def test_build_table__with_pandas_DataFrame():
df = pd.DataFrame(dict(a=[1, 2, 3], b=["c", "d", "e"]))
table = build_table("test", "syn123", df)
for i, row in enumerate(table):
assert_equals(row[0], (i+1))
assert_equals(row[1], ["c", "d", "e"][i])
assert_equals(len(table), 3)
headers = [
{'name': 'a', 'columnType': 'INTEGER'},
{'name': 'b', 'columnType': 'STRING'}
]
assert_equals(headers, table.headers)
def test_build_table__with_pandas_DataFrame():
df = pd.DataFrame(dict(a=[1, 2, 3], b=["c", "d", "e"]))
table = build_table("test", "syn123", df)
for i, row in enumerate(table):
assert row[0] == (i + 1)
assert row[1] == ["c", "d", "e"][i]
assert len(table) == 3
headers = [
{'name': 'a', 'columnType': 'INTEGER'},
{'name': 'b', 'columnType': 'STRING'}
]
assert headers == table.headers
def test_build_table__with_pandas_DataFrame():
df = pd.DataFrame(dict(a=[1, 2, 3], b=["c", "d", "e"]))
table = build_table("test", "syn123", df)
for i, row in enumerate(table):
assert_equals(row[0], (i + 1))
assert_equals(row[1], ["c", "d", "e"][i])
assert_equals(len(table), 3)
headers = [{
'name': 'a',
'columnType': 'INTEGER'
}, {
'name': 'b',
'columnType': 'STRING'
}]
assert_equals(headers, table.headers)
def test_build_table__with_csv():
string_io = StringIOContextManager('a,b\n'
'1,c\n'
'2,d\n'
'3,e')
with patch.object(synapseclient.table, "as_table_columns",
return_value=[Column(name="a", columnType="INTEGER"),
Column(name="b", columnType="STRING")]),\
patch.object(io, "open", return_value=string_io):
table = build_table("test", "syn123", "some_file_name")
for col, row in enumerate(table):
assert_equals(row[0], (col + 1))
assert_equals(row[1], ["c", "d", "e"][col])
assert_equals(len(table), 3)
headers = [
{'name': 'a', 'columnType': 'INTEGER'},
{'name': 'b', 'columnType': 'STRING'}
]
assert_equals(headers, table.headers)
def test_build_table__with_csv():
string_io = StringIOContextManager('a,b\n' '1,c\n' '2,d\n' '3,e')
with patch.object(synapseclient.table, "as_table_columns",
return_value=[Column(name="a", columnType="INTEGER"),
Column(name="b", columnType="STRING")]),\
patch.object(io, "open", return_value=string_io):
table = build_table("test", "syn123", "some_file_name")
for col, row in enumerate(table):
assert_equals(row[0], (col + 1))
assert_equals(row[1], ["c", "d", "e"][col])
assert_equals(len(table), 3)
headers = [{
'name': 'a',
'columnType': 'INTEGER'
}, {
'name': 'b',
'columnType': 'STRING'
}]
assert_equals(headers, table.headers)
def main():
gfile = '../../data/igraphPPI.pkl'
g = pickle.load(open(gfile, 'rb')) #hyp.make_graph_from_dict(gfile)
args = parser.parse_args()
beta = 0.5
proteomics_dictionary = significant_prots(data, 'AML sample', 'Gene',
'LogFoldChange')
gene_dictionary = tumor_genes(data, 'AML sample', 'Gene', 'Tumor VAF')
if args.fromFile is None:
hyphae = dict()
hyphae['mutations'] = hyphalNetwork(gene_dictionary, g.copy(), beta)
hyphae['proteomics'] = hyphalNetwork(proteomics_dictionary, g.copy(),
beta)
for key, this_hyp in hyphae.items():
this_hyp._to_file(key + '_amlPatientData_hypha.pkl')
else:
hyphae = loadFromFile(args.fromFile)
#now compute graph distances to ascertain fidelity
if args.getDist:
res = hyStats.compute_all_distances(hyphae)
res.to_csv('amlNetworkdistances.csv')
tab = table.build_table("AML Network Distances", 'syn22128879', res)
syn.store(tab)
nmi = hyStats.compute_all_nmi(hyphae, g)
nmi.to_csv('amlNMI.csv')
syn.store(File('amlNMI.csv', parent='syn22269875'))
#store distances
for key, this_hyp in hyphae.items():
node_stats = this_hyp.node_stats()
node_stats.to_csv(key + '_nodelist.csv')
tab = table.build_table("AML Network Nodes", 'syn22128879', node_stats)
syn.store(tab)
if args.doEnrich:
if len(this_hyp.forest_enrichment) == 0:
for_e = hyEnrich.go_enrich_forests(this_hyp) #SG, ncbi)
this_hyp.assign_enrichment(for_e, type='forest')
for_e.to_csv(key + 'enrichedForestGoTerms.csv')
syn.store(
File(key + 'enrichedForestGoTerms.csv',
parent='syn22269875'))
this_hyp._to_file(key + '_amlPatientData_hypha.pkl')
if len(this_hyp.community_enrichment) == 0:
com_e = hyEnrich.go_enrich_communities(this_hyp)
this_hyp.assign_enrichment(com_e, type='community')
com_e.to_csv(key + 'enrichedCommunityGOterms.csv')
syn.store(
File(key + 'enrichedCommunityGOterms.csv',
parent='syn22269875'))
this_hyp._to_file(key + '_amlPatientData_hypha.pkl')
##next: compare enrichment between patients mapped to communities
this_hyp.community_stats(prefix=key).to_csv(key +
'_communityStats.csv')
this_hyp.forest_stats().to_csv(key + '_TreeStats.csv')
for files in [
key + '_amlPatientData_hypha.pkl', key + '_communityStats.csv',
key + '_TreeStats.csv'
]:
syn.store(File(files, parent='syn22269875'))