def mp_worker((k, sigma, distancePath, dtype)):
"""
run spectral clustering
"""
sc = SpectralCluster(distancePath, dtype=dtype)
sc.run(k, sk=None, sigma=sigma, verbose=True)
return sc
def mp_worker((k,sigma,distancePath,dtype)):
"""
run spectral clustering
"""
sc = SpectralCluster(distancePath,dtype=dtype)
sc.run(k,sk=None,sigma=sigma,verbose=True)
return sc
def _run_sc(self, toRun):
"""
run spectral clustering (single core)
"""
for params in toRun:
k, sigma, dpath, dtype = params
sc = SpectralCluster(self.distancePath, dtype=dtype)
sc.run(k, sk=None, sigma=sigma, verbose=True)
clusterSizes = self.get_cluster_sizes(sc)
self.writer1.writerow([k, sigma] + [round(sc.avgSilValue, 4)])
self.writer2.writerow([k, sigma] + clusterSizes)
def _run_sc(self,toRun):
"""
run spectral clustering (single core)
"""
for params in toRun:
k,sigma,dpath,dtype = params
sc = SpectralCluster(self.distancePath,dtype=dtype)
sc.run(k,sk=None,sigma=sigma,verbose=True)
clusterSizes = self.get_cluster_sizes(sc)
self.writer1.writerow([k,sigma] + [round(sc.avgSilValue,4)])
self.writer2.writerow([k,sigma] + clusterSizes)
def __init__(self,
distancePath,
dtype='distance',
aspect='biological_process'):
"""
distancePath - path to distance matrix
dype = distance [default] or similarity
aspect = biological_process, molecular_function, or cellular_component
"""
## input
if os.path.exists(distancePath) == False:
raise Exception("cannot find distances file %s\nexiting..." %
(distancePath))
if dtype not in ['distance', 'similarity']:
raise Exception("Invalid distant type (dtype) specified")
## call an instance of SpectralClustering to ensure labels and matrix files are saved
self.dtype = dtype
self.aspect = aspect
self.distancePath = distancePath
sc = SpectralCluster(distancePath, dtype=dtype)
matrixPath = re.sub("\.csv", "-matrix.npy", distancePath)
genesPath = re.sub("\.csv", "-genes.npy", distancePath)
self.M = np.load(matrixPath)
self.items = np.load(genesPath)
## output
self.resultsPath1 = re.sub("\.csv", "-scparams-sv.csv", distancePath)
self.resultsPath2 = re.sub("\.csv", "-scparams-cl.csv", distancePath)
scps = SpectralClusterParamSearch(geneDistancePath,dtype='distance')
scps.run(chunks=15)
## plot the parameter search
psFigureFile = os.path.join(homeDir,"param-scan-%s.png"%(_aspect))
if not os.path.exists(psFigureFile):
scr = SpectralClusterResults(silvalFile,clustersFile)
scr.plot(figName=psFigureFile)
## run spectral clustering
k = 20
sigma = 0.08
labelsPath = os.path.join(homeDir,"sc-labels-%s.csv"%(_aspect))
if not os.path.exists(labelsPath):
sc = SpectralCluster(geneDistancePath,dtype='distance')
sc.run(k,sk=None,sigma=sigma,verbose=True)
sc.save(labelsPath=labelsPath)
## Save gene sets
bm = BlastMapper()
bmap = bm.load_summary('blast-parsed-summary.csv',best=False,taxaList=['8355','8364'])
transcriptMin,transcriptMax = 9,1000
gsFile = os.path.join(homeDir,"%s.gmt"%(_aspect))
if not os.path.exists(gsFile):
gsc = GeneSetCollection(labelsPath,gene2go)
gsc.write(blastMap=bmap,transcriptMin=transcriptMin,transcriptMax=transcriptMax,outFile=gsFile)
print("process complete.")
scps.run(chunks=5, kRange=range(3, 11))
## plot the parameter search
psFigureFile = os.path.join(gsaDir, "param-scan-%s.png" % (_aspect))
if not os.path.exists(psFigureFile):
scr = SpectralClusterResults(silvalFile, clustersFile)
scr.plot(figName=psFigureFile)
## run spectral clustering
k = 3
sigma = 0.43
labelsPath = os.path.join(gsaDir, "sc-labels-%s.csv" % (_aspect))
if not os.path.exists(labelsPath):
sc = SpectralCluster(geneDistancePath, dtype='distance')
sc.run(k, sk=None, sigma=sigma, verbose=True)
sc.save(labelsPath=labelsPath)
import networkx
from parse_KGML import KGML2Graph
from KeggPathway import KeggPathway
p = KeggPathway()
#p.add_node('gene1', data={'type': 'gene', })
#p.get_node('gene1')
#{'type': 'gene'}
graphfile = "%s.xml" % pathway
graph = KGML2Graph(graphfile)[1]