def evaluate(options, svm, kernel, features, motifs):
"""Evaluate examples using a trained kernel"""
query = MotifFinder(finder_settings=MotifFinderSettings(
kirmes_ini.MOTIF_LENGTH, options.window_width))
query.setFastaFile(options.query)
query.setMotifs(options.qgff)
qmotifs, qpositions = query.getResults()
feats_query = CombinedFeatures()
wds_svm = EasySVM.EasySVM(kirmes_ini.WDS_KERNEL_PARAMETERS)
try:
assert set(qmotifs.keys()).issuperset(set(motifs))
except AssertionError:
print "The motif positions in the query sequence are incomplete, there are no positions for:"
print set(motifs).difference(qmotifs.keys())
raise
for motif in motifs:
feats_query.append_feature_obj(wds_svm.createFeatures(qmotifs[motif]))
query_positions = array(qpositions, dtype=float64)
query_positions = query_positions.T
rbf_svm = EasySVM.EasySVM(kirmes_ini.RBF_KERNEL_PARAMETERS)
feats_query.append_feature_obj(rbf_svm.createFeatures(query_positions))
kernel.init(features, feats_query)
out = svm.classify().get_labels()
qgenes = query.getGenes()
ret_str = ""
print "#example\toutput\tsplit"
for i in xrange(len(out)):
if out[i] >= 0:
classif = "\tpositive\t"
else:
classif = "\tnegative\t"
ret_str += qgenes[i] + classif + str(out[i]) + "\n"
print str(i) + "\t" + str(out[i]) + "\t0"
return ret_str
def evaluate(options, svm, kernel, features, motifs):
"""Evaluate examples using a trained kernel"""
query = MotifFinder(finder_settings=MotifFinderSettings(kirmes_ini.MOTIF_LENGTH, options.window_width))
query.setFastaFile(options.query)
query.setMotifs(options.qgff)
qmotifs, qpositions = query.getResults()
feats_query = CombinedFeatures()
wds_svm = EasySVM.EasySVM(kirmes_ini.WDS_KERNEL_PARAMETERS)
try:
assert set(qmotifs.keys()).issuperset(set(motifs))
except AssertionError:
print "The motif positions in the query sequence are incomplete, there are no positions for:"
print set(motifs).difference(qmotifs.keys())
raise
for motif in motifs:
feats_query.append_feature_obj(wds_svm.createFeatures(qmotifs[motif]))
query_positions = array(qpositions, dtype=float64)
query_positions = query_positions.T
rbf_svm = EasySVM.EasySVM(kirmes_ini.RBF_KERNEL_PARAMETERS)
feats_query.append_feature_obj(rbf_svm.createFeatures(query_positions))
kernel.init(features, feats_query)
out = svm.classify().get_labels()
qgenes = query.getGenes()
ret_str = ""
print "#example\toutput\tsplit"
for i in xrange(len(out)):
if out[i] >= 0:
classif = "\tpositive\t"
else:
classif = "\tnegative\t"
ret_str += qgenes[i] + classif + str(out[i]) + "\n"
print str(i) + "\t" + str(out[i]) + "\t0"
return ret_str
def training_run(options):
"""Conduct a training run and return a trained SVM kernel"""
settings = MotifFinderSettings(kirmes_ini.MOTIF_LENGTH, options.window_width, options.replace)
positives = MotifFinder(finder_settings=settings)
positives.setFastaFile(options.positives)
positives.setMotifs(options.pgff)
pmotifs, ppositions = positives.getResults()
negatives = MotifFinder(finder_settings=settings)
negatives.setFastaFile(options.negatives)
negatives.setMotifs(options.ngff)
nmotifs, npositions = negatives.getResults()
wds_kparams = kirmes_ini.WDS_KERNEL_PARAMETERS
wds_svm = EasySVM.EasySVM(wds_kparams)
num_positives = len(pmotifs.values()[0])
num_negatives = len(nmotifs.values()[0])
# Creating Kernel Objects
kernel = CombinedKernel()
features = CombinedFeatures()
kernel_array = []
motifs = pmotifs.keys()
motifs.sort()
# Adding Kmer Kernels
for motif in motifs:
all_examples = pmotifs[motif] + nmotifs[motif]
motif_features = wds_svm.createFeatures(all_examples)
wds_kernel = WeightedDegreePositionStringKernel(motif_features, motif_features, wds_kparams["degree"])
wds_kernel.set_shifts(wds_kparams["shift"] * ones(wds_kparams["seqlength"], dtype=int32))
features.append_feature_obj(motif_features)
kernel_array.append(wds_kernel)
kernel.append_kernel(wds_kernel)
rbf_svm = EasySVM.EasySVM(kirmes_ini.RBF_KERNEL_PARAMETERS)
positions = array(ppositions + npositions, dtype=float64).T
position_features = rbf_svm.createFeatures(positions)
features.append_feature_obj(position_features)
motif_labels = append(ones(num_positives), -ones(num_negatives))
complete_labels = Labels(motif_labels)
rbf_kernel = GaussianKernel(position_features, position_features, kirmes_ini.RBF_KERNEL_PARAMETERS["width"])
kernel_array.append(rbf_kernel)
kernel.append_kernel(rbf_kernel)
# Kernel init
kernel.init(features, features)
kernel.set_cache_size(kirmes_ini.K_CACHE_SIZE)
svm = LibSVM(kirmes_ini.K_COMBINED_C, kernel, complete_labels)
svm.parallel.set_num_threads(kirmes_ini.K_NUM_THREADS)
# Training
svm.train()
if not os.path.exists(options.output_path):
os.mkdir(options.output_path)
html = {}
if options.contrib:
html["contrib"] = contrib(svm, kernel, motif_labels, kernel_array, motifs)
if options.logos:
html["poims"] = poims(svm, kernel, kernel_array, motifs, options.output_path)
if options.query:
html["query"] = evaluate(options, svm, kernel, features, motifs)
htmlize(html, options.output_html)
def training_run(options):
"""Conduct a training run and return a trained SVM kernel"""
settings = MotifFinderSettings(kirmes_ini.MOTIF_LENGTH,
options.window_width, options.replace)
positives = MotifFinder(finder_settings=settings)
positives.setFastaFile(options.positives)
positives.setMotifs(options.pgff)
pmotifs, ppositions = positives.getResults()
negatives = MotifFinder(finder_settings=settings)
negatives.setFastaFile(options.negatives)
negatives.setMotifs(options.ngff)
nmotifs, npositions = negatives.getResults()
wds_kparams = kirmes_ini.WDS_KERNEL_PARAMETERS
wds_svm = EasySVM.EasySVM(wds_kparams)
num_positives = len(pmotifs.values()[0])
num_negatives = len(nmotifs.values()[0])
#Creating Kernel Objects
kernel = CombinedKernel()
features = CombinedFeatures()
kernel_array = []
motifs = pmotifs.keys()
motifs.sort()
#Adding Kmer Kernels
for motif in motifs:
all_examples = pmotifs[motif] + nmotifs[motif]
motif_features = wds_svm.createFeatures(all_examples)
wds_kernel = WeightedDegreePositionStringKernel(motif_features, motif_features, \
wds_kparams['degree'])
wds_kernel.set_shifts(wds_kparams['shift'] *
ones(wds_kparams['seqlength'], dtype=int32))
features.append_feature_obj(motif_features)
kernel_array.append(wds_kernel)
kernel.append_kernel(wds_kernel)
rbf_svm = EasySVM.EasySVM(kirmes_ini.RBF_KERNEL_PARAMETERS)
positions = array(ppositions + npositions, dtype=float64).T
position_features = rbf_svm.createFeatures(positions)
features.append_feature_obj(position_features)
motif_labels = append(ones(num_positives), -ones(num_negatives))
complete_labels = Labels(motif_labels)
rbf_kernel = GaussianKernel(position_features, position_features, \
kirmes_ini.RBF_KERNEL_PARAMETERS['width'])
kernel_array.append(rbf_kernel)
kernel.append_kernel(rbf_kernel)
#Kernel init
kernel.init(features, features)
kernel.set_cache_size(kirmes_ini.K_CACHE_SIZE)
svm = LibSVM(kirmes_ini.K_COMBINED_C, kernel, complete_labels)
svm.parallel.set_num_threads(kirmes_ini.K_NUM_THREADS)
#Training
svm.train()
if not os.path.exists(options.output_path):
os.mkdir(options.output_path)
html = {}
if options.contrib:
html["contrib"] = contrib(svm, kernel, motif_labels, kernel_array,
motifs)
if options.logos:
html["poims"] = poims(svm, kernel, kernel_array, motifs,
options.output_path)
if options.query:
html["query"] = evaluate(options, svm, kernel, features, motifs)
htmlize(html, options.output_html)
