def test_filter_genes_only():
st_out = ac.filter_genes_only([st1, st5])
assert len(st_out) == 2
st_out = ac.filter_genes_only([st6, st7])
assert len(st_out) == 0
st_out = ac.filter_genes_only([st4])
assert len(st_out) == 0
st_out = ac.filter_genes_only([st3], specific_only=True)
assert len(st_out) == 0
def main(args):
# This file takes about 32 GB to load
if not args.infile:
args.infile = './Data/indra_raw/bioexp_all_raw.pkl'
if not args.outfile:
args.outfile = './filtered_indra_network.sif'
# Load statements from file
stmts_raw = assemble_corpus.load_statements(args.infile)
# Expand families, fix grounding errors and run run preassembly
stmts_fixed = assemble_corpus.run_preassembly(
assemble_corpus.map_grounding(
assemble_corpus.expand_families(stmts_raw)))
# Default filtering: specific (unique) genes that are grounded.
stmts_filtered = assemble_corpus.filter_grounded_only(
assemble_corpus.filter_genes_only(stmts_fixed, specific_only=True))
# Custom filters
if args.human_only:
stmts_filtered = assemble_corpus.filter_human_only(stmts_filtered)
if args.filter_direct:
stmts_filtered = assemble_corpus.filter_direct(stmts_filtered)
binary_stmts = [s for s in stmts_filtered if len(s.agent_list()) == 2 and s.agent_list()[0] is not None]
rows = []
for s in binary_stmts:
rows.append([ag.name for ag in s.agent_list()])
# Write rows to .sif file
with open(args.outfile, 'w', newline='') as csvfile:
wrtr = csv.writer(csvfile, delimiter='\t')
for row in rows:
wrtr.writerow(row)
def get_indra_phos_stmts():
stmts = by_gene_role_type(stmt_type='Phosphorylation')
stmts += by_gene_role_type(stmt_type='Dephosphorylation')
stmts = ac.map_grounding(stmts)
# Expand families before site mapping
stmts = ac.expand_families(stmts)
stmts = ac.filter_grounded_only(stmts)
stmts = ac.map_sequence(stmts)
ac.dump_statements(stmts, 'sources/indra_phos_sitemap.pkl')
stmts = ac.run_preassembly(stmts,
poolsize=4,
save='sources/indra_phos_stmts_pre.pkl')
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=True)
ac.dump_statements(stmts, 'sources/indra_phos_stmts.pkl')
return stmts
def get_indra_expression():
#inc_stmts = by_gene_role_type(stmt_type='IncreaseAmount')
#dec_stmts = by_gene_role_type(stmt_type='DecreaseAmount')
#stmts = inc_stmts + dec_stmts
#ac.dump_statements(stmts, 'indra_regulate_amount_stmts.pkl')
#stmts = ac.load_statements('indra_regulate_amount_stmts.pkl')
#stmts = ac.map_grounding(stmts)
# Expand families before site mapping
#stmts = ac.expand_families(stmts)
#stmts = ac.filter_grounded_only(stmts)
#stmts = ac.map_sequence(stmts)
#stmts = ac.run_preassembly(stmts, poolsize=4,
# save='indra_regulate_amount_pre.pkl')
stmts = ac.load_statements('indra_regulate_amount_pre.pkl')
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts)
stmts = [s for s in stmts if s.agent_list()[0] is not None]
return stmts
def regulons_from_stmts(stmts, filename):
regulons = defaultdict(set)
stmts = ac.filter_genes_only(stmts)
stmts = ac.filter_human_only(stmts)
for stmt in stmts:
kinase = stmt.enz.name
# Blacklist annoying stmts from NCI-PID
if (kinase == 'BRAF' or kinase == 'RAF1') and \
(stmt.sub.name == 'MAPK1' or stmt.sub.name == 'MAPK3'):
continue
if stmt.residue and stmt.position:
site = '%s_%s%s' % (stmt.sub.name, stmt.residue, stmt.position)
regulons[kinase].add(site)
rows = []
for kinase, sites in regulons.items():
rows.append([kinase, 'Description'] + [s for s in sites])
with open(filename, 'wt') as f:
csvwriter = csv.writer(f, delimiter='\t')
csvwriter.writerows(rows)
def get_indra_reg_act_stmts():
try:
stmts = ac.load_statements('sources/indra_reg_act_stmts.pkl')
return stmts
except:
pass
stmts = []
for stmt_type in ('Activation', 'Inhibition', 'ActiveForm'):
print("Getting %s statements from INDRA DB" % stmt_type)
stmts += by_gene_role_type(stmt_type=stmt_type)
stmts = ac.map_grounding(stmts, save='sources/indra_reg_act_gmap.pkl')
stmts = ac.filter_grounded_only(stmts)
stmts = ac.run_preassembly(stmts,
poolsize=4,
save='sources/indra_reg_act_pre.pkl')
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=True)
ac.dump_statements(stmts, 'sources/indra_reg_act_stmts.pkl')
return stmts
def load_statements_from_synapse(synapse_id='syn11273504'):
syn = synapseclient.Synapse()
syn.login()
# Obtain a pointer and download the data
syn_data = syn.get(synapse_id)
stmts = []
for row in read_unicode_csv(syn_data.path, delimiter='\t'):
sub_name, site_info = row[0].split(':')
res = site_info[0]
pos = site_info[1:]
gene_list = row[1].split(',')
for enz_name in gene_list:
enz = Agent(enz_name, db_refs=get_ids(enz_name))
sub = Agent(sub_name, db_refs=get_ids(sub_name))
stmt = Phosphorylation(enz, sub, res, pos)
stmts.append(stmt)
stmts = ac.map_sequence(stmts)
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=True)
return stmts
def test_filter_genes_only():
st_out = ac.filter_genes_only([st1, st5])
assert len(st_out) == 2
st_out = ac.filter_genes_only([st6, st7])
assert len(st_out) == 0
st_out = ac.filter_genes_only([st4])
assert len(st_out) == 0
st_out = ac.filter_genes_only([st3], specific_only=True)
assert len(st_out) == 0
# Can we remove statements with non-gene bound conditions?
st_out = ac.filter_genes_only([st18]) # remove_bound defaults to False
assert len(st_out) == 0
st_out = ac.filter_genes_only([st18], remove_bound=False)
assert len(st_out) == 0
# Can we remove non-gene bound conditions?
st18_copy = deepcopy(st18)
assert len(st18_copy.sub.bound_conditions) == 1
st_out = ac.filter_genes_only([st18_copy], remove_bound=True)
assert len(st_out[0].sub.bound_conditions) == 0
#prior_stmts = build_prior(data_genes, pjoin(outf, 'prior.pkl'))
prior_stmts = ac.load_statements(pjoin(outf, 'prior.pkl'))
prior_stmts = ac.map_grounding(prior_stmts,
save=pjoin(outf, 'gmapped_prior.pkl'))
reach_stmts = ac.load_statements(pjoin(outf, 'phase3_stmts.pkl'))
reach_stmts = ac.filter_no_hypothesis(reach_stmts)
#extra_stmts = ac.load_statements(pjoin(outf, 'extra_stmts.pkl'))
extra_stmts = read_extra_sources(pjoin(outf, 'extra_stmts.pkl'))
reading_stmts = reach_stmts + extra_stmts
reading_stmts = ac.map_grounding(reading_stmts,
save=pjoin(outf,
'gmapped_reading.pkl'))
stmts = prior_stmts + reading_stmts + extra_stmts
stmts = ac.filter_grounded_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=False)
stmts = ac.filter_human_only(stmts)
stmts = ac.expand_families(stmts)
stmts = ac.filter_gene_list(stmts, data_genes, 'one')
stmts = ac.map_sequence(stmts, save=pjoin(outf, 'smapped.pkl'))
#stmts = ac.load_statements(pjoin(outf, 'smapped.pkl'))
stmts = ac.run_preassembly(stmts,
return_toplevel=False,
save=pjoin(outf, 'preassembled.pkl'),
poolsize=4)
### PySB assembly
if 'pysb' in assemble_models:
pysb_model = assemble_pysb(stmts, data_genes,
pjoin(outf, 'korkut_model_pysb.py'))
### SIF assembly
reassemble = False
if not reassemble:
stmts = ac.load_statements(pjoin(outf, 'preassembled.pkl'))
#stmts = ac.load_statements(pjoin(outf, 'prior.pkl'))
else:
#prior_stmts = build_prior(data_genes, pjoin(outf, 'prior.pkl'))
prior_stmts = ac.load_statements(pjoin(outf, 'prior.pkl'))
prior_stmts = ac.map_grounding(prior_stmts,
save=pjoin(outf, 'gmapped_prior.pkl'))
reading_stmts = ac.load_statements(pjoin(outf, 'phase3_stmts.pkl'))
reading_stmts = ac.map_grounding(reading_stmts,
save=pjoin(outf, 'gmapped_reading.pkl'))
stmts = prior_stmts + reading_stmts
stmts = ac.filter_grounded_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=False)
stmts = ac.filter_human_only(stmts)
stmts = ac.expand_families(stmts)
stmts = ac.filter_gene_list(stmts, data_genes, 'one')
stmts = ac.map_sequence(stmts, save=pjoin(outf, 'smapped.pkl'))
stmts = ac.run_preassembly(stmts, return_toplevel=False,
save=pjoin(outf, 'preassembled.pkl'))
assemble_models = []
assemble_models.append('sif')
assemble_models.append('pysb')
assemble_models.append('cx')
### PySB assembly
if 'pysb' in assemble_models:
pysb_model = assemble_pysb(stmts, data_genes,
def get_phosphosite_stmts():
stmts = ac.load_statements('sources/phosphosite_stmts.pkl')
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts, specific_only=True)
return stmts
default_prior_list = [t[0] for t in kin_ctr[0:200]]
default_prior_filename = 'priors/indra_nkconf2_combined_default200.txt'
save_default_prior(default_prior_list, default_prior_filename)
syn_file = synapseclient.File(default_prior_filename, parent='syn11272284')
syn.store(syn_file)
import sys
sys.exit()
"""
with open('sources/stmt_cache.pkl', 'rb') as f:
syn_stmts, omni_stmts, phos_stmts, indra_stmts = pickle.load(f)
"""
#db_stmts = syn_stmts + omni_stmts + phos_stmts
all_stmts = ac.filter_genes_only(all_stmts, specific_only=True)
all_prior = to_prior(all_stmts)
ext_prior_100 = add_regulators(reg_stmts, all_prior, max_features=100)
save_prior(ext_prior_100, 'regulators_prior_100.txt')
ext_prior_200 = add_regulators(reg_stmts, all_prior, max_features=200)
save_prior(ext_prior_200, 'regulators_prior_200.txt')
print("Phosphosite: %d of %d peptides" %
(coverage(ov_sites, get_stmt_sites(phos_stmts)), len(ov_sites)))
print("Phosphosite + NetworKIN: %d of %d peptides" %
(coverage(ov_sites, get_stmt_sites(syn_stmts)), len(ov_sites)))
print("Omnipath (incl. PSP, Signor, et al.): %d of %d peptides" %
(coverage(ov_sites, get_stmt_sites(omni_stmts)), len(ov_sites)))
print("REACH/INDRA: %d of %d peptides" %
return pd.DataFrame(tf_df)
wd = __file__
INDRA_SIF = os.path.join(os.pardir, 'input', 'sif.pkl')
with open(INDRA_SIF, 'rb') as fh:
SIF = pickle.load(fh)
n_stmt_type = list(SIF.columns).index('stmt_type')
n_stmt_hash = list(SIF.columns).index('stmt_hash')
hash_set = set()
for r, c in SIF.iterrows():
if c[n_stmt_type] == 'IncreaseAmount' or c[n_stmt_type] == 'DecreaseAmount':
hash_set.add(c[n_stmt_hash])
#stmts = download_statements(hash_set)
indra_stmts = list(stmts.values())
with open('../output/all_stmts.pkl', 'wb') as fh:
pickle.dump(indra_stmts, fh)
indra_stmts = filter_human_only(indra_stmts)
indra_stmts = filter_genes_only(indra_stmts)
indra_stmts = filter_transcription_factor(indra_stmts)
indra_stmts_db_only = filter_db_only(indra_stmts)
indra_stmts_df = make_dataframe(indra_stmts)
indra_stmts_df.to_csv('../output/indra_all_tf.csv')
indra_stmts_db_only_df = make_dataframe(indra_stmts_db_only)
indra_stmts_db_only_df.to_csv('../output/indra_db_only_tf.csv')
return
if __name__ == "__main__":
stmts = "../work/phospho_stmts.pkl"
prize_outpath = "../work/pybel_prize.tsv"
interactome_path = "../work/big_pybel_interactome2.tsv"
site_file = "../work/gsea_sites.rnk"
# Load the statements linking kinases/regulators to phospho sites
# in the data
stmts = ac.load_statements(stmts)
# Employ filters to reduce network size
stmts = ac.filter_grounded_only(stmts)
stmts = ac.filter_human_only(stmts)
stmts = ac.filter_genes_only(stmts)
# In this data, statements of these two types will not act on
# a short enough timescale to play a meaningful role
stmts = ac.filter_by_type(stmts, DecreaseAmount, invert=True)
stmts = ac.filter_by_type(stmts, IncreaseAmount, invert=True)
stmts = ac.filter_by_type(stmts, Complex, invert=True)
stmts = ac.filter_enzyme_kinase(stmts)
# Assemble a pybel graph from statements
pba = PybelAssembler(stmts)
pb_graph = make_model(pba)
signed_graph = to_signed_nodes(pb_graph)
gn_dict = get_gene_node_dict(signed_graph)
# Next we have to load the data file and assign values to
