO terms w/annotated study info (large plots)
#plot_results("nbt3102_{NS}.png", goea_results_sig)
#plot_results("nbt3102_{NS}_sym.png", goea_results_sig, study_items=5, items_p_line=2, id2symbol=geneids_study)
# --------------------------------------------------------------------
# --------------------------------------------------------------------
# Further examination of GOEA results...
# --------------------------------------------------------------------
# --------------------------------------------------------------------
obo = goeaobj.obo_dag
dpi = 150 # For review: Figures can be saved in .jpg, .gif, .tif or .eps, at 150 dpi
# --------------------------------------------------------------------
# Item 1) Words in GO names associated with large numbers of study genes
# --------------------------------------------------------------------
# What GO term words are associated with the largest number of study genes?
prt_word2genecnt("nbt3102_genecnt_GOword.txt", goea_results_sig, log)
# Curated selection of GO words associated with large numbers of study genes
freq_seen = [
'RNA',
'translation',
'mitochondr',
'ribosom', # 'ribosomal', 'ribosome',
'adhesion',
'endoplasmic',
'nucleotide',
'apoptotic',
'myelin'
]
# Collect the GOs which contains the chosen frequently seen words
word2NS2gos = get_word2NS2gos(freq_seen, goea_results_sig)
go2res = {nt.GO: nt for nt in goea_results_sig}
# Print words of interest, the sig GO terms which contain that word, and study genes.
prt_word_GO_genes("nbt3102_GO_word_genes.txt", word2NS2gos, go2res,
geneids_study, log)
# Plot each set of GOs along w/study gene info
for word, NS2gos in word2NS2gos.items():
for NS in ['BP', 'MF', 'CC']:
if NS in NS2gos:
gos = NS2gos[NS]
goid2goobj = {go: go2res[go].goterm for go in gos}
# dpi: 150 for review, 1200 for publication
#dpis = [150, 1200] if word == "RNA" else [150]
dpis = [150]
for dpi in dpis:
fmts = ['png', 'tif', 'eps'] if word == "RNA" else ['png']
for fmt in fmts:
plot_goid2goobj(
"nbt3102_{WORD}_{NS}_dpi{DPI}.{FMT}".format(
WORD=word, NS=NS, DPI=dpi, FMT=fmt),
goid2goobj, # source GOs and their GOTerm object
items_p_line=3,
study_items=
6, # Max number of gene symbols to print in each GO term
id2symbol=geneids_study, # Contains GeneID-to-Symbol
goea_results=
goea_results_all, # pvals used for GO Term coloring
dpi=dpi)
# --------------------------------------------------------------------
# Item 2) Explore findings of Nature paper:
#
# Gene Ontology (GO) enrichment analysis showed that the
# differentially expressed genes contained statistically
# significant enrichments of genes involved in
# glycolysis,
# cellular response to IL-4 stimulation and
# positive regulation of B-cell proliferation
# --------------------------------------------------------------------
goid_subset = [
'GO:0006096', # BP 4.24e-12 10 glycolytic process
'GO:0071353', # BP 7.45e-06 5 cellular response to interleukin-4
'GO:0030890', # BP 8.22e-07 7 positive regulation of B cell proliferation
]
plot_gos("nbt3102_GOs.png", goid_subset, obo, dpi=dpi)
plot_gos("nbt3102_GOs_genecnt.png",
goid_subset,
obo,
goea_results=goea_results_all,
dpi=dpi)
plot_gos("nbt3102_GOs_genelst.png",
goid_subset,
obo,
study_items=True,
goea_results=goea_results_all,
dpi=dpi)
plot_gos("nbt3102_GOs_symlst.png",
goid_subset,
obo,
study_items=True,
id2symbol=geneids_study,
goea_results=goea_results_all,
dpi=dpi)
plot_gos("nbt3102_GOs_symlst_trunc.png",
goid_subset,
obo,
study_items=5,
id2symbol=geneids_study,
goea_results=goea_results_all,
dpi=dpi)
plot_gos("nbt3102_GOs_GO0005743.png", ["GO:0005743"],
obo,
items_p_line=2,
study_items=6,
id2symbol=geneids_study,
goea_results=goea_results_all,
dpi=dpi)
# --------------------------------------------------------------------
# Item 3) Create one GO sub-plot per significant GO term from study
# --------------------------------------------------------------------
for rec in goea_results_sig:
png = "nbt3102_{NS}_{GO}.png".format(GO=rec.GO.replace(':', '_'),
NS=rec.NS)
goid2goobj = {rec.GO: rec.goterm}
plot_goid2goobj(
png,
goid2goobj, # source GOs and their GOTerm object
study_items=
15, # Max number of gene symbols to print in each GO term
id2symbol=geneids_study, # Contains GeneID-to-Symbol
goea_results=goea_results_all, # pvals used for GO Term coloring
dpi=dpi)
# --------------------------------------------------------------------
# Item 4) Explore using manually curated lists of GO terms
# --------------------------------------------------------------------
goid_subset = [
'GO:0030529', # CC D03 intracellular ribonucleoprotein complex (42 genes)
'GO:0015934', # CC D05 large ribosomal subunit (4 genes)
'GO:0015935', # CC D05 small ribosomal subunit (13 genes)
'GO:0022625', # CC D06 cytosolic large ribosomal subunit (16 genes)
'GO:0022627', # CC D06 cytosolic small ribosomal subunit (19 genes)
'GO:0036464', # CC D06 cytoplasmic ribonucleoprotein granule (4 genes)
'GO:0005840', # CC D05 ribosome (35 genes)
'GO:0005844', # CC D04 polysome (6 genes)
]
plot_gos("nbt3102_CC_ribosome.png",
goid_subset,
obo,
study_items=6,
id2symbol=geneids_study,
items_p_line=3,
goea_results=goea_results_sig,
dpi=dpi)
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,
obo,
goea_results=goea_results_all,
dpi=150)
for dpi in [150, 1200]: # 150 for review, 1200 for publication
plot_gos("nbt3102_MF_RNA_dpi{DPI}.png".format(DPI=dpi),
goid_subset,
obo,
study_items=6,
id2symbol=geneids_study,
items_p_line=3,
goea_results=goea_results_all,
dpi=dpi)
# --------------------------------------------------------------------
# Item 5) Are any significant geneids related to cell cycle?
# --------------------------------------------------------------------
import test_genes_cell_cycle as CC
genes_cell_cycle = CC.get_genes_cell_cycle(taxid, log=log)
genes_cell_cycle_sig = genes_cell_cycle.intersection(geneids)
CC.prt_genes("nbt3102_cell_cycle.txt",
genes_cell_cycle_sig,
taxid,
log=None)
def _runGOanalysis(cluster, n_genes=75):
clusterNum=cluster.replace('Cluster', '')
genesList = []
if comparison == 'DiffExp_DownOC':
sigGenes = genesDf.loc[genesDf['(1, ' + str(clusterNum) + ')_p'] < .05]
genesList = sigGenes['(1, ' + str(clusterNum) + ')_n'].tolist()
elif comparison == 'DiffExp_UpOC':
sigGenes = genesDf.loc[genesDf['(2, ' + str(clusterNum) + ')_p'] < .05]
genesList = sigGenes['(2, ' + str(clusterNum) + ')_n'].tolist()
else:
genesList = genesDf['(' + str(clusterNum) + '_n)']
genesList =genesList[:n_genes]
setName = cluster + '_' + comparison
entrezIDlist, nullGenes = getEntrezIDs(genesList)
print(str(len(entrezIDlist)) + " Entrez IDs retrieved, searching NCBI for " + str(len(nullGenes)) + " genes")
newGeneList = []
newEntrezList = []
unfoundList = []
for gene in nullGenes:
search = Entrez.esearch(db='gene', term=gene, retmax=1, start=0, sort='relevance')
record = Entrez.read(search)
ID = record.get('IdList')
if not len(ID) == 0:
newGeneList.append(gene)
newEntrezList.append(ID[0])
else:
unfoundList.append(gene)
# geneIndex = pd.read_excel(os.path.join(goaResultDir, 'EntrezIndex.xlsx'), index_col=0)
newEntrez = pd.DataFrame([newEntrezList, newGeneList]).T
newEntrez.columns=['entrez_id', 'symbol']
# geneIndex = pd.concat([geneIndex, newEntrez], axis=0)
# geneIndex.to_excel(os.path.join(goaResultDir, 'EntrezIndex.xlsx'))
print(str(len(newEntrezList)) + " additional Entrez IDs retrieved, " + str(len(unfoundList)) + " genes with no results")
entrezIDlist.extend(newEntrezList)
print("Proceeding with GO analysis of " + str(len(entrezIDlist)) + " genes")
goea_results_all = goeaobj.run_study(entrezIDlist)
goea_results_sig = [r for r in goea_results_all if r.p_fdr_bh < 0.05]
print('{N} of {M:,} results were significant'.format(
N=len(goea_results_sig),
M=len(goea_results_all)))
print('Significant results: {E} enriched, {P} purified'.format(
E=sum(1 for r in goea_results_sig if r.enrichment=='e'),
P=sum(1 for r in goea_results_sig if r.enrichment=='p')))
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_all),
BP=ctr['BP'], # biological_process
MF=ctr['MF'], # molecular_function
CC=ctr['CC'])) # cellular_component
goeaobj.wr_xlsx(os.path.join(goaResultDir, cluster + '_' + comparison + "_GOA_Results_" + str(n_genes) + "genes.xlsx"), goea_results_sig)
# goeaobj.wr_txt(os.path.join(goaResultDir, cluster + '_' + comparison + "_GOA_Results.txt"), goea_results_sig)
plot_results(os.path.join(goaResultDir, cluster + '_' + comparison + '_' + str(n_genes) + "genes_GOA.png"), goea_results_sig)
goid_subset = [
'GO:0098984', # CC neuron to neuron synapse
'GO:0099699', # CC integral component of synaptic membrane
'GO:2000474', # BP regulation of opioid receptor signaling
'GO:0038003', # BP opioid receptor signaling pathway
'GO:0048167', # BP regulation of synaptic plasticity
'GO:0021897', # BP forebrain astrocyte development
'GO:0014003', # BP oligodendroyte development
'GO:0035249', # BP synaptic transmission, glutamatergic
'GO:0051932', # BP synaptic transmission, GABAergic
'GO:0014004', # BP microglia differentiation
]
"""
This plot contains GOEA results:
GO terms colored by P-value:
pval < 0.005 (light red)
pval < 0.01 (light orange)
pval < 0.05 (yellow)
pval > 0.05 (grey) Study terms that are not statistically significant
GO terms with study gene counts printed. e.g., "32 genes"
"""
plot_gos(os.path.join(goaResultDir, cluster + '_' + comparison + "_" + str(n_genes) + "genes_GOA_Subset_Plot.png"),
goid_subset, # Source GO ids
obodag,
goea_results=goea_results_all, # use pvals for coloring
# We can further configure the plot...
# id2symbol=geneid2symbol, # Print study gene Symbols, not Entrez GeneIDs
study_items=6, # Only only 6 gene Symbols max on GO terms
items_p_line=3, # Print 3 genes per line
)
return(newEntrez)
for g in goea_results_sig])
df_go = df_go1.merge(df_p, left_index=True, right_index=True)
go_genes = pandas.DataFrame([{'id': g.goterm.id, 'gene': s, 'symbol': geneid2symbol[s]}
for g in goea_results_sig
for s in g.study_items])
df_go = df_go.merge(go_genes, on='id')
print('SAVE -> name spaces of the significant GO terms in namespace.csv')
print(df_go.groupby('namespace').count())
df_go.to_csv(out_dir + "/name_space.csv")
print()
# -------------- Plot subset starting from these significant GO terms --------------
goid_subset = [g.GO for g in goea_results_sig]
plot_gos(out_dir + "/go_enrich.png",
goid_subset, # Source GO ids
obodag,
goea_results=goea_results_all) # Use pvals for coloring
plot_gos(out_dir + "/go_enrich_symbols.pdf",
goid_subset, # Source GO ids
obodag,
goea_results=goea_results_all, # use pvals for coloring
id2symbol=geneid2symbol, # Print study gene Symbols, not Entrez GeneIDs
study_items=6, # Only only 6 gene Symbols max on GO terms
items_p_line=3) # Print 3 genes per line
print()
cids = [int(data.drug_idx_to_id[c].replace('CID', '')) for c in pd_idx[1]]
drugs = [Compound.from_cid(int(cid)) for cid in set(cids)]
drug_ids = pandas.DataFrame([[data.drug_id_to_idx['CID{}'.format(d.cid)],
d.cid,
def enrich(gene2go: str,
study: str,
obo: str,
population: str = None,
geneid2symbol: str = None,
correct='fdr_bh',
alpha=0.05,
top=20,
goea_out=None,
dag_out=None,
dpi=300,
show_gene_limit=6,
only_plot_sig=False):
"""
Go enrichment based on goatools
:param gene2go: a file with two columns: gene_id \t go_term_id
:param study: a file with at least one column, first column contains gene id, second columns is regulation direction
:param obo: go-basic file download from GeneOntology
:param population: a file with each row contains one gene; default to use all genes in gene2go file as population
:param geneid2symbol: file with two columns: gene_id \t gene_symbol, used for DAG plot
:param correct: pvalue adjustment method:
Method used for testing and adjustment of pvalues. Can be either the
full name or initial letters. Available methods are:
- `bonferroni` : one-step correction
- `sidak` : one-step correction
- `holm-sidak` : step down method using Sidak adjustments
- `holm` : step-down method using Bonferroni adjustments
- `simes-hochberg` : step-up method (independent)
- `hommel` : closed method based on Simes tests (non-negative)
- `fdr_bh` : Benjamini/Hochberg (non-negative)
- `fdr_by` : Benjamini/Yekutieli (negative)
- `fdr_tsbh` : two stage fdr correction (non-negative)
- `fdr_tsbky` : two stage fdr correction (non-negative)
:param alpha: fdr cutoff, default 0.05
:param top: n top go terms to plot, sorted by corrected pvalue
:param goea_out: output enrichment result file
:param dag_out: dag figure file
:param dpi: resolution of image, no effect for svg
:param show_gene_limit: the max number of gene in a node to show
:param only_plot_sig: only plot dag for significantly enriched terms
:return: None
"""
if str(correct) == '3':
correct = 'fdr_bh'
if geneid2symbol:
geneid2symbol = dict(x.strip().split()[:2] for x in open(geneid2symbol)
if x.strip())
else:
geneid2symbol = dict()
obo = GODag(obo, optional_attrs=['relationship', 'is_a'])
gene2go = read_associations(gene2go)
study_genes = [x.strip().split()[0] for x in open(study)]
try:
reg_dict = dict(x.strip().split()[:2] for x in open(study))
except:
reg_dict = {x.strip(): '' for x in open(study)}
if not population:
population = gene2go.keys()
else:
population = [
x.strip().split()[0] for x in open(population) if x.strip()
]
goea_obj = GOEnrichmentStudy(population,
gene2go,
obo,
propagate_counts=False,
alpha=alpha,
methods=('fdr_bh', ))
keep_if = lambda r: r.ratio_in_study[0] != 0
goea_results_all = goea_obj.run_study(study_genes, keep_if=keep_if)
goea_out = goea_out or study + '.goea.xls'
goea_obj.wr_tsv(goea_out, goea_results_all)
def func(y):
results = []
genes = [x.strip() for x in y.split(',')]
for gene in genes:
tmp = [gene]
if gene in reg_dict:
tmp.append(reg_dict[gene])
if gene in geneid2symbol:
tmp.append(geneid2symbol[gene])
results.append('|'.join(tmp))
return ';'.join(results)
# func = lambda y: ';'.join(x.strip()+'|'+reg_dict[x.strip()] if x.strip() in reg_dict else x.strip() for x in y.split(','))
table = pd.read_table(goea_out, header=0, index_col=0)
# 重新校正pvalue, 修改内容
fdr = multipletests(table['p_uncorrected'], method=correct)[1]
table['p_fdr_bh'] = fdr
# 修改goea_result_all方便后续的画图
for r, fdr in zip(goea_results_all, fdr):
r.p_fdr_bh = fdr
table.columns = [
x if x != 'p_fdr_bh' else 'p_corrected' for x in table.columns
]
table['enrichment'] = [
'e' if x <= alpha else 'p' for x in table['p_corrected']
]
table['study_items'] = table.loc[:, 'study_items'].map(func)
# table = table.sort_values(by=['p_corrected', 'p_uncorrected'])
table.to_csv(goea_out, header=True, index=True, sep='\t')
# -------------------plot dag------------------------
for each in ['BP', 'MF', 'CC']:
if only_plot_sig:
goea_results_sig = table[table['enrichment'] == 'e']
else:
goea_results_sig = table.copy()
goea_results_sig = goea_results_sig[goea_results_sig['NS'] == each]
if not goea_results_sig.shape[0]:
print(f"No significant term to plot for {each} ")
return
if goea_results_sig.shape[0] >= top:
goea_results_sig = goea_results_sig.iloc[:top]
goid_subset = list(goea_results_sig.index)
# t = obo[goid_subset[5]]
# for k, v in t.relationship.items():
# print(t, k, type(v), list(v)[0].id)
# print(dag_out[:-4]+'.'+each+dag_out[-4:])
dag_out = dag_out or study + '.goea.dag.svg'
plot_gos(
dag_out[:-4] + '.' + each + dag_out[-4:],
goid_subset, # Source GO ids, 如果分析结果里面没有包含这个节点，则他的颜色会是苍白绿色，但这里这个情况不会出现
obo,
goea_results=
goea_results_all, # use pvals for coloring:"p_{M}".format(M=goea[0].method_flds[0].fieldname)
# We can further configure the plot...
id2symbol=geneid2symbol, # Print study gene Symbols, not GeneIDs
study_items=show_gene_limit, # Only max 6 gene Symbols on GO terms
items_p_line=3, # Print 3 genes per line)
dpi=0 if dag_out.endswith('svg') else dpi,
# title="Directed Graph of enriched {} terms".format(each)
)