Mapping the complete target space of drugs and drug-like compounds, including both intended ‘primary targets’ as well as secondary ‘off-targets’, is a critical part of drug discovery efforts. Such a map would enable one not only to explore the therapeutic potential of chemical agents but also to better predict and manage their possible adverse effects prior to clinical trials [1]. However, the massive size of the chemical universe makes experimentally mapping the bioactivity of the full space of compound-target interactions quickly infeasible in practice, even with automated high-throughput profiling assays.

This IDG-DREAM Drug-Kinase Binding Prediction Challenge seeks to evaluate the power of statistical and machine learning models as a systematic and cost-effective means for catalyzing compound-target interaction mapping efforts by prioritizing most potent interactions for further experimental evaluation. The Challenge will focus on kinase inhibitors, due to their clinical importance [2], and will be implemented in a screening-based, pre-competitive drug discovery project in collaboration with theIlluminating the Druggable Genome (IDG) Kinase-focused Data and Resource Generation Center, consortium, with the aim to establish kinome-wide target profiles of small-molecule agents, with the goal of extending the druggability of the human kinome space.

[1] Santos et al. A comprehensive map of molecular drug targets. Nat Rev Drug Discovery 2017, 16, 19-34.[2] Elkins et al. Comprehensive characterization of the Published Kinase Inhibitor Set. Nat Biotech. 2016, 34, 95-103.

Publication

Cichonska, Anna, Balaguru Ravikumar, Robert J. Allaway, Sungjoon Park, Fangping Wan, Olexandr Isayev, Shuya Li, et al. “Crowdsourced Mapping Extends the Target Space of Kinase Inhibitors.” BioRxiv, February 11, 2020, 2019.12.31.891812. https://doi.org/10.1101/2019.12.31.891812.