Real-SWIT, a generative ULVS framework that learns Enamine REAL Space as a synthesizable molecular distribution and couples this generator with a target-specific scoring model to enable docking-guided exploration of REAL Space at the level of complete molecule, establishes generative access to make-on-demand chemical space as a practical strategy for ULVS.
Abstract
Ultra-large-scale virtual screening (ULVS) increasingly relies on make-on-demand chemical spaces, but efficient access to these spaces remains challenging because their scale far exceeds what can be exhaustively enumerated and docked. Here, we present REAL-SWIT, a generative ULVS framework that learns Enamine REAL Space as a synthesizable molecular distribution and couples this generator with a target-specific scoring model to enable docking-guided exploration of REAL Space at the level of complete molecule. The generative model learned transferable features of the REAL Space distribution: approximately 96% of generated molecules were found in REAL Space, and a subset of generated molecules absent from the training release appeared in later expanded releases. In computational benchmarks, REAL-SWIT identified more molecules with favorable docking scores than representative fragment-based search strategies, including cooperative building-block combinations that fragment-level prioritization tended to miss. Experimental validation for ROCK1 yielded six biochemical inhibitors among 23 synthesized compounds, including RX-3 with an IC50 of 0.17 µM. These results establish generative access to make-on-demand chemical space as a practical strategy for ULVS.
This work forms the specialization of pretrained virtual screening models to individual pockets as a test-time adaptation problem and proposes PETA, a parameter-efficient framework that directly adapts pretrained model at test time and outperforms both pretrained and fully retrained baselines while updating only the La...
Jia-Qi Lin, Ying-Hua Yao, Chang-Ran Wang et al.· 0 citations
The first application of the V-SYNTHES2 synthon-based screening approach to the 173-billion-compound Enamine xREAL Space is reported, demonstrating near-linear computational scaling with only a 10–15% increase in cost relative to the 11-billion-compound REAL Space.
Mykola V. Protopopov, Olha Semenenko, Maryna Vasylchuk et al.· npj Drug Discovery· 0 citations
This work investigates whether LLMs can learn molecular design strategies from cheaper synthetic tasks that generalize to expensive molecular lead optimization settings and suggests that scaling post-training using synthetic tasks is an effective strategy for adapting LLMs to high-cost experimental scenarios that are t...
Frank Hu, Shriram Chennakesavalu, Zi-Cheng Wang et al.· 0 citations
AdaptiveFlow enables drug discovery at unprecedented scale and supports the development of AI-driven methods, and identifies nanomolar inhibitors of two disease-relevant targets, ferroptosis suppressor protein 1 and poly(ADP-ribose) polymerase 1.
Domiziana Cecchini, AkshatKumar Nigam, Ming Tang et al.· Nature Biotechnology· 1 citation
CRAFT is a reaction-aware molecular optimization framework that integrates Monte Carlo Tree Search (MCTS) with a multimodal strategy network and explicitly encodes two-dimensional molecular topology and atom-level reaction roles, enabling chemically feasible transformations during multi-step optimization.
Run-Fu Yu, Tong-Mao Ma, Zian Song et al.· Journal of Medicinal Chemist...· 0 citations
QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework that combines an E(3)-equivariant diffusion model with active learning and efficient quantum-mechanical methods to iteratively explore targeted QM property manifolds, is introduced.
Michael Hanna, Julian Cremer, Zekiye Erarslan et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.