期刊
NATURE COMMUNICATIONS
卷 12, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41467-021-23165-1
关键词
-
资金
- Academy of Finland [310507, 313267, 326238]
- Cancer Research UK
- Brain Tumour Charity [REF: C42454/A28596]
- Helse SOr-Ost [2020026]
- National Institutes of Health [1U24DK116204-01, U54OD020353, U24CA224370, U24TR002278, U01CA239108]
- AbbVie
- Bayer Pharma AG
- Boehringer Ingelheim
- Canada Foundation for Innovation
- Eshelman Institute for Innovation
- Genome Canada
- Innovative Medicines Initiative [ULTRA-DD 115766]
- Wellcome Trust
- Janssen
- Merck Kga
- Merck Sharp Dohme
- Novartis Pharma AG
- Ontario Ministry of Economic Development and Innovation
- Pfizer
- Sao Paulo Research Foundation-FAPESP
- Takeda
- National Science Foundation (NSF) [CHE-1802789, CHE-2041108]
- Eshelman Institute for Innovation (EII) awards
- Molecular Sciences Software Institute (MolSSI) Software Fellowship
- NVIDIA Graduate Fellowship
By benchmarking predictive algorithms on unpublished bioactivity data, it was found that ensemble models based on various approaches can improve prediction accuracy and accelerate experimental mapping of unexplored compound-kinase interactions.
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benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data.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. The IDG-DREAM Challenge carried out crowdsourced benchmarking of predictive algorithms for kinase inhibitor activities on unpublished data. This study provides a resource to compare emerging algorithms and prioritize new kinase activities to accelerate drug discovery and repurposing efforts.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据