for i,m in enumerate(actives[k]):
fp_dict = scor.getFP(fp_build, m[1])
actives[k][i] = [str(target)+'_'+str(k)+'_A_'+str(i+1), fp_dict]
# read in test actives and calculate fps
div_actives = []
for line in gzip.open(inpath_cmp+'ChEMBL/cmp_list_ChEMBL_'+str(target)+'_actives.dat.gz', 'r'):
if line[0] != '#':
# structure of line: [external ID, internal ID, SMILES]]
line = line.rstrip().split()
fp_dict = scor.getFP(fp_build, line[2])
# store: [internal ID, dict with fps]
div_actives.append([line[1], fp_dict])
num_test_actives = conf.num_div_act - 1
# convert fps to numpy arrays
np_fps_div_act = ml_func.getNumpy(div_actives)
# read in decoys and calculate fps
if firstchembl:
decoys = []
for line in gzip.open(inpath_cmp+'ChEMBL/cmp_list_ChEMBL_zinc_decoys.dat.gz', 'r'):
if line[0] != '#':
# structure of line: [external ID, internal ID, SMILES]]
line = line.rstrip().split()
fp_dict = scor.getFP(fp_build, line[2])
# store: [internal ID, dict with fps]
decoys.append([line[1], fp_dict])
# convert fps to numpy arrays
np_fps_dcy = ml_func.getNumpy(decoys)
firstchembl = False
num_decoys = len(decoys)
# read in actives and calculate fps
actives = []
for line in gzip.open(
inpath_cmp + dataset + '/cmp_list_' + dataset + '_' +
str(target) + '_actives.dat.gz', 'r'):
if line[0] != '#':
# structure of line: [external ID, internal ID, SMILES]]
line = line.rstrip().split()
fp_dict = scor.getFP(fp_build, line[2])
# store: [internal ID, dict with fps]
actives.append([line[1], fp_dict])
num_actives = len(actives)
num_test_actives = num_actives - num_query_mols
# convert fps to numpy arrays
np_fps_act = ml_func.getNumpy(actives)
# read in decoys and calculate fps
if dataset == 'ChEMBL':
if firstchembl:
decoys = []
for line in gzip.open(
inpath_cmp + dataset + '/cmp_list_' + dataset +
'_zinc_decoys.dat.gz', 'r'):
if line[0] != '#':
# structure of line: [external ID, internal ID, SMILES]]
line = line.rstrip().split()
fp_dict = scor.getFP(fp_build, line[2])
# store: [internal ID, dict with fps]
decoys.append([line[1], fp_dict])
# convert fps to numpy arrays