def graph(args):
"""
%prog graph best.edges
Convert Celera Assembler's "best.edges" to a GEXF which can be used to
feed into Gephi to check the topology of the best overlapping graph. Mutual
best edges are represented as thicker edges.
Reference:
https://github.com/PacificBiosciences/Bioinformatics-Training/blob/master/scripts/CeleraToGephi.py
"""
p = OptionParser(graph.__doc__)
p.add_option(
"--query",
default=-1,
type="int",
help="Search from node, -1 to select random node, 0 to disable",
)
p.add_option("--contig", help="Search from contigs, use comma to separate")
p.add_option("--largest",
default=0,
type="int",
help="Only show largest components")
p.add_option("--maxsize", default=500, type="int", help="Max graph size")
p.add_option(
"--nomutualbest",
default=False,
action="store_true",
help="Do not plot mutual best edges as heavy",
)
add_graph_options(p)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
(bestedges, ) = args
query = opts.query
contig = opts.contig
largest = opts.largest
frgctg = opts.frgctg
edgeweight = not opts.nomutualbest
G = read_graph(bestedges, maxerr=opts.maxerr)
if largest:
H = list(nx.connected_component_subgraphs(G))
c = min(len(H), largest)
logging.debug("{0} components found, {1} retained".format(len(H), c))
G = nx.Graph()
for x in H[:c]:
G.add_edges_from(x.edges())
if query:
if query == -1:
query = choice(G.nodes())
reads_to_ctgs = parse_ctgs(bestedges, frgctg)
if contig:
contigs = set(contig.split(","))
core = [k for k, v in reads_to_ctgs.items() if v in contigs]
else:
ctg = reads_to_ctgs.get(query)
core = [k for k, v in reads_to_ctgs.items() if v == ctg]
logging.debug(
"Reads ({0}) extended from the same contig {1}".format(
len(core), ctg))
# Extract a local neighborhood
SG = nx.Graph()
H = graph_local_neighborhood(G, query=core, maxsize=opts.maxsize)
SG.add_edges_from(H.edges(data=edgeweight))
G = SG
seen = []
for n, attrib in G.nodes_iter(data=True):
contig = reads_to_ctgs.get(n, "na")
attrib["label"] = contig
seen.append(contig)
c = Counter(seen)
cc = ["{0}({1})".format(k, v) for k, v in c.most_common()]
print("Contigs: {0}".format(" ".join(cc)), file=sys.stderr)
gexf = "best"
if query >= 0:
gexf += ".{0}".format(query)
gexf += ".gexf"
nx.write_gexf(G, gexf)
logging.debug("Graph written to `{0}` (|V|={1}, |E|={2})".format(
gexf, len(G), G.size()))
def graph(args):
"""
%prog graph best.edges
Convert Celera Assembler's "best.edges" to a GEXF which can be used to
feed into Gephi to check the topology of the best overlapping graph. Mutual
best edges are represented as thicker edges.
Reference:
https://github.com/PacificBiosciences/Bioinformatics-Training/blob/master/scripts/CeleraToGephi.py
"""
p = OptionParser(graph.__doc__)
p.add_option("--query", default=-1, type="int", help="Search from node, -1 to select random node, 0 to disable")
p.add_option("--contig", help="Search from contigs, use comma to separate")
p.add_option("--largest", default=0, type="int", help="Only show largest components")
p.add_option("--maxsize", default=500, type="int", help="Max graph size")
p.add_option("--nomutualbest", default=False, action="store_true", help="Do not plot mutual best edges as heavy")
add_graph_options(p)
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
bestedges, = args
query = opts.query
contig = opts.contig
largest = opts.largest
frgctg = opts.frgctg
edgeweight = not opts.nomutualbest
G = read_graph(bestedges, maxerr=opts.maxerr)
if largest:
H = list(nx.connected_component_subgraphs(G))
c = min(len(H), largest)
logging.debug("{0} components found, {1} retained".format(len(H), c))
G = nx.Graph()
for x in H[:c]:
G.add_edges_from(x.edges())
if query:
if query == -1:
query = choice(G.nodes())
reads_to_ctgs = parse_ctgs(bestedges, frgctg)
if contig:
contigs = set(contig.split(","))
core = [k for k, v in reads_to_ctgs.items() if v in contigs]
else:
ctg = reads_to_ctgs.get(query)
core = [k for k, v in reads_to_ctgs.items() if v == ctg]
logging.debug("Reads ({0}) extended from the same contig {1}".format(len(core), ctg))
# Extract a local neighborhood
SG = nx.Graph()
H = graph_local_neighborhood(G, query=core, maxsize=opts.maxsize)
SG.add_edges_from(H.edges(data=edgeweight))
G = SG
seen = []
for n, attrib in G.nodes_iter(data=True):
contig = reads_to_ctgs.get(n, "na")
attrib["label"] = contig
seen.append(contig)
c = Counter(seen)
cc = ["{0}({1})".format(k, v) for k, v in c.most_common()]
print >> sys.stderr, "Contigs: {0}".format(" ".join(cc))
gexf = "best"
if query >= 0:
gexf += ".{0}".format(query)
gexf += ".gexf"
nx.write_gexf(G, gexf)
logging.debug("Graph written to `{0}` (|V|={1}, |E|={2})".format(gexf, len(G), G.size()))
def graph(args):
"""
%prog graph best.edges
Convert Celera Assembler's "best.edges" to a GEXF which can be used to
feed into Gephi to check the topology of the best overlapping graph.
Reference:
https://github.com/PacificBiosciences/Bioinformatics-Training/blob/master/scripts/CeleraToGephi.py
"""
import networkx as nx
from jcvi.algorithms.graph import graph_stats, graph_local_neighborhood
p = OptionParser(graph.__doc__)
p.add_option("--maxerr", default=100, type="int", help="Maximum error rate")
p.add_option("--query", default=-1, type="int", help="Search from node")
p.add_option("--largest", default=1, type="int", help="Only show largest components")
p.add_option("--maxsize", default=100, type="int", help="Max graph size")
p.add_option("--contigs", help="Annotate graph with contig membership, "
" typically from `asm.posmap.frgctg`")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
bestedges, = args
maxerr = opts.maxerr
query = opts.query
largest = opts.largest
logging.debug("Max error = {0}%".format(maxerr))
bestgraph = bestedges.split(".")[0] + ".err{0}.graph".format(maxerr)
if need_update(bestedges, bestgraph):
G = nx.Graph()
fp = open(bestedges)
for row in fp:
if row[0] == '#':
continue
id1, lib_id, best5, o1, best3, o3, j1, j2 = row.split()
id1, best5, best3 = int(id1), int(best5), int(best3)
j1, j2 = float(j1), float(j2)
if j1 < maxerr or j2 < maxerr:
G.add_node(id1)
if best5 != '0' and j1 < maxerr:
G.add_edge(best5, id1)
if best3 != '0' and j2 < maxerr:
G.add_edge(id1, best3)
nx.write_gpickle(G, bestgraph)
logging.debug("Graph pickled to `{0}`".format(bestgraph))
logging.debug("Read graph from `{0}`".format(bestgraph))
G = nx.read_gpickle(bestgraph)
graph_stats(G)
if len(G) > 10000:
SG = nx.Graph()
H = graph_local_neighborhood(G, query=query,
maxsize=opts.maxsize)
SG.add_edges_from(H.edges())
G = SG
if largest > 1: # only works for un-directed graph
H = nx.connected_component_subgraphs(G)
c = min(len(H), largest)
logging.debug("{0} components found, {1} retained".format(len(H), c))
G = nx.Graph()
for x in H[:c]:
G.add_edges_from(x.edges())
if opts.contigs:
reads_to_ctgs = parse_ctgs(bestedges, opts.contigs)
annotate_contigs(G, reads_to_ctgs)
gexf = "best"
if query >= 0:
gexf += ".{0}".format(query)
gexf += ".gexf"
nx.write_gexf(G, gexf)
logging.debug("Graph written to `{0}` (|V|={1}, |E|={2})".\
format(gexf, len(G), G.size()))
