def main(argv):
kmers = files.read_lines(argv[0])
edges = graphs.debruijn_graph(kmers)
adj = graphs.adjacency_table(edges)
print '\n'.join('%s -> %s' % (head, ','.join(sorted(adj[head])))
for head in sorted(adj))
def main(argv):
n, m, edges = files.read_graph(argv[0])
adjacency = graphs.adjacency_table(edges, directed=False)
D = []
for i in xrange(1, n + 1):
D.append(sum(len(adjacency[node]) for node in adjacency[i]))
print ' '.join(str(d) for d in D)
def main(argv):
lines = files.read_lines(argv[0])
k = int(lines[0])
text = lines[1]
kmers = genetics.list_kmers(text, k)
edges = graphs.debruijn_graph(kmers)
adj = graphs.adjacency_table(edges)
print '\n'.join('%s -> %s' % (head, ','.join(sorted(adj[head])))
for head in sorted(adj))
def assemble_genome_from_reads(reads):
length = len(reads[0])
for i in xrange(length - 1, 1, -1):
kmers = kmer_candidates(reads, i, rc=True)
edges = graphs.debruijn_graph(kmers)
adj = graphs.adjacency_table(edges)
if len(graphs.connected_components_iterative(adj)) == 2:
path = graphs.eulerian_cycle(edges[0][1], edges)
return reconstruct_circular_string_from_path(path)
return None
def two_break_distance(P, Q):
edges = set()
for genome in [P, Q]:
for edge in colored_edges_from_genome(genome):
edges.add(edge)
# nodes = graphs.nodes_from_edges(edges)
# components = graphs.connected_components(nodes, edges, False)
adjacency = graphs.adjacency_table(edges, False)
components = graphs.connected_components_iterative(adjacency)
return sum(len(g) for g in P) - len(components)