def _get_id2gos(file_id2gos, godag, name2go):
"""Get annotations"""
if os.path.exists(file_id2gos):
return IdToGosReader(file_id2gos, godag=godag).get_id2gos('CC')
id2num = {
name2go['A']: 10,
name2go['B']: 10,
name2go['C']: 10,
name2go['D']: 10,
name2go['E']: 10,
name2go['F']: 10,
name2go['G']: 10,
name2go['H']: 10,
name2go['I']: 30,
name2go['L']: 30,
name2go['M']: 20,
name2go['N']: 30,
}
go2genes = cx.defaultdict(set)
genenum = 0
for goid, qty in id2num.items():
for _ in range(qty):
go2genes[goid].add(genenum)
genenum += 1
id2gos = get_b2aset(go2genes)
IdToGosReader.wr_id2gos(file_id2gos, id2gos)
return id2gos
def _get_goeaobj(methods=None):
"""Test GOEA with method, fdr."""
# REad GODag
obo_fin = os.path.join(REPO, "go-basic.obo")
obo_dag = get_godag(obo_fin, loading_bar=None)
# Read association
fin_assc = "{REPO}/tests/data/small_association".format(REPO=REPO)
objanno = IdToGosReader(fin_assc, godag=obo_dag)
ns2assc = objanno.get_ns2assc()
popul_fin = "{REPO}/tests/data/small_population".format(REPO=REPO)
popul_ids = [line.rstrip() for line in open(popul_fin)]
goeaobj = GOEnrichmentStudyNS(popul_ids, ns2assc, obo_dag, methods=methods)
return goeaobj
def _get_id2gos(file_id2gos, godag, name2go, name2num):
"""Get annotations"""
if os.path.exists(file_id2gos):
return IdToGosReader(file_id2gos, godag=godag).get_id2gos('CC')
go2genes = cx.defaultdict(set)
genenum = 0
for name, qty in name2num.items():
goid = name2go[name]
for _ in range(qty):
go2genes[goid].add(genenum)
genenum += 1
id2gos = get_b2aset(go2genes)
IdToGosReader.wr_id2gos(file_id2gos, id2gos)
return id2gos
def get_objanno(fin_anno, anno_type=None, **kws):
"""Read annotations in GAF, GPAD, Entrez gene2go, or text format."""
# kws get_objanno: taxids hdr_only prt allow_missing_symbol
anno_type = get_anno_desc(fin_anno, anno_type)
if anno_type is not None:
if anno_type == 'gene2go':
# kws: taxid taxids
kws_ncbi = {
k: kws[k]
for k in Gene2GoReader.exp_kws.intersection(kws.keys())
}
return Gene2GoReader(fin_anno, **kws_ncbi)
if anno_type == 'gaf':
kws_gaf = {
k: kws[k]
for k in GafReader.exp_kws.intersection(kws.keys())
}
return GafReader(fin_anno, **kws_gaf)
if anno_type == 'gpad':
kws_gpad = {
k: kws[k]
for k in GpadReader.exp_kws.intersection(kws.keys())
}
return GpadReader(fin_anno, **kws_gpad)
if anno_type == 'id2gos':
kws_id2go = {
k: kws[k]
for k in IdToGosReader.exp_kws.intersection(kws.keys())
}
return IdToGosReader(fin_anno, **kws_id2go)
raise RuntimeError('UNEXPECTED ANNOTATION FILE FORMAT: {F} {D}'.format(
F=fin_anno, D=anno_type))
def intialize_term_counts():
go_freq_dict = dict()
go_dag = GODag(os.path.join(DATA_DIR, "go-basic.obo"))
associations = IdToGosReader(UNIPROT_ASSOCIATIONS_FILE_PATH,
godag=go_dag).get_id2gos('all')
term_counts = TermCounts(go_dag, associations)
for i in go_dag.values():
go_freq_dict[i.id] = term_counts.get_count(i.id)
# write frequency dict to JSON file
with open(JSON_INDEXED_FILE_PATH, 'w') as json_file:
json.dump(go_freq_dict, json_file)
def _precompute_term_frequencies():
print("Start precomputations of term frequencies...")
go_freq_dict = dict()
go_dag = GODag(GO_DAG_FILE_PATH, prt=open(os.devnull, 'w'))
associations = IdToGosReader(UNIPROT_ASSOCIATIONS_FILE_PATH,
godag=go_dag).get_id2gos('all')
term_counts = TermCounts(go_dag, associations)
for i in go_dag.values():
go_freq_dict[i.id] = term_counts.get_count(i.id)
for alt_id in i.alt_ids:
go_freq_dict[alt_id] = term_counts.get_count(i.id)
# write frequency dict to JSON file
with open(FREQUENCY_COUNTS_FILE_PATH, 'w') as json_file:
json.dump(go_freq_dict, json_file)
def test_tcntobj_relationships(do_plt=False):
"""Test loading of relationships, like part_of, into TermCounts"""
# Filenames
fin_obo = os.path.join(REPO, "tests/data/yangRWC/fig2a.obo")
fin_anno = os.path.join(REPO, "tests/data/yangRWC/fig2a.anno")
fout_png_r0 = os.path.join(REPO, 'yang_fig2a_r0.png')
fout_png_r1 = os.path.join(REPO, 'yang_fig2a_r1.png')
relationships = {
'part_of',
}
# Load ontologies
go2obj = GODag(fin_obo, optional_attrs=['relationship'])
# Load annotations
assoc = IdToGosReader(fin_anno, godag=go2obj).get_id2gos('CC')
# Count genes annotated to GO terms w and wo/relationships
tcntobj_r0 = TermCounts(go2obj, assoc)
# relationship: G (GO:0000007) is part_of F (GO:0000006)
tcntobj_r1 = TermCounts(go2obj, assoc, relationships)
# Check results
# Adding relationships does not change the total count of genes:
assert tcntobj_r0.gocnts['GO:0005575'] == tcntobj_r1.gocnts['GO:0005575']
# Counts without relationships:
assert tcntobj_r0.gocnts['GO:0000002'] == 40 # GO Term B
assert tcntobj_r0.gocnts['GO:0000006'] == 10 # GO Term F
# Counts with relationships: F counts G's 30 genes, so does B
assert tcntobj_r1.gocnts['GO:0000002'] == 70 # GO Term B
assert tcntobj_r1.gocnts['GO:0000006'] == 40 # GO Term F
# Optionally visualize the difference between term counts w and wo/relationships
if do_plt:
go2txt_r0 = {
nt.GO: 'tcnt={}'.format(nt.tcnt)
for nt in tcntobj_r0.gosubdag.go2nt.values()
}
GoSubDagPlot(tcntobj_r0.gosubdag,
go2txt=go2txt_r0).plt_dag(fout_png_r0)
go2txt_r1 = {
nt.GO: 'tcnt={}'.format(nt.tcnt)
for nt in tcntobj_r1.gosubdag.go2nt.values()
}
GoSubDagPlot(tcntobj_r1.gosubdag,
go2txt=go2txt_r1).plt_dag(fout_png_r1)
uniprot_notnull['Encoding'])
])
#run gene ontology enrichment analysis
# Get http://geneontology.org/ontology/go-basic.obo
from goatools.base import download_go_basic_obo
obo_fname = download_go_basic_obo()
uniprot_df['Gene ontology IDs'] = uniprot_df['Gene ontology IDs'].str.replace(
' ', '')
uniprot_df.drop(['Encoding', 'Organism', 'Protein families', 'n'],
axis=1).to_csv("GOA.txt", sep='\t', header=False, index=False)
from goatools.anno.idtogos_reader import IdToGosReader
objanno = IdToGosReader("GOA.txt")
ns2assoc = objanno.get_id2gos()
from goatools.obo_parser import GODag
obodag = GODag("go-basic.obo")
from goatools.go_enrichment import GOEnrichmentStudy
goeaobj = GOEnrichmentStudy(
uniprot_df.Entry,
ns2assoc, # geneid/GO associations
obodag, # Ontologies
propagate_counts=False,
alpha=0.001, # default significance cut-off
methods=['fdr_bh']) # default multipletest correction method
gos = []
sys.stderr = open(snakemake.log[0], "w")
import pandas as pd
import matplotlib.pyplot as plt
from goatools.obo_parser import GODag
from goatools.anno.idtogos_reader import IdToGosReader
from goatools.goea.go_enrichment_ns import GOEnrichmentStudyNS
from goatools.godag_plot import plot_results#, plot_goid2goobj, plot_gos
# read in directed acyclic graph of GO terms / IDs
obodag = GODag(snakemake.input.obo)
# read in mapping gene ids from input to GO terms / IDs
objanno = IdToGosReader(snakemake.input.ens_gene_to_go, godag = obodag)
# extract namespace(?) -> id2gos mapping
ns2assoc = objanno.get_ns2assc()
for nspc, id2gos in ns2assoc.items():
print("{NS} {N:,} annotated genes".format(NS=nspc, N=len(id2gos)))
# read gene diffexp table
all_genes = pd.read_table(snakemake.input.diffexp)
# select genes significantly differentially expressed according to BH FDR of sleuth
fdr_level_gene = float(snakemake.params.gene_fdr)
sig_genes = all_genes[all_genes['qval']<fdr_level_gene]