Crowdsourced mapping of unexplored target space of kinase inhibitors

Team KinaseHunter, Team AmsterdamUMC-KU-team, Team DruginaseLearning, Team KERMIT-LAB - Ghent University, Team QED, Team METU_EMBLEBI_CROssBAR, Team DMIS_DK, Team AI Winter is Coming, Team hulab, Team ML-Med, Team Prospectors, Challenge organizers, The IDG-DREAM Drug-Kinase Binding Prediction Challenge Consortium, User oselot, Team N121, Team Let_Data_Talk, User thinng, Team KKT, Team Boun

Research output: Contribution to journalArticlepeer-review

40 Scopus citations


Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound–kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.

Original languageEnglish
Article number3307
JournalNature Communications
Issue number1
StatePublished - Dec 2021


Dive into the research topics of 'Crowdsourced mapping of unexplored target space of kinase inhibitors'. Together they form a unique fingerprint.

Cite this