A decision-theoretic approach to the evaluation of machine learning algorithms in computational drug discovery.

ABSTRACT:

Motivation

Artificial intelligence, trained via machine learning (e.g. neural nets, random forests) or computational statistical algorithms (e.g. support vector machines, ridge regression), holds much promise for the improvement of small-molecule drug discovery. However, small-molecule structure-activity data are high dimensional with low signal-to-noise ratios and proper validation of predictive methods is difficult. It is poorly understood which, if any, of the currently available machine learning algorithms will best predict new candidate drugs.

Results

The quantile-activity bootstrap is proposed as a new model validation framework using quantile splits on the activity distribution function to construct training and testing sets. In addition, we propose two novel rank-bas

SUBMITTER: Watson OP 

PROVIDER: S-EPMC6853675 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature