nguyen-crowdsourcedmappingof-2021.pdf (4.4 MB)
Crowdsourced mapping of unexplored target space of kinase inhibitors
journal contribution
posted on 2021-01-01, 00:00 authored by Anna Cichonska, Balaguru Ravikumar, Robert J Allaway, Fangping Wan, Sungjoon Park, Olexandr Isayev, Shuya Li, Michael Mason, Andrew Lamb, Ziaurrehman Tanoli, Minji Jeon, Sunkyu Kim, Mariya Popova, Stephen Capuzzi, Jianyang Zeng, Kristen Dang, Gregory Koytiger, Jaewoo Kang, Carrow I Wells, Timothy M Willson, Tudor I Oprea, Avner Schlessinger, David H Drewry, Gustavo Stolovitzky, Krister Wennerberg, Justin Guinney, Tero Aittokallio, Mehmet Tan, Chih-Han Huang, Edward S C Shih, Tsai-Min Chen, Chih-Hsun Wu, Wei-Quan Fang, Jhih-Yu Chen, Ming-Jing Hwang, Xiaokang Wang, Marouen Ben Guebila, Behrouz Shamsaei, Sourav Singh, Thin NguyenThin Nguyen, Mostafa Karimi, Di Wu, Zhangyang Wang, Yang Shen, Hakime Ozturk, Elif Ozkirimli, Arzucan Ozgur, Hansaim Lim, Lei Xie, Georgi K Kanev, Albert J Kooistra, Bart A Westerman, Panagiotis Terzopoulos, Konstantinos Ntagiantas, Christos Fotis, Leonidas Alexopoulos, Dimitri Boeckaerts, Michiel Stock, Bernard De Baets, Yves Briers, Yunan Luo, Hailin Hu, Jian Peng, Tunca Dogan, Ahmet S Rifaioglu, Heval Atas, Rengul Cetin Atalay, Volkan Atalay, Maria J Martin, Junhyun Lee, Seongjun Yun, Bumsoo Kim, Buru Chang, Gabor Turu, Adam Misak, Bence Szalai, Laszlo Hunyady, Matthias Lienhard, Paul Prasse, Ivo Bachmann, Julia Ganzlin, Gal Barel, Ralf Herwig, Davor Orsolic, Bono Lucic, Visnja Stepanic, Tomislav SmucAbstractDespite 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benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data.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.
History
Journal
Nature CommunicationsVolume
12Article number
3307Pagination
1 - 18Publisher
Nature ResearchLocation
London, Eng.Publisher DOI
Link to full text
ISSN
2041-1723eISSN
2041-1723Language
engPublication classification
C1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC