Drug Discovery Maps, a Machine Learning Model That Visualizes and Predicts Kinome–Inhibitor Interaction Landscapes
Open Access
- 29 October 2018
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 59 (3), 1221-1229
- https://doi.org/10.1021/acs.jcim.8b00640
Abstract
The interpretation of high dimensional structure-activity datasets in drug discovery to predict ligand-protein interaction landscapes is a challenging task. Here we present Drug Discovery Maps (DDM), a machine learning model that maps the activity profile of compounds across an entire protein family, illustrated here for the kinase family. DDM is based on the t-Distributed Stochastic Neighbour Embedding algorithm to generate a visualization of molecular and biological similarity. DDM maps chemical and target space and predicts activity of novel kinase inhibitors across the kinome. The model was validated by independent datasets and in a prospective experimental setting, where DDM predicted new inhibitors for FMS-like tyrosine kinase 3 (FLT3), a therapeutic target for the treatment of acute myeloid leukemia. Compounds were resynthesized yielding highly potent, cellularly active FLT3 inhibitors. Biochemical assays confirmed most of the predicted off-targets. DDM is further unique in that it is completely open source, and available as a ready-to-use executable to facilitate a broad and easy adoption.Keywords
Funding Information
- Universiteit Leiden
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
- Agentschap Innoveren en Ondernemen (155028)
This publication has 40 references indexed in Scilit:
- The target landscape of clinical kinase drugsScience, 2017
- The ins and outs of selective kinase inhibitor developmentNature Chemical Biology, 2015
- The Chemical Space ProjectAccounts of Chemical Research, 2015
- Comprehensive analysis of kinase inhibitor selectivityNature Biotechnology, 2011
- Navigating the kinomeNature Chemical Biology, 2011
- A quantitative analysis of kinase inhibitor selectivityNature Biotechnology, 2008
- Chemical spaceNature, 2004
- Molecular similarity: a key technique in molecular informaticsOrganic & Biomolecular Chemistry, 2004
- Structural Basis for Control by PhosphorylationChemical Reviews, 2001
- Kinetic and Catalytic Mechanisms of Protein KinasesChemical Reviews, 2001