科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ Nature biotechnology2026-09-01

AI-enhanced adaptive virtual screening of large libraries for ligand discovery.

Domiziana Cecchini, AkshatKumar Nigam, Ming Tang, Joana Reis, Matt Koop, Andrea Gottinger, Callum Robert Nicoll, Yao Wang, Abhilash Jayaraj, Süleyman Selim Çınaroglu, Ricarda Törner, Yehor Malets, Minko Gehev, Krishna M Padmanabha Das, Kelly Churion, Jongwan Kim, Nidhin Thomas, Yong Li, Hyuk-Soo Seo, Sirano Dhe-Paganon, Christopher Secker, Mohammad Haddadnia, Alexander Hasson, Minkai Li, Abhishek Kumar, Roni Levin-Konigsberg, Eun-Bee Choi, Geoffrey I Shapiro, Huel Cox, Luke Sebastian, Chelsea Braithwaite, Puspalata Bashyal, Dmytro S Radchenko, Aditya Kumar, Lei Yang, Pierre-Yves Aquilanti, Henry Gabb, Amr Alhossary, Eric O'Neill, Gerhard Wagner, Alán Aspuru-Guzik, Yurii S Moroz, Charalampos G Kalodimos, Konstantin Fackeldey, John D Schuetz, Andrea Mattevi, Haribabu Arthanari, Christoph Gorgulla

原始摘要(英文原文)· Original abstract
Ultralarge virtual screenings (ULVSs) evaluate billions of molecules for drug discovery but face cost, flexibility and scalability limits. We introduce AdaptiveFlow, an open-source platform that makes ULVSs more accessible, scalable and efficient and supports artificial intelligence (AI) and machine learning (ML) method development. AdaptiveFlow provides a screening-ready version of the Enamine REAL Space, to our knowledge the largest library of ready-to-dock, drug-like molecules, comprising 69 billion compounds, also available in SELFIES format. An 18-dimensional grid of molecular properties prioritizes promising chemical subspaces, with optional active learning, reducing computational costs by orders of magnitude. AdaptiveFlow integrates >1,500 docking protocols, including GPU-accelerated and ML-based methods, and achieves near-linear scaling on up to 5.6 million CPUs in the Amazon Web Services cloud. We identified nanomolar inhibitors of two disease-relevant targets, ferroptosis suppressor protein 1 (FSP1) and poly(ADP-ribose) polymerase 1. Co-crystal structures provided mechanistic insights into FSP1 inhibition. AdaptiveFlow enables drug discovery at unprecedented scale and supports the development of AI-driven methods.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

AI-enhanced adaptive virtual screening of large libraries for ligand discovery. — 科研速览 Science Skim