simil_metric = 'Dice'
if options.simil: simil_metric = options.simil
outpath = path
outpath_set = False
if options.outpath:
outpath_set = True
outpath = path+options.outpath
# check for sensible input
if outpath_set: scor.checkPath(outpath, 'output')
scor.checkSimil(simil_metric)
# default machine-learning method variables
ml_dict = dict(alpha=1.0, binarize=None, fit_prior=True)
if options.ml:
ml_dict = ml_func.readMLFile(ml_dict, read_dict, path+options.ml)
# initialize machine-learning method
ml = BernoulliNB(alpha=ml_dict['alpha'], binarize=ml_dict['binarize'], fit_prior=ml_dict['fit_prior'])
# loop over targets
for target in conf.set_data:
print target
# read in training actives and calculate fps
actives = cPickle.load(open(inpath_cmp+'ChEMBL_II/Target_no_'+str(target)+'.pkl', 'r'))
for k in actives.keys():
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]
# check for sensible input
if outpath_set: scor.checkPath(outpath, 'output')
scor.checkSimil(simil_metric)
scor.checkQueryMols(num_query_mols, conf.list_num_query_mols)
# default machine-learning method variables
ml_dict = dict(criterion='gini',
max_features='auto',
n_jobs=1,
max_depth=10,
min_samples_split=2,
min_samples_leaf=1,
num_estimators=100)
if options.ml:
ml_dict = ml_func.readMLFile(ml_dict, read_dict, path + options.ml)
# initialize machine-learning method
ml = RandomForestClassifier(criterion=ml_dict['criterion'],
max_features=ml_dict['max_features'],
min_samples_split=ml_dict['min_samples_split'],
max_depth=ml_dict['max_depth'],
min_samples_leaf=ml_dict['min_samples_leaf'],
n_estimators=ml_dict['num_estimators'],
n_jobs=ml_dict['n_jobs'])
# loop over data-set sources
for dataset in conf.set_data.keys():
print dataset
# loop over targets
for target in conf.set_data[dataset]['ids']: