def load_sif(args):
conn = aql.Connection(args.server)
O = conn.graph(args.db)
proteins = set()
with open(args.input) as handle:
rows = []
for line in handle:
row = line.rstrip().split("\t")
if not (row[0].startswith("CHEBI:")
or row[2].startswith("CHEBI:")):
rows.append(row)
proteins.add(row[0])
proteins.add(row[2])
print "Loading Proteins"
for i in proteins:
O.addVertex(i, "Protein", {})
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in range(0, len(l), n):
yield l[i:i + n]
i = 0
for chunk in chunks(rows, 10000):
b = O.bulkAdd()
for row in chunk:
b.addEdge(row[0], row[2], row[1], {})
b.commit()
i += len(chunk)
print "Loaded %s edges" % i
def run(args):
conn = aql.Connection(args.arachne)
O = conn.graph(args.graph)
ensembl_id = conversions.hugo_ensembl(args.gene)
gid = "gene:" + ensembl_id
sample_mutation_status = {}
query = O.query().V(gid).\
in_("variantIn").mark("variant").\
out("variantCall").where(aql.eq("method", "MUTECT")).mark("callset").\
out("callSetOf").where(aql.eq("sample_type", "Primary Tumor")).mark("sample").\
in_("fileFor").mark("cel")
if args.project is not None:
query = query.where(aql.eq("project", args.project))
query = query.mark("cel").\
select(["variant", "sample", "callset", "cel"])
for res in query:
if res.variant.data.alternateBases != res.variant.data.referenceBases:
if res.cel.data.individual_barcode not in sample_mutation_status:
sample_mutation_status[res.cel.data.individual_barcode] = 2
query = O.query().V().where(aql.eq("_label", "CELFile"))
if args.project is not None:
query = query.where(aql.eq("project", args.project))
for res in query:
if res.data.individual_barcode not in sample_mutation_status:
sample_mutation_status[res.data.individual_barcode] = 1
for k in sample_mutation_status:
print(k, k, sample_mutation_status[k], sep="\t")
return
def load_matrix(args):
conn = aql.Connection(args.server)
O = conn.graph(args.db)
matrix = pandas.read_csv(args.input, sep="\t", index_col=0).transpose()
for c in matrix.columns:
if list(O.query().V(c).count())[0]['count'] == 0:
if args.debug:
print("AddVertex", c)
else:
O.addVertex(c, "Protein")
for name, row in matrix.iterrows():
src = "%s:%s" % (args.data_type, name)
print("Loading: %s" % (src))
data = {}
for c in matrix.columns:
v = row[c]
if not math.isnan(v):
data[c] = v
if args.debug:
print("Add Vertex", name)
else:
O.addVertex(name, "Sample")
if args.debug:
print("AddVertex", "Data:%s" % (args.data_type))
else:
O.addVertex(src, "Data:%s" % (args.data_type), data)
if args.debug:
print("AddEdge", name)
else:
O.addEdge(name, src, "has")
def load_matrix(args):
conn = aql.Connection(args.server)
O = conn.graph(args.db)
matrix = pandas.read_csv(args.input, sep="\t", index_col=0)
for name, row in matrix.iterrows():
data = {}
for k, v in row.iteritems():
if not isinstance(v, float) or not math.isnan(v):
data[k] = v
O.addVertex(name, "Sample", data)
#!/usr/bin/env python
import aql
import json
conn = aql.Connection("http://localhost:8201")
conn.delete("test-graph")
conn.new("test-graph")
O = conn.graph("test-graph")
O.addVertex("1", "Person", {"name": "marko", "age": "29"})
O.addVertex("2", "Person", {"name": "vadas", "age": "27"})
O.addVertex("3", "Software", {"name": "lop", "lang": "java"})
O.addVertex("4", "Person", {"name": "josh", "age": "32"})
O.addVertex("5", "Software", {"name": "ripple", "lang": "java"})
O.addVertex("6", "Person", {"name": "peter", "age": "35"})
O.addEdge("1", "3", "created", {"weight": 0.4})
O.addEdge("1", "2", "knows", {"weight": 0.5})
O.addEdge("1", "4", "knows", {"weight": 1.0})
O.addEdge("4", "3", "created", {"weight": 0.4})
O.addEdge("6", "3", "created", {"weight": 0.2})
O.addEdge("4", "5", "created", {"weight": 1.0})
"""
query = O.query().V()
"""
query = O.query().V().match([
O.mark('a').outgoing('created').mark('b'),
O.mark('b').has('name', 'lop'),
BASE = os.path.dirname(os.path.abspath(__file__))
TESTS = os.path.join(BASE, "tests")
AQL = os.path.join(os.path.dirname(BASE), "aql", "python")
GRAPH = "test_graph"
sys.path.append(AQL)
import aql
if __name__ == "__main__":
server = sys.argv[1]
if len(sys.argv) > 2:
tests = sys.argv[2:]
else:
tests = []
conn = aql.Connection(server)
if GRAPH in conn.listGraphs():
print(list(conn.graph(GRAPH).query().V().count())[0])
if int(list(conn.graph(GRAPH).query().V().count())[0]['count']) != 0:
print("Need to start with empty DB: %s" % (GRAPH))
sys.exit()
correct = 0
total = 0
for a in glob(os.path.join(TESTS, "ot_*.py")):
name = os.path.basename(a)[:-3]
if len(tests) == 0 or name[3:] in tests:
mod = imp.load_source('test.%s' % name, a)
for f in dir(mod):
if f.startswith("test_"):
func = getattr(mod, f)