Active learning for computational chemogenomics
OPEN ACCESS
Loading...
Author / Producer
Date
2017-03
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Abstract
Aim: 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. Conclusion: Chemogenomic active learning identifies small subsets of ligand–target interactions in a large screening database that lead to knowledge discovery and highly predictive models.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
9 (4)
Pages / Article No.
381 - 402
Publisher
Future Science
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
chemogenomics; computational chemistry and modeling; virtual screening
Organisational unit
03852 - Schneider, Gisbert / Schneider, Gisbert