def generate_read_to_ctg_map(self):
rawread_id_file = fn(self.rawread_id_file)
pread_id_file = fn(self.pread_id_file)
read_to_contig_map = fn(self.read_to_contig_map)
pread_did_to_rid = open(pread_id_file).read().split("\n")
rid_to_oid = open(rawread_id_file).read().split("\n")
asm_G = AsmGraph(fn(self.sg_edges_list), fn(self.utg_data), fn(self.ctg_paths))
pread_to_contigs = {}
with open(read_to_contig_map, "w") as f:
for ctg in asm_G.ctg_data:
if ctg[-1] == "R":
continue
ctg_g = asm_G.get_sg_for_ctg(ctg)
for n in ctg_g.nodes():
pid = int(n.split(":")[0])
rid = pread_did_to_rid[pid].split("/")[1]
rid = int(int(rid) / 10)
oid = rid_to_oid[rid]
k = (pid, rid, oid)
pread_to_contigs.setdefault(k, set())
pread_to_contigs[k].add(ctg)
for k in pread_to_contigs:
pid, rid, oid = k
for ctg in list(pread_to_contigs[k]):
print >> f, "%09d %09d %s %s" % (pid, rid, oid, ctg)
def generate_read_to_ctg_map(self):
rawread_id_file = fn(self.rawread_id_file)
pread_id_file = fn(self.pread_id_file)
read_to_contig_map = fn(self.read_to_contig_map)
pread_did_to_rid = open(pread_id_file).read().split('\n')
rid_to_oid = open(rawread_id_file).read().split('\n')
asm_G = AsmGraph(fn(self.sg_edges_list), fn(self.utg_data),
fn(self.ctg_paths))
pread_to_contigs = {}
with open(read_to_contig_map, 'w') as f:
for ctg in asm_G.ctg_data:
if ctg[-1] == 'R':
continue
ctg_g = asm_G.get_sg_for_ctg(ctg)
for n in ctg_g.nodes():
pid = int(n.split(':')[0])
rid = pread_did_to_rid[pid].split('/')[1]
rid = int(int(rid) / 10)
oid = rid_to_oid[rid]
k = (pid, rid, oid)
pread_to_contigs.setdefault(k, set())
pread_to_contigs[k].add(ctg)
for k in pread_to_contigs:
pid, rid, oid = k
for ctg in list(pread_to_contigs[k]):
print >> f, '%09d %09d %s %s' % (pid, rid, oid, ctg)
def test_add_nx_string_graph():
# Load the assembly graph.
sg_edges_list = os.path.join(helpers.get_test_data_dir(), 'gfa-1',
'sg_edges_list')
utg_data = os.path.join(helpers.get_test_data_dir(), 'gfa-1', 'utg_data')
ctg_paths = os.path.join(helpers.get_test_data_dir(), 'gfa-1', 'ctg_paths')
asm_graph = AsmGraph(sg_edges_list, utg_data, ctg_paths)
# The following block is taken from Unzip, graphs_to_h_tigs.py.
nx_sg = nx.DiGraph()
arid_to_phase = {}
for ctg_id in asm_graph.ctg_data.keys():
ctg_G = asm_graph.get_sg_for_ctg(ctg_id)
ctg_nodes = set(ctg_G.nodes())
for v, w in ctg_G.edges():
vrid = v[:9]
wrid = w[:9]
edge_data = asm_graph.sg_edges[(v, w)]
if edge_data[-1] != "G":
continue
vphase = arid_to_phase.get(vrid, (-1, 0))
wphase = arid_to_phase.get(wrid, (-1, 0))
if vphase[0] == wphase[0] and vphase[1] != wphase[1]:
cross_phase = "Y"
else:
cross_phase = "N"
nx_sg.add_node(v,
label="%d_%d" % vphase,
phase="%d_%d" % vphase,
src="P")
nx_sg.add_node(w,
label="%d_%d" % wphase,
phase="%d_%d" % wphase,
src="P")
nx_sg.add_edge(v, w, src="OP", cross_phase=cross_phase)
# we need to add the complimentary edges as the ctg_graph does not contain the dual edges
rv = reverse_end(v)
rw = reverse_end(w)
nx_sg.add_node(rv,
label="%d_%d" % vphase,
phase="%d_%d" % vphase,
src="P")
nx_sg.add_node(rw,
label="%d_%d" % wphase,
phase="%d_%d" % wphase,
src="P")
nx_sg.add_edge(rw, rv, src="OP", cross_phase=cross_phase)
# Add the string graph to the GFA.
gfa_graph = mod.GFAGraph()
gexf_file = os.path.join(helpers.get_test_data_dir(), 'gfa-1', 'sg.gexf')
nx_sg = nx.read_gexf(gexf_file)
gfa_graph.add_nx_string_graph(nx_sg)
