Active learning for computational chemogenomics.

TitleActive learning for computational chemogenomics.
Publication TypeJournal Article
Year of Publication2017
AuthorsD Reker, P Schneider, G Schneider, and JB Brown
JournalFuture Medicinal Chemistry
Volume9
Start Page381
Issue4
Pagination381 - 402
Date Published03/2017
Abstract

<h4>Aim</h4>Computational chemogenomics models the compound-protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of proteins and ligands. As an alternative to modeling entire large datasets at once, active learning adaptively incorporates a minimum of informative examples for modeling, yielding compact but high quality models. Results/methodology: We assessed active learning for protein/target family-wide chemogenomic modeling by replicate experiment. Results demonstrate that small yet highly predictive models can be extracted from only 10-25% of large bioactivity datasets, irrespective of molecule descriptors used.<h4>Conclusion</h4>Chemogenomic active learning identifies small subsets of ligand-target interactions in a large screening database that lead to knowledge discovery and highly predictive models.

DOI10.4155/fmc-2016-0197
Short TitleFuture Medicinal Chemistry