# Load the perceptual descriptors data.
perceptual_headers, perceptual_obs_data = loading.load_perceptual_data('training')
loading.format_leaderboard_perceptual_data()
# Show the perceptual metadata types and perceptual descriptor names.
print(perceptual_headers)
# Show the metadata and perceptual descriptor values for the first compound.
print(perceptual_obs_data[1])
num_descriptors = len(perceptual_headers[6:])
assert num_descriptors == dream.NUM_DESCRIPTORS
num_subjects = dream.NUM_SUBJECTS
print('There are %d different perceptual descriptors and %d different subjects' % (num_descriptors,num_subjects))
# Load the molecular descriptors data.
molecular_headers, molecular_data = loading.load_molecular_data()
print("First ten molecular descriptor types are %s" % molecular_headers[:10])
print("First ten descriptor values for the first compound are %s" % molecular_data[0][:10])
total_size = len(set([int(row[0]) for row in molecular_data]))
print("We have molecular descriptors for %d unique molecules" % total_size)
# Load the molecular descriptors data.
molecular_headers, molecular_data = loading.load_molecular_data()
print("First ten molecular descriptor types are %s" % molecular_headers[:10])
print("First ten descriptor values for the first compound are %s" % molecular_data[0][:10])
total_size = len(set([int(row[0]) for row in molecular_data]))
print("We have molecular descriptors for %d unique molecules" % total_size)
training_size = len(set([int(row[0]) for row in perceptual_obs_data]))
print("We have perceptual data for %d unique molecules" % training_size)
remaining_size = total_size - training_size
loading.format_leaderboard_perceptual_data()
# Show the perceptual metadata types and perceptual descriptor names.
print(perceptual_headers)
# Show the metadata and perceptual descriptor values for the first compound.
print(perceptual_obs_data[1])
num_descriptors = len(perceptual_headers[6:])
assert num_descriptors == dream.NUM_DESCRIPTORS
num_subjects = dream.NUM_SUBJECTS
print(
'There are %d different perceptual descriptors and %d different subjects' %
(num_descriptors, num_subjects))
# Load the molecular descriptors data.
molecular_headers, molecular_data = loading.load_molecular_data()
print("First ten molecular descriptor types are %s" % molecular_headers[:10])
print("First ten descriptor values for the first compound are %s" %
molecular_data[0][:10])
total_size = len(set([int(row[0]) for row in molecular_data]))
print("We have molecular descriptors for %d unique molecules" % total_size)
# Load the molecular descriptors data.
molecular_headers, molecular_data = loading.load_molecular_data()
print("First ten molecular descriptor types are %s" % molecular_headers[:10])
print("First ten descriptor values for the first compound are %s" %
molecular_data[0][:10])
total_size = len(set([int(row[0]) for row in molecular_data]))
print("We have molecular descriptors for %d unique molecules" % total_size)
training_size = len(set([int(row[0]) for row in perceptual_obs_data]))
def get_molecular_data(sources,CIDs):
import pandas
DATA = '../../data/'
if 1 or ('dragon' in sources):
molecular_headers, molecular_data = loading.load_molecular_data()
if 'episuite' in sources:
episuite = pandas.read_table('%s/DREAM_episuite_descriptors.txt' % DATA)
episuite.iloc[:,49] = 1*(episuite.iloc[:,49]=='YES ')
episuite = episuite.iloc[:,2:].as_matrix()
print("Episuite has %d features for %d molecules." % (episuite.shape[1],episuite.shape[0]))
'''
if 'verbal' in sources:
verbal = pandas.read_table('%s/name_features.txt' % DATA, sep='\t', header=None)
verbal = verbal.as_matrix()[:,1:]
print("Verbal has %d features for %d molecules." % (verbal.shape[1],verbal.shape[0]))
'''
if 'morgan' in sources:
morgan = pandas.read_csv('%s/morgan_sim.csv' % DATA)
morgan = morgan.as_matrix()[:,1:]
print("Morgan has %d features for %d molecules." % (morgan.shape[1],morgan.shape[0]))
if 'nspdk' in sources:
# Start to load the NSPDK features.
with open('%s/derived/nspdk_r3_d4_unaug.svm' % DATA) as f:
nspdk_dict = {}
i = 0
while True:
x = f.readline()
if(len(x)):
key_vals = x.split(' ')[1:]
for key_val in key_vals:
key,val = key_val.split(':')
if key in nspdk_dict:
nspdk_dict[key][CIDs[i]] = val
else:
nspdk_dict[key] = {CIDs[i]:val}
i+=1
if i == len(CIDs):
break
else:
break
nspdk_dict = {key:value for key,value in nspdk_dict.items() if len(value)>1}
# Get the NSPDK features into the right format.
nspdk = np.zeros((len(CIDs),len(nspdk_dict)))
for j,(feature,facts) in enumerate(nspdk_dict.items()):
for CID,value in facts.items():
i = CIDs.index(CID)
nspdk[i,j] = value
print("NSPDK has %d features for %d molecules." % (nspdk.shape[1],nspdk.shape[0]))
if 'gramian' in sources:
# These require a large file that is not on GitHub, but can be obtained separately.
nspdk_gramian = pandas.read_table('%s/derived/nspdk_r3_d4_unaug_gramian.mtx' % DATA, delimiter=' ', header=None)
nspdk_gramian = nspdk_gramian.as_matrix()[:len(CIDs),:]
print("NSPDK Gramian has %d features for %d molecules." % \
(nspdk_gramian.shape[1],nspdk_gramian.shape[0]))
# Add all these new features to the molecular data dict.
mdx = []
for i,line in enumerate(molecular_data):
CID = int(line[0])
if CID in CIDs:
index = CIDs.index(CID)
if 'episuite' in sources:
line += list(episuite[index])
if 'morgan' in sources:
line += list(morgan[index])
if 'nspdk' in sources:
line += list(nspdk[index])
if 'gramian' in sources:
line += list(nspdk_gramian[index])
mdx.append(line)
print("There are now %d total features." % len(mdx[0]))
return molecular_data
