def calc_mdsres_2d(request):
if request.method == 'POST':
# Calculate The Similarity Matrix
#Calculate Finger Prints
simmatrix_method = str(request.POST["simmatrix_method"])
cg = CompoundCollection.objects().with_id(str(request.POST['collection_id']))
if simmatrix_method == "FP" :
print "\n Calculating Simmatrix (FingerPrints) ... \n "
sm = SimilarityMatrix(compound_group = cg , method=simmatrix_method)
sm.distance_matrix(0.0)
elif simmatrix_method == "eden" :
print "\n Calculating Simmatrix (EDeN) ...\n "
sm = SimilarityMatrix(compound_group = cg,method=simmatrix_method)
sm.distance_matrix_eden()
# Calculate MDS
print "\n Calculating MDS ... \n "
res = MDSRes(title = str(request.POST['mds_title']),simmatrix = sm,max_iter =300,eps = 1e-6) ;
data = numpy.fromstring(sm.data.read())
d = math.sqrt(len(data))
datamd = numpy.reshape(data, (d,d))
res.data.new_file()
res.data.write(res.runMDS(simmatrix = datamd,n_comp=2).tostring())
res.data.close()
res.save()
response_data = {}
response_data['result'] = 'Success'
response_data['message'] = 'Calculate Mds Results'
return HttpResponseRedirect('/space_explorer/')
def calc_pca_consistent(request) :
if request.is_ajax() :
# pdb.set_trace()
response_data = {}
pca_res = []
comps = []
# for cluster_id in [request.GET["cluster_ids"]] :
cg = CompoundCollection.objects().with_id(str(request.POST['collection_id']))
centriods = Cluster.get_clusters_centriod(compound_group=cg)
clusters = Cluster.objects(id__in = [request.GET["cluster_ids"]])
comps.extend(centriods)
comps.extend([c.nodes for c in clusters])
pca = PCARes(collection=comps , title="PCA_on_clusters")
response_data['clusters'] = [{"nodes" : [node.name for node in cluster.nodes] ,"id":str(cluster.id) ,"centriod" : cluster.centriod.name ,"density" :len(cluster.nodes)} for cluster in Clusters]
response_data['pca_res'] = pca.PerformPCA().tolist()
response_data['nodes'] = [{"name" : comp.name} for c in clusters for comp in c.nodes ]
pca.save()
#returen PCA Results
response_data['result'] = 'Success'
response_data['message'] = 'PCA Results'
return HttpResponse(json.dumps(response_data), mimetype="application/json")
def get_collection_mdsres(request):
if request.is_ajax():
collection = CompoundCollection.objects().with_id(request.GET["collection_id"])
response_data = {}
response_data['result'] = 'Success'
response_data['message'] = 'Collection Mds Results'
#response_data['field_names'] = []
#for f in field_names :
# response_data['field_names'].append(f)
sim_matrix = SimilarityMatrix.objects(compound_group = collection)
mds_res_list = []
response_data['mdsresults'] = []
response_data['pcaresults'] = []
for sm in sim_matrix :
mds_res = MDSRes.objects(simmatrix = sm)
for res in mds_res :
mds_res_list.append({"title" : res.title , "id" : str(res.id)})
# add PCA Pos Res :
pca_res_list =[]
for pca_res in PCARes.objects(compound_group = collection) :
pca_res_list.append({"title":pca_res.title, "id" : str(pca_res.id)})
response_data['mdsresults'] = mds_res_list
response_data['pcaresults'] = pca_res_list
return HttpResponse(json.dumps(response_data), mimetype="application/json")
def calculate_clusters_eden(collection):
compounds = Compound.objects(compound_group=collection)
# call EdenUtil Cluster
clusters_file = EdenUtil.cluster(
EdenUtil.sdf_to_gspan(
CompoundCollection.generateTmpSDF(compounds,
'tmpcollection').name))
clusters = []
# create a cluster for each line
for eden_cluster in clusters_file:
eden_nodes = eden_cluster.split(" ")
eden_nodes = [x for x in eden_nodes if (x != '' and x != '\n')]
cluster = Cluster(
title="Cluster_" + str(eden_nodes[0]),
collection=collection,
nodes=[compounds[int(node)] for node in eden_nodes],
centriod=compounds[int(eden_nodes[0])],
density=0.0,
Color="#EF0000")
clusters.append(cluster)
cluster.save()
clusters_file.close()
def calc_clusters(request):
if request.method == 'POST':
form = CalcClusterForm(request.POST)
if form.is_valid():
compound_group = CompoundCollection.objects().with_id(
str(request.POST["collection_id"]))
compounds = Compound.objects(
compound_group=str(request.POST["collection_id"]))
#input_text = "<("
#for compound in compounds :
# input_text += compound.mol + "\n"
#input_text += ")"
input_text = "/home/mjs/Test/approved.gspan.gz"
Cluster.calcualte_clusters(compound_group, input_text, "EDEN")
# handle_uploaded_file(request.FILES['file'])
return HttpResponseRedirect('/cluster/')
else:
form = CalcClusterForm()
return render_to_response(
'calc_clusters.html', {
"view_titel": "Calculate Clusters",
"form": form
},
context_instance=RequestContext(request)) # Create your views here.
def calc_new_mol(request) :
if request.is_ajax():
selected_compounds = request.GET["selected_compounds"]
compounds = Compound.objects({"name__in":selected_compounds})
new_comp = EdenUtil.molcule_design(EdenUtil.sdf_to_gspan(CompoundCollection.generateTmpSDF(compounds,"tmpsdf").name))
response_data = {}
response_data["new_comp" ] = new_comp
response_data['result'] = 'Success'
response_data['message'] = 'New Molcule Designed'
return HttpResponse(json.dumps(response_data), mimetype="application/json")
def get_coordinate(request):
if request.is_ajax():
# pdb.set_trace()
mdsres = MDSRes.objects().with_id(request.session.get("mds_id"))
Clusters = []
compound_group = CompoundCollection.objects().with_id(request.session.get("collection_id"))
if(mdsres is not None) :
data = numpy.fromstring(mdsres.data.read())
d = len(data)
datamd = numpy.reshape(data, (d/3,3))
compounds = Compound.objects(compound_group = request.session.get("collection_id"))
if mdsres.simmatrix.method == "FP" :
arena = chemfp.load_fingerprints(mdsres.simmatrix.compound_group.fp_file)
compounds = arena.ids
elif mdsres.simmatrix.method == "eden" :
compounds = [compound.name for compound in compounds]
elif mdsres.simmatrix.method == "pre_cluster_eden" or mdsres.simmatrix.method == "pre_cluster_eden_pca" :
Clusters = Cluster.objects(collection = request.session.get("collection_id"))
Clusters = [{"nodes" : [node.name for node in cluster.nodes] ,"id":str(cluster.id) ,"centriod" : cluster.centriod.name ,"density" :len(cluster.nodes)} for cluster in Clusters]
compounds = Cluster.get_clusters_centriod(compound_group)
compounds = [compound.name for compound in compounds]
elif(mdsres is None) :
pcares = PCARes.objects().with_id(request.session.get("mds_id"))
data = numpy.fromstring(pcares.data.read())
d = len(data)
datamd = numpy.reshape(data, (d/3,3))
Clusters = Cluster.objects(collection = request.session.get("collection_id"))
Clusters = [{"nodes" : [node.name for node in cluster.nodes] ,"id":str(cluster.id) ,"centriod" : cluster.centriod.name ,"density" :len(cluster.nodes)} for cluster in Clusters]
compounds = Cluster.get_clusters_centriod(compound_group)
compounds = [compound.name for compound in compounds]
# the order of the compounds is not correct !!! make sure to fix (arena.ids[idx] from the fingerprint file)
response_data = {}
response_data['result'] = 'Success'
response_data['message'] = 'Compounds Coordinate'
response_data['coord'] = datamd.tolist()
response_data["clusters"] = Clusters
response_data['comps'] = []
for compound in compounds :
compitem = {
"name" :compound
}
response_data['comps'].append(compitem)
return HttpResponse(json.dumps(response_data), mimetype="application/json")
return HttpResponse({}, mimetype="application/json")
def distance_matrix_cluster_centriods(self) :
#1- generat an sdf file of the clusters centriod
tmpsdffile = CompoundCollection.generateTmpSDF(Cluster.get_clusters_centriod(self.compound_group),'centriods')
pdb.set_trace()
#2- calcualte distance matrix for the centriods
sm_output = EdenUtil.similarty_matrix(EdenUtil.sdf_to_gspan(tmpsdffile.name))
distances = 1 - sm_output
#######################################
self.data.new_file()
self.data.write(distances.tostring())
self.data.close()
self.save(validate=False,cascade=False)
self.calc_knn_eden()
def add_meta(request):
if request.method == 'POST':
comp_collec = CompoundCollection.objects().with_id(request.session["collection_id"])
comp_collec.add_meta_info(request.FILES["metainfo_file"],int(request.POST["key_col"]))
response_data = {}
response_data['result'] = 'Success'
response_data['message'] = 'Compounds Fields'
return redirect('/space_explorer/')
return HttpResponse(json.dumps(""), mimetype="application/json")
def view_space(request):
if request.method == 'POST':
return HttpResponseRedirect('/space_explorer/')
cc = CompoundCollection.objects()
cc_list = [ {"name":collection.title,"id":collection.id} for collection in cc ]
c = {
"view_titel":"Space Explorer" ,
"collections":cc_list ,
"current_collction" :request.session.get("collection_id") ,
"current_mds" :request.session.get("mds_id")
}
c.update(csrf(request))
return render_to_response('explorer.html',c,context_instance=RequestContext(request))
def calc_pca(request) :
if request.is_ajax() :
if(str(request.GET["consistent"]) == 'true'):
# pdb.set_trace()
response_data = {}
pca_res = []
comps = []
clusters_nodes = []
# for cluster_id in [request.GET["cluster_ids"]] :
cg = CompoundCollection.objects().with_id(str(request.session['collection_id']))
centriods = Cluster.get_clusters_centriod(compound_group=cg)
clusters = Cluster.objects(id__in = request.GET.getlist('embededClusters[]'))
clusters_nodes = [comp for c in clusters for comp in c.nodes ]
comps.extend(centriods)
comps.extend(node for node in clusters_nodes if node not in centriods)
pca = PCARes(cluster=clusters , title="PCA_on_clusters")
response_data['pca_res'] = pca.PerformPCA(collection=comps).tolist()
response_data['nodes'] = [{"name" : c.name} for c in comps]
# response_data['nodes'] = [{"name" : comp.name} for c in clusters for comp in c.nodes ]
pca.save()
#returen PCA Results
response_data['result'] = 'Success'
response_data['message'] = 'PCA Results'
else :
response_data = {}
pca_res = []
# for cluster_id in [request.GET["cluster_ids"]] :
cluster = Cluster.objects(id__in = [request.GET["cluster_ids"]])
pca = PCARes(cluster =cluster, title="PCA_on_clusters")
response_data['pca_res'] = pca.PerformPCA().tolist()
pca.save()
response_data['nodes'] = [{"name" : comp.name} for c in cluster for comp in c.nodes ]
#returen PCA Results
response_data['result'] = 'Success'
response_data['message'] = 'PCA Results'
return HttpResponse(json.dumps(response_data), mimetype="application/json")
def distance_matrix_cluster_centriods(self):
#1- generat an sdf file of the clusters centriod
tmpsdffile = CompoundCollection.generateTmpSDF(
Cluster.get_clusters_centriod(self.compound_group), 'centriods')
pdb.set_trace()
#2- calcualte distance matrix for the centriods
sm_output = EdenUtil.similarty_matrix(
EdenUtil.sdf_to_gspan(tmpsdffile.name))
distances = 1 - sm_output
#######################################
self.data.new_file()
self.data.write(distances.tostring())
self.data.close()
self.save(validate=False, cascade=False)
self.calc_knn_eden()
def PerformPCA(self, collection=None):
# pdb.set_trace()
use_sparse = True
feature_vectors = []
feature_dim = 15
if collection is None:
collection = [node for c in self.cluster for node in c.nodes]
#Genrate gspan for Cluster nodes
tmpsdffile = CompoundCollection.generateTmpSDF(collection, 'cluster')
#Calculate Feature for cluster nodes
feature_file = EdenUtil.feature(EdenUtil.sdf_to_gspan(tmpsdffile.name),
feature_dim)
i = 0
if use_sparse:
sparse_mtx = lil_matrix((len(collection), 2**feature_dim))
row_indx = 0
for row in feature_file:
for fet in row.split(" ")[1:]:
sparse_mtx[row_indx, int(fet.split(":")[0])] = float(
fet.split(":")[1])
#compound_feature = Feature(compound=collection[i] , features = sparse_mtx.rows[row_indx])
#compound_feature.save()
row_indx += 1
pca = sklearn.decomposition.RandomizedPCA(n_components=3)
pca_res = pca.fit_transform(sparse_mtx)
else:
for row in feature_file:
feat_vect = [0] * (2**feature_dim)
for fet in row.split(" ")[1:]:
feat_vect[int(fet.split(":")[0])] = float(
fet.split(":")[1])
compound_feature = Feature(compound=collection[i],
features=feat_vect)
compound_feature.save()
i += 1
feature_vectors.append(feat_vect)
#Perform PCA on Feature Vectors
pca = sklearn.decomposition.PCA(n_components=3)
pca_res = pca.fit_transform(feature_vectors)
#store PCA Cluster Result
#
return pca_res
def calc_knn_eden(self):
# Calculate and Store KNN
print "\n Calculating KNN ... \n"
compounds = Compound.objects(compound_group=self.compound_group)
tmpsdffile = CompoundCollection.generateTmpSDF(compounds, "comps_eden")
knn = EdenUtil.nearest_neighbor(EdenUtil.sdf_to_gspan(tmpsdffile.name))
for knn_entry in knn:
knn_item = KnnItem(
simmatrix=self,
mol_id=str(compounds[int(knn_entry['indxs'].pop(0))].name),
neighbors=[{
"mol_id":
str(compounds[int(x)].name),
"val":
float(knn_entry['knn_vals'][knn_entry['indxs'].index(x)])
} for x in knn_entry['indxs']])
knn_item.save()
def calc_similarity(request):
if request.method == 'POST':
form = CalcSimForm(request.POST, request.FILES)
if form.is_valid():
f = request.FILES['fingerprint_file']
cg = CompoundCollection.objects().with_id(str(request.POST['compound_group']))
sm = SimilarityMatrix(compound_group = cg ,fp = f)
arrstr = sm.distance_matrix(f,0.0).tostring()
sm.data.new_file()
sm.data.write(arrstr)
sm.data.close()
sm.save(validate=False,cascade=False)
return HttpResponseRedirect('/similarity/')
else:
form = CalcSimForm()
return render_to_response('calc_similarity.html',{"view_titel":"Calculate SimilartyMatrix","form":form},context_instance=RequestContext(request))
def calc_knn_eden(self) :
# Calculate and Store KNN
print "\n Calculating KNN ... \n"
compounds = Compound.objects(compound_group=self.compound_group)
tmpsdffile = CompoundCollection.generateTmpSDF(compounds,"comps_eden")
knn = EdenUtil.nearest_neighbor(EdenUtil.sdf_to_gspan(tmpsdffile.name))
for knn_entry in knn :
knn_item = KnnItem(
simmatrix = self
,mol_id = str(compounds[int(knn_entry['indxs'].pop(0))].name)
,neighbors = [
{
"mol_id":str(compounds[int(x)].name)
,"val":float(knn_entry['knn_vals'][knn_entry['indxs'].index(x)])
} for x in knn_entry['indxs']
]
)
knn_item.save()
def distance_matrix_eden(self) :
comps = Compound.objects(compound_group=self.compound_group)
n = comps.count()
distances = numpy.ones((n, n), numpy.float64)
# mmfile = self.compound_group.mol_file.read()
# tmpsdffile = open('/tmp/'+self.compound_group.title+'.sdf', 'wb+')
# tmpsdffile.write(mmfile)
# tmpsdffile.close()
tmpsdffile = CompoundCollection.generateTmpSDF(comps,"comps_eden")
# Calcuate Distances using EDeN
sm_output = EdenUtil.similarty_matrix(EdenUtil.sdf_to_gspan(tmpsdffile.name))
distances = 1 - sm_output
#######################################
self.data.new_file()
self.data.write(distances.tostring())
self.data.close()
self.save(validate=False,cascade=False)
self.calc_knn_eden()
def calc_clusters(request):
if request.method == 'POST':
form = CalcClusterForm(request.POST)
if form.is_valid():
compound_group = CompoundCollection.objects().with_id(str(request.POST["collection_id"]))
compounds = Compound.objects(compound_group = str(request.POST["collection_id"]))
#input_text = "<("
#for compound in compounds :
# input_text += compound.mol + "\n"
#input_text += ")"
input_text = "/home/mjs/Test/approved.gspan.gz"
Cluster.calcualte_clusters(compound_group,input_text,"EDEN")
# handle_uploaded_file(request.FILES['file'])
return HttpResponseRedirect('/cluster/')
else:
form = CalcClusterForm()
return render_to_response('calc_clusters.html',{"view_titel":"Calculate Clusters","form":form},context_instance=RequestContext(request)) # Create your views here.
def distance_matrix_eden(self):
comps = Compound.objects(compound_group=self.compound_group)
n = comps.count()
distances = numpy.ones((n, n), numpy.float64)
# mmfile = self.compound_group.mol_file.read()
# tmpsdffile = open('/tmp/'+self.compound_group.title+'.sdf', 'wb+')
# tmpsdffile.write(mmfile)
# tmpsdffile.close()
tmpsdffile = CompoundCollection.generateTmpSDF(comps, "comps_eden")
# Calcuate Distances using EDeN
sm_output = EdenUtil.similarty_matrix(
EdenUtil.sdf_to_gspan(tmpsdffile.name))
distances = 1 - sm_output
#######################################
self.data.new_file()
self.data.write(distances.tostring())
self.data.close()
self.save(validate=False, cascade=False)
self.calc_knn_eden()
def calculate_clusters_eden(collection) :
compounds = Compound.objects(compound_group = collection)
# call EdenUtil Cluster
clusters_file = EdenUtil.cluster(EdenUtil.sdf_to_gspan(CompoundCollection.generateTmpSDF(compounds,'tmpcollection').name))
clusters = []
# create a cluster for each line
for eden_cluster in clusters_file :
eden_nodes = eden_cluster.split(" ")
eden_nodes = [x for x in eden_nodes if (x != '' and x != '\n')]
cluster = Cluster(
title = "Cluster_" + str(eden_nodes[0])
,collection = collection
,nodes = [compounds[int(node)] for node in eden_nodes]
,centriod = compounds[int(eden_nodes[0])]
,density = 0.0
,Color = "#EF0000"
)
clusters.append(cluster)
cluster.save()
clusters_file.close()
def calc_similarity(request):
if request.method == 'POST':
form = CalcSimForm(request.POST, request.FILES)
if form.is_valid():
f = request.FILES['fingerprint_file']
cg = CompoundCollection.objects().with_id(
str(request.POST['compound_group']))
sm = SimilarityMatrix(compound_group=cg, fp=f)
arrstr = sm.distance_matrix(f, 0.0).tostring()
sm.data.new_file()
sm.data.write(arrstr)
sm.data.close()
sm.save(validate=False, cascade=False)
return HttpResponseRedirect('/similarity/')
else:
form = CalcSimForm()
return render_to_response('calc_similarity.html', {
"view_titel": "Calculate SimilartyMatrix",
"form": form
},
context_instance=RequestContext(request))
def calc_pos(request):
if request.method == 'POST':
# Calculate The Similarity Matrix
#Calculate Finger Prints
calc_method = str(request.POST["method"])
cg = CompoundCollection.objects().with_id(str(request.POST['collection_id']))
if calc_method == "FP" :
print "\n Calculating Simmatrix (FingerPrints) ... \n "
sm = SimilarityMatrix(compound_group = cg , method=calc_method)
sm.distance_matrix(0.0)
elif calc_method == "eden" :
print "\n Calculating Simmatrix (EDeN) ...\n "
sm = SimilarityMatrix(compound_group = cg,method=calc_method)
sm.distance_matrix_eden()
elif calc_method == "pre_cluster_eden" :
Cluster.calculate_clusters_eden(cg)
sm = SimilarityMatrix(compound_group = cg,method=calc_method)
sm.distance_matrix_cluster_centriods()
if calc_method == "pre_cluster_eden_pca" :
# Calculate PCA
if(len(Cluster.objects(collection = cg))<1):
print "\n Calculating Clusters ... \n "
Cluster.calculate_clusters_eden(cg)
# Calculate and Store KNN
compounds = Compound.objects(compound_group=cg)
tmpsdffile = CompoundCollection.generateTmpSDF(compounds,"comps_eden")
print "\n Calculating KNN ... \n"
knn = EdenUtil.nearest_neighbor(EdenUtil.sdf_to_gspan(tmpsdffile.name))
for knn_entry in knn :
knn_item = KnnItem(
compound_group = cg
,mol_id = str(compounds[int(knn_entry['indxs'].pop(0))].name)
,neighbors = [
{
"mol_id":str(compounds[int(x)].name)
,"val":float(knn_entry['knn_vals'][knn_entry['indxs'].index(x)])
} for x in knn_entry['indxs']
]
)
knn_item.save()
print "\n Calculating PCA ... \n "
pca = PCARes(compound_group=cg, title=str(request.POST['pos_title']))
res = pca.PerformPCA(collection=Cluster.get_clusters_centriod(compound_group=cg)).tostring()
pca.data.new_file()
pca.data.write(res)
pca.data.close()
pca.save()
else :
# Calculate MDS
print "\n Calculating MDS ... \n "
res = MDSRes(title = str(request.POST['pos_title']),simmatrix = sm,max_iter =300,eps = 1e-6) ;
data = numpy.fromstring(sm.data.read())
d = math.sqrt(len(data))
datamd = numpy.reshape(data, (d,d))
res.data.new_file()
res.data.write(res.runMDS(simmatrix = datamd).tostring())
res.data.close()
res.save()
response_data = {}
response_data['result'] = 'Success'
response_data['message'] = 'Calculate Position Results'
return HttpResponseRedirect('/space_explorer/')
def test_add_meta(request):
CC = CompoundCollection.objects().with_id(request.session["collection_id"])
CC.add_meta_info()
compounds = Compound.objects()
return render_to_response('view_file.html',{"view_titel":"Home",'compounds':compounds},context_instance=RequestContext(request))