Crowdsourced mapping of unexplored target space of kinase inhibitors.
Crowdsourced mapping of unexplored target space of kinase inhibitors.
复制标题
DOI：
10.1038/s41467-021-23165-1
复制
发表时间：
2021-06-03
影响因子：
16.6
通讯作者：
Aittokallio T
中科院分区：
文献类型：
--
作者：
Cichońska A;Ravikumar B;Allaway RJ;Wan F;Park S;Isayev O;Li S;Mason M;Lamb A;Tanoli Z;Jeon M;Kim S;Popova M;Capuzzi S;Zeng J;Dang K;Koytiger G;Kang J;Wells CI;Willson TM;IDG-DREAM Drug-Kinase Binding Prediction Challenge Consortium;Oprea TI;Schlessinger A;Drewry DH;Stolovitzky G;Wennerberg K;Guinney J;Aittokallio T
尽管几十年来对调节特定蛋白质靶点活性的化合物进行了深入研究，但大部分人类激酶组仍然未被发现。因此，需要有效的方法来映射未探索的化合物-激酶相互作用的巨大空间，以获得新的和有效的活性。在这里，我们对未发表的生物活性数据进行了多个激酶家族的激酶抑制剂效力预测算法的众包基准测试。我们发现表现最好的预测是基于各种模型，包括内核学习，梯度提升和深度学习，它们的集成导致预测准确性超过单剂量激酶活性测定。我们根据模型预测设计实验，并确定即使是研究不足的激酶也会出现意想不到的活动，从而加速实验作图工作。开源预测算法以及95种化合物和295种激酶之间的生物活性为基准预测算法和扩展可药用激酶组提供了资源。IDG-DREAM Challenge根据未发表的数据对激酶抑制剂活性的预测算法进行了众包基准测试。这项研究提供了一个资源来比较新兴的算法，并优先考虑新的激酶活性，以加速药物发现和再利用的努力。
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benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data.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IDG-DREAM Challenge carried out crowdsourced benchmarking of predictive algorithms for kinase inhibitor activities on unpublished data.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.
登录
查看更多内容
影响因子：
14.8
作者：
Arrowsmith CH;Audia JE;Austin C;Baell J;Bennett J;Blagg J;Bountra C;Brennan PE;Brown PJ;Bunnage ME;Buser-Doepner C;Campbell RM;Carter AJ;Cohen P;Copeland RA;Cravatt B;Dahlin JL;Dhanak D;Edwards AM;Frederiksen M;Frye SV;Gray N;Grimshaw CE;Hepworth D;Howe T;Huber KV;Jin J;Knapp S;Kotz JD;Kruger RG;Lowe D;Mader MM;Marsden B;Mueller-Fahrnow A;Müller S;O'Hagan RC;Overington JP;Owen DR;Rosenberg SH;Roth B;Ross R;Schapira M;Schreiber SL;Shoichet B;Sundström M;Superti-Furga G;Taunton J;Toledo-Sherman L;Walpole C;Walters MA;Willson TM;Workman P;Young RN;Zuercher WJ
通讯作者：
Zuercher WJ
影响因子：
14.9
作者：
Nguyen DT;Mathias S;Bologa C;Brunak S;Fernandez N;Gaulton A;Hersey A;Holmes J;Jensen LJ;Karlsson A;Liu G;Ma'ayan A;Mandava G;Mani S;Mehta S;Overington J;Patel J;Rouillard AD;Schürer S;Sheils T;Simeonov A;Sklar LA;Southall N;Ursu O;Vidovic D;Waller A;Yang J;Jadhav A;Oprea TI;Guha R
通讯作者：
Guha R
影响因子：
14.9
作者：
Berginski ME;Moret N;Liu C;Goldfarb D;Sorger PK;Gomez SM
通讯作者：
Gomez SM
影响因子：
46.9
作者：
Davis, Mindy I.;Hunt, Jeremy P.;Zarrinkar, Patrick P.
通讯作者：
Zarrinkar, Patrick P.
影响因子：
64.8
作者：
Dar, Arvin C.;Das, Tirtha K.;Shokat, Kevan M.;Cagan, Ross L.
通讯作者：
Cagan, Ross L.