def test_deserialize():
gfa_graph = mod.GFAGraph()
gfa_graph.add_node('node1', 7, 'ACTGAAA', tags={}, labels={})
gfa_graph.add_node('node2', 10, 'AAACCCGGGT', tags={}, labels={})
gfa_graph.add_edge('edge1',
'node1',
'+',
'node2',
'+',
4,
7,
0,
3,
'*',
tags={},
labels={})
gfa_graph.add_path('000000F', ['node1', 'node2'], ['4M', '7M'],
tags={},
labels={'label1': 'test'})
dump = mod.serialize_gfa(gfa_graph)
fp_in = StringIO(dump)
result = mod.deserialize_gfa(fp_in)
assert (result.nodes == gfa_graph.nodes)
assert (result.edges == gfa_graph.edges)
assert (result.paths == gfa_graph.paths)
def test_serialize():
gfa_graph = mod.GFAGraph()
gfa_graph.add_node('node1', 7, 'ACTGAAA', tags={}, labels={})
gfa_graph.add_node('node2', 10, 'AAACCCGGGT', tags={}, labels={})
gfa_graph.add_edge('edge1', 'node1', '+', 'node2', '+', 4, 7, 0, 3, '*', tags={}, labels={})
gfa_graph.add_path('000000F', ['node1', 'node2'], ['4M', '7M'], tags={}, labels={'label1': 'test'})
result = mod.serialize_gfa(gfa_graph)
expected = '{"paths": {"000000F": {"labels": {"label1": "test"}, "nodes": ["node1", "node2"], "tags": {}, "name": "000000F", "cigars": ["4M", "7M"]}}, "nodes": {"node1": {"labels": {}, "seq": "ACTGAAA", "name": "node1", "len": 7, "tags": {}}, "node2": {"labels": {}, "seq": "AAACCCGGGT", "name": "node2", "len": 10, "tags": {}}}, "edges": {"(\'node1\', \'node2\')": {"labels": {}, "v_orient": "+", "tags": {}, "v_start": 4, "cigar": "*", "w_end": 3, "w_start": 0, "w_orient": "+", "name": "edge1", "v_end": 7, "w": "node2", "v": "node1"}}}'
assert(result == expected)
def run(fp_out, p_ctg_tiling_path, a_ctg_tiling_path,
p_ctg_fasta, a_ctg_fasta,
write_contigs,
min_p_len, min_a_len, only_these_contigs):
gfa_graph = GFAGraph()
# Load the primary and associate contig files.
p_ctg_dict = falcon_kit.mains.collect_pread_gfa.load_seqs(p_ctg_fasta, (not write_contigs))
p_ctg_lens = {key: val[0] for key, val in p_ctg_dict.iteritems()}
p_ctg_seqs = {key: val[1] for key, val in p_ctg_dict.iteritems()}
a_ctg_dict = falcon_kit.mains.collect_pread_gfa.load_seqs(a_ctg_fasta, (not write_contigs))
a_ctg_lens = {key: val[0] for key, val in a_ctg_dict.iteritems()}
a_ctg_seqs = {key: val[1] for key, val in a_ctg_dict.iteritems()}
# Create whitelists for filtering contigs.
p_ctg_whitelist = set(p_ctg_seqs.keys())
a_ctg_whitelist = set([key for key in a_ctg_seqs.keys()])
if only_these_contigs:
p_ctg_whitelist = set(open(only_these_contigs).read().splitlines()) & set(p_ctg_whitelist)
a_ctg_whitelist = set([key for key in a_ctg_seqs.keys() if key.split('-')[0].split('_')[0] in p_ctg_whitelist])
# Load the tiling paths and assign coordinates.
p_paths = falcon_kit.tiling_path.load_tiling_paths(p_ctg_tiling_path, whitelist_seqs=p_ctg_whitelist, contig_lens=p_ctg_lens)
a_paths = falcon_kit.tiling_path.load_tiling_paths(a_ctg_tiling_path, whitelist_seqs=a_ctg_whitelist, contig_lens=a_ctg_lens)
# Find the associate contig placement. `a_placement` is a dict:
# placement[p_ctg_id][a_ctg_id] = (start, end, p_ctg_id, a_ctg_id, first_node, last_node)
a_placement = falcon_kit.tiling_path.find_a_ctg_placement(p_paths, a_paths)
# Add the nodes.
for ctg_id, tiling_path in p_paths.iteritems():
gfa_graph.add_node(ctg_id, p_ctg_lens[ctg_id], p_ctg_seqs[ctg_id])
for ctg_id, tiling_path in a_paths.iteritems():
gfa_graph.add_node(ctg_id, a_ctg_lens[ctg_id], a_ctg_seqs[ctg_id])
for p_ctg_id, a_dict in a_placement.iteritems():
for a_ctg_id, placement in a_dict.iteritems():
start, end, p_ctg_id, a_ctg_id, first_node, last_node = placement
a_ctg_len = a_ctg_lens[a_ctg_id]
# edge_name = 'edge-%d-out-%s-to-%s' % (len(gfa_graph.edges), a_ctg_id, p_ctg_id)
edge_name = 'edge-%d' % (len(gfa_graph.edges))
gfa_graph.add_edge(edge_name, p_ctg_id, '+', a_ctg_id, '+', start, start, 0, 0, '*', tags = {}, labels = {})
# edge_name = 'edge-%d-in-%s-to-%s' % (len(gfa_graph.edges), a_ctg_id, p_ctg_id)
edge_name = 'edge-%d' % (len(gfa_graph.edges))
gfa_graph.add_edge(edge_name, a_ctg_id, '+', p_ctg_id, '+', a_ctg_len, a_ctg_len, end, end, '*', tags = {}, labels = {})
fp_out.write(serialize_gfa(gfa_graph))
fp_out.write('\n')
def test_deserialize():
gfa_graph = mod.GFAGraph()
gfa_graph.add_node('node1', 7, 'ACTGAAA', tags={}, labels={})
gfa_graph.add_node('node2', 10, 'AAACCCGGGT', tags={}, labels={})
gfa_graph.add_edge('edge1', 'node1', '+', 'node2', '+', 4, 7, 0, 3, '*', tags={}, labels={})
gfa_graph.add_path('000000F', ['node1', 'node2'], ['4M', '7M'], tags={}, labels={'label1': 'test'})
dump = mod.serialize_gfa(gfa_graph)
fp_in = StringIO(dump)
result = mod.deserialize_gfa(fp_in)
assert (result.nodes == gfa_graph.nodes)
assert (result.edges == gfa_graph.edges)
assert (result.paths == gfa_graph.paths)
def test_serialize():
gfa_graph = mod.GFAGraph()
gfa_graph.add_node('node1', 7, 'ACTGAAA', tags={}, labels={})
gfa_graph.add_node('node2', 10, 'AAACCCGGGT', tags={}, labels={})
gfa_graph.add_edge('edge1',
'node1',
'+',
'node2',
'+',
4,
7,
0,
3,
'*',
tags={},
labels={})
gfa_graph.add_path('000000F', ['node1', 'node2'], ['4M', '7M'],
tags={},
labels={'label1': 'test'})
result = mod.serialize_gfa(gfa_graph)
expected = '{"paths": {"000000F": {"labels": {"label1": "test"}, "nodes": ["node1", "node2"], "tags": {}, "name": "000000F", "cigars": ["4M", "7M"]}}, "nodes": {"node1": {"labels": {}, "seq": "ACTGAAA", "name": "node1", "len": 7, "tags": {}}, "node2": {"labels": {}, "seq": "AAACCCGGGT", "name": "node2", "len": 10, "tags": {}}}, "edges": {"(\'node1\', \'node2\')": {"labels": {}, "v_orient": "+", "tags": {}, "v_start": 4, "cigar": "*", "w_end": 3, "w_start": 0, "w_orient": "+", "name": "edge1", "v_end": 7, "w": "node2", "v": "node1"}}}'
assert (result == expected)