Automated discovery of noncovalent inhibitors of SARS-CoV-2 main protease by consensus Deep Docking of 40 billion small molecules.
Automated discovery of noncovalent inhibitors of SARS-CoV-2 main protease by consensus Deep Docking of 40 billion small molecules.
复制标题
通过400亿个小分子的共识深度对接，自动发现SARS-CoV-2主要蛋白酶的非共价抑制剂。
DOI：
10.1039/d1sc05579h
复制
发表时间：
2021-12-15
期刊：
影响因子：
8.4
通讯作者：
Cherkasov A
中科院分区：
文献类型：
--
作者：
Gentile F;Fernandez M;Ban F;Ton AT;Mslati H;Perez CF;Leblanc E;Yaacoub JC;Gleave J;Stern A;Wong B;Jean F;Strynadka N;Cherkasov A
近年来，“按需制造”化学库的爆炸性增长给计算机辅助药物发现领域带来了前所未有的机遇，但也带来了重大挑战。为了解决可访问的化学宇宙的这种扩展，分子对接需要对数十亿个化学结构进行准确排名，这需要开发自动命中选择协议，以最大限度地减少人为干预和错误。在此，我们报告了一个人工智能驱动的虚拟筛选管道的开发，该管道利用Autodock GPU，Glide SP，FRED，ICM和QuickVina 2程序的深度对接来筛选400亿个针对SARS-CoV-2主要蛋白酶（Mpro）的分子。该活动返回了大量实验证实的Mpro酶抑制剂，并且还能够对28种不同严格程度和自动化程度的命中选择策略的性能进行基准测试。这些发现为针对Mpro的点击到领先优化活动提供了新的起点，并鼓励开发集成机器学习和人类专业知识的全自动端到端药物发现协议。深度学习加速对接结合计算命中选择策略，能够从400亿个小分子的化学库中识别SARS-CoV-2主要蛋白酶的抑制剂。
Recent explosive growth of ‘make-on-demand’ chemical libraries brought unprecedented opportunities but also significant challenges to the field of computer-aided drug discovery. To address this expansion of the accessible chemical universe, molecular docking needs to accurately rank billions of chemical structures, calling for the development of automated hit-selecting protocols to minimize human intervention and error. Herein, we report the development of an artificial intelligence-driven virtual screening pipeline that utilizes Deep Docking with Autodock GPU, Glide SP, FRED, ICM and QuickVina2 programs to screen 40 billion molecules against SARS-CoV-2 main protease (Mpro). This campaign returned a significant number of experimentally confirmed inhibitors of Mpro enzyme, and also enabled to benchmark the performance of twenty-eight hit-selecting strategies of various degrees of stringency and automation. These findings provide new starting scaffolds for hit-to-lead optimization campaigns against Mpro and encourage the development of fully automated end-to-end drug discovery protocols integrating machine learning and human expertise. Deep learning-accelerated docking coupled with computational hit selection strategies enable the identification of inhibitors for the SARS-CoV-2 main protease from a chemical library of 40 billion small molecules.
登录
查看更多内容
影响因子：
5.6
作者：
Grebner, Christoph;Malmerberg, Erik;Sadowski, Jens
通讯作者：
Sadowski, Jens
影响因子：
16.6
作者：
Douangamath A;Fearon D;Gehrtz P;Krojer T;Lukacik P;Owen CD;Resnick E;Strain-Damerell C;Aimon A;Ábrányi-Balogh P;Brandão-Neto J;Carbery A;Davison G;Dias A;Downes TD;Dunnett L;Fairhead M;Firth JD;Jones SP;Keeley A;Keserü GM;Klein HF;Martin MP;Noble MEM;O'Brien P;Powell A;Reddi RN;Skyner R;Snee M;Waring MJ;Wild C;London N;von Delft F;Walsh MA
通讯作者：
Walsh MA
分子对接中的配体姿势和定向抽样。
影响因子：
3.7
作者：
Coleman RG;Carchia M;Sterling T;Irwin JJ;Shoichet BK
通讯作者：
Shoichet BK
影响因子：
56.9
作者：
Dai, Wenhao;Zhang, Bing;Liu, Hong
通讯作者：
Liu, Hong
影响因子：
14.8
作者：
Forli S;Huey R;Pique ME;Sanner MF;Goodsell DS;Olson AJ
通讯作者：
Olson AJ