def run(args):
# Load input graph
print "* Loading input graph..."
with open(args.edgelist_file) as infile:
G = nx.Graph()
G.add_edges_from([map(int, l.rstrip().split()[:2]) for l in infile])
print "\t{} nodes with {} edges".format(len(G.nodes()), len(G.edges()))
# Remove self-loops and zero degree nodes, and
# restrict to the largest connected component
print "* Removing self-loops, zero degree nodes, and ",
print "restricting to the largest connected component"
G.remove_edges_from([(u,v) for u, v in G.edges() if u == v])
G.remove_nodes_from([n for n in G.nodes() if G.degree(n) == 0])
G = G.subgraph(sorted(nx.connected_components( G ), key=lambda cc: len(cc), reverse=True)[0])
print "\t{} nodes with {} edges remaining".format(len(G.nodes()), len(G.edges()))
# Load gene index
indexToGene = hnio.load_index(args.gene_index_file)
# Compute and save Laplacian
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
print "* Computing Laplacian..."
L = nx.laplacian_matrix(G)
# Exponentiate the Laplacian for the given time and save it
print "* Computing diffusion matrix..."
Li = expm_eig( -args.time * L.todense() )
#Li = sp.sparse.linalg.expm( -args.time * L)
output_prefix = "{}/{}_inf_{}".format(args.output_dir, args.prefix, args.time)
if args.format == 'hdf5':
hnio.save_hdf5(output_prefix + ".h5", dict(Li=Li))
elif args.format == 'npy':
np.save(output_prefix + ".npy", Li)
# Save the index to gene mapping
indexOutputFile = "{}/{}_index_genes".format(args.output_dir, args.prefix)
nodes = G.nodes()
geneIndexOutput = ["{} {}".format(i+args.start_index, indexToGene[node])
for i, node in enumerate(nodes)]
hnio.write_file(indexOutputFile, "\n".join(geneIndexOutput))
# Create edge list with revised indices
edgeIndices = []
for u, v in G.edges():
i = nodes.index(u) + args.start_index
j = nodes.index(v) + args.start_index
edgeIndices.append( sorted([i, j]) )
edgeOutputFile = "{}/{}_edge_list".format(args.output_dir, args.prefix)
edgeOutput = ["{} {} 1".format(u, v) for u, v in edgeIndices]
hnio.write_file(edgeOutputFile, "\n".join(edgeOutput))
def run(args):
# Load gene-index map
with open(args.gene_index_file) as infile:
arrs = [l.rstrip().split() for l in infile]
indexToGene = dict((int(arr[0]), arr[1]) for arr in arrs)
G = nx.Graph()
G.add_nodes_from(
indexToGene.values()) # in case any nodes have degree zero
# Load graph
print "* Loading PPI..."
with open(args.edgelist_file) as infile:
edges = [map(int, l.rstrip().split()[:2]) for l in infile]
G.add_edges_from([(indexToGene[u], indexToGene[v]) for u, v in edges])
print "\t- Edges:", len(G.edges())
print "\t- Nodes:", len(G.nodes())
# Remove self-loops and restrict to largest connected component
print "* Removing self-loops, multi-edges, and restricting to",
print "largest connected component..."
selfLoops = [(u, v) for u, v in G.edges() if u == v]
G.remove_edges_from(selfLoops)
G = G.subgraph(
sorted(nx.connected_components(G),
key=lambda cc: len(cc),
reverse=True)[0])
nodes = sorted(G.nodes())
n = len(nodes)
print "\t- Largest CC Edges:", len(G.edges())
print "\t- Largest CC Nodes:", len(G.nodes())
# Set up output directory
print "* Saving updated graph to file..."
os.system('mkdir -p ' + args.output_dir)
output_dir = os.path.normpath(os.getcwd() + "/" + args.output_dir)
output_prefix = "{}/{}".format(output_dir, args.prefix)
if args.format == 'hdf5': ext = 'h5'
elif args.format == 'matlab': ext = 'mat'
else: ext = args.format
pprfile = "{}_ppr_{:g}.{}".format(output_prefix, args.beta, ext)
# Index mapping for genes
index_map = [
"{} {}".format(i + args.start_index, nodes[i]) for i in range(n)
]
with open("{}_index_genes".format(output_prefix), 'w') as outfile:
outfile.write("\n".join(index_map))
# Edge list
edges = [
sorted([
nodes.index(u) + args.start_index,
nodes.index(v) + args.start_index
]) for u, v in G.edges()
]
edgelist = ["{} {} 1".format(u, v) for u, v in edges]
with open("{}_edge_list".format(output_prefix), 'w') as outfile:
outfile.write("\n".join(edgelist))
## Create the PPR matrix either using Scipy or MATLAB
# Create "walk" matrix (normalized adjacency matrix)
print "* Creating PPR matrix..."
W = nx.to_numpy_matrix(G, nodelist=nodes, dtype=np.float64)
W = np.asarray(W)
W = W / W.sum(axis=1) # normalization step
## Create PPR matrix using Python
from scipy.linalg import inv
PPR = args.beta * inv(sp.eye(n) - (1. - args.beta) * W)
if args.format == 'hdf5':
hnio.save_hdf5(pprfile, dict(PPR=PPR))
elif args.format == 'npy':
np.save(pprfile, PPR)
elif args.format == 'matlab':
scipy.io.savemat(pprfile, dict(PPR=PPR))
def run(args):
# Load gene-index map
with open(args.gene_index_file) as infile:
arrs = [ l.rstrip().split() for l in infile ]
indexToGene = dict((int(arr[0]), arr[1]) for arr in arrs)
G = nx.Graph()
G.add_nodes_from( indexToGene.values() ) # in case any nodes have degree zero
# Load graph
print "* Loading PPI..."
with open(args.edgelist_file) as infile:
edges = [ map(int, l.rstrip().split()[:2]) for l in infile ]
G.add_edges_from( [(indexToGene[u], indexToGene[v]) for u,v in edges] )
print "\t- Edges:", len(G.edges())
print "\t- Nodes:", len(G.nodes())
# Remove self-loops and restrict to largest connected component
print "* Removing self-loops, multi-edges, and restricting to",
print "largest connected component..."
selfLoops = [(u, v) for u, v in G.edges() if u == v]
G.remove_edges_from( selfLoops )
G = G.subgraph( sorted(nx.connected_components( G ), key=lambda cc: len(cc),
reverse=True)[0] )
nodes = sorted(G.nodes())
n = len(nodes)
print "\t- Largest CC Edges:", len( G.edges() )
print "\t- Largest CC Nodes:", len( G.nodes() )
# Set up output directory
print "* Saving updated graph to file..."
os.system( 'mkdir -p ' + args.output_dir )
output_dir = os.path.normpath(os.getcwd() + "/" + args.output_dir)
output_prefix = "{}/{}".format(output_dir, args.prefix)
if args.format == 'hdf5': ext = 'h5'
elif args.format == 'matlab': ext = 'mat'
else: ext = args.format
pprfile = "{}_ppr_{:g}.{}".format(output_prefix, args.beta, ext)
# Index mapping for genes
index_map = [ "{} {}".format(i+args.start_index, nodes[i]) for i in range(n) ]
with open("{}_index_genes".format(output_prefix), 'w') as outfile:
outfile.write( "\n".join(index_map) )
# Edge list
edges = [sorted([nodes.index(u) + args.start_index,
nodes.index(v) + args.start_index])
for u, v in G.edges()]
edgelist = [ "{} {} 1".format(u, v) for u, v in edges ]
with open("{}_edge_list".format(output_prefix), 'w') as outfile:
outfile.write( "\n".join(edgelist) )
## Create the PPR matrix either using Scipy or MATLAB
# Create "walk" matrix (normalized adjacency matrix)
print "* Creating PPR matrix..."
W = nx.to_numpy_matrix( G , nodelist=nodes, dtype=np.float64 )
W = np.asarray(W)
W = W / W.sum(axis=1) # normalization step
## Create PPR matrix using Python
from scipy.linalg import inv
PPR = args.beta*inv(sp.eye(n)-(1.-args.beta)*W)
if args.format == 'hdf5':
hnio.save_hdf5(pprfile, dict(PPR=PPR))
elif args.format == 'npy':
np.save(pprfile, PPR)
elif args.format == 'matlab':
scipy.io.savemat(pprfile, dict(PPR=PPR))