MolSculptor: an adaptive diffusion-evolution framework enabling generative drug design for multi-target affinity and selectivity

The rational design of molecules with tailored activity/selectivity across multiple protein targets is crucial for developing therapies for complex diseases like cancer, yet remains a formidable challenge. While deep generative models show immense promise, their application to these tasks faces fundamental challenges, as they struggle to incorporate the structural information of multiple distinct protein pockets and require vast multi-target datasets or specialized expert knowledge that are rarely available. Here we introduce MolSculptor, an adaptive diffusion-evolution framework designed to generate inhibitors for any combination of on- and off-targets, circumventing the need for target-specific training data or prior expert knowledge. MolSculptor conveniently unifies both de novo design and lead optimization, provides a versatile workflow applicable to different stages of drug discovery, and allows for direct conditioning on key drug-like properties. At its core, the framework integrates a 3D-aware surrogate model that enables flexible guidance for any set of specified on- and off-targets. Furthermore, MolSculptor employs an active learning protocol to adaptively refine this guidance, ensuring high performance even in data-scarce scenarios. We demonstrate MolSculptor on a series of challenging multi-target and selective inhibitor design tasks, where it significantly outperforms state-of-the-art methods in generating high-quality candidates that satisfy all complex constraints. Notably, many of the generated molecules exhibit predicted affinity profiles superior to those of experimentally validated references. MolSculptor provides a powerful and generalizable paradigm for designing ligands with complex, multi-target activity profiles, paving the way for data-efficient solutions to complex therapeutic problems.