def main():
description = 'Build ML models to predict by-cellline drug response.'
parser = get_parser(description)
args = parser.parse_args()
print('Args:', args, end='\n\n')
print('Use percent growth for dose levels in log concentration range: [{}, {}]'.format(args.min_logconc, args.max_logconc))
print()
cells = NCI60.all_cells() if 'all' in args.cells else args.cells
for cell in cells:
print('-' * 10, 'Cell line:', cell, '-' * 10)
df = NCI60.load_by_cell_data(cell, drug_features=args.drug_features, scaling=args.scaling,
min_logconc=args.min_logconc, max_logconc=args.max_logconc,
subsample=args.subsample, feature_subsample=args.feature_subsample)
if not df.shape[0]:
print('No response data found\n')
continue
if args.classify:
good_bins = summarize(df, args.cutoffs, min_count=args.cv)
if good_bins < 2:
print('Not enough classes\n')
continue
else:
summarize(df)
out = os.path.join(args.out_dir, cell)
for model in args.models:
if args.classify:
classify(model, df, cv=args.cv, cutoffs=args.cutoffs, threads=args.threads, prefix=out)
else:
regress(model, df, cv=args.cv, cutoffs=args.cutoffs, threads=args.threads, prefix=out)
def main():
parser = get_parser()
args = parser.parse_args()
set_seed(args.seed)
prefix = args.prefix or os.path.basename(args.data)
prefix = os.path.join(args.out_dir, prefix)
df = pd.read_table(args.data, engine='c', sep=',' if args.csv else '\t')
x, y, splits, features = split_data(df, ycol=args.ycol, classify=args.classify, cv=args.cv,
bins=args.bins, cutoffs=args.cutoffs, groupcols=args.groupcols,
ignore_categoricals=args.ignore_categoricals, verbose=True)
if args.classify and len(np.unique(y)) < 2:
print('Not enough classes\n')
return
best_score, best_model = -np.Inf, None
for model in args.models:
if args.classify:
class_weight = 'balanced' if args.balanced else None
score = classify(model, x, y, splits, features, threads=args.threads, prefix=prefix, seed=args.seed, class_weight=class_weight)
else:
score = regress(model, x, y, splits, features, threads=args.threads, prefix=prefix, seed=args.seed)
if score >= best_score:
best_score = score
best_model = model
print('Training the best model ({}={:.3g}) on the entire dataset...'.format(best_model, best_score))
name = 'best.classifier' if args.classify else 'best.regressor'
fname = train(best_model, x, y, features, classify=args.classify,
threads=args.threads, prefix=prefix, name=name, save=True)
print('Model saved in {}\n'.format(fname))
def main():
description = 'Build ML models to predict by-drug tumor response.'
parser = get_parser(description)
args = parser.parse_args()
print('Args:', args, end='\n\n')
if args.use_gi50:
print('Use NCI GI50 value instead of percent growth')
else:
print('Use percent growth at log concentration: {}'.format(args.logconc))
drugs = args.drugs
if 'all' in drugs:
drugs = NCI60.all_drugs()
elif len(drugs) == 1 and re.match("^[ABC]$", drugs[0].upper()):
drugs = NCI60.drugs_in_set('Jason:' + drugs[0].upper())
print("Drugs in set '{}': {}".format(args.drugs[0], len(drugs)))
print()
for drug in drugs:
print('-' * 10, 'Drug NSC:', drug, '-' * 10)
df = NCI60.load_by_drug_data(drug, cell_features=args.cell_features, scaling=args.scaling,
use_gi50=args.use_gi50, logconc=args.logconc,
subsample=args.subsample, feature_subsample=args.feature_subsample)
if not df.shape[0]:
print('No response data found\n')
continue
if args.classify:
cutoffs = None if args.autobins > 1 else args.cutoffs
good_bins = summarize(df, cutoffs, autobins=args.autobins, min_count=args.cv)
if good_bins < 2:
print('Not enough classes\n')
continue
else:
summarize(df)
out = os.path.join(args.out_dir, 'NSC_' + drug)
for model in args.models:
if args.classify:
classify(model, df, cv=args.cv, cutoffs=args.cutoffs, autobins=args.autobins, threads=args.threads, prefix=out)
else:
regress(model, df, cv=args.cv, cutoffs=args.cutoffs, threads=args.threads, prefix=out)
def test1():
df = NCI60.load_by_cell_data()
regress('XGBoost', df)
def test2():
from sklearn.ensemble import RandomForestRegressor
model = RandomForestRegressor(n_estimators=20)
df = NCI60.load_by_cell_data()
regress(model, df, cv=2)