CAGenMol-2, a masked diffusion molecular language model that represents molecules, continuous scalar properties, and 3D protein pockets within a single wrapped sequence is introduced, allowing one checkpoint to perform property prediction, property- and pocket-conditioned generation, and partial-constraint design without task-specific architectures or backbone fine-tuning.
Abstract
Drug design couples property evaluation, conditional generation, structure-based design, and local optimization, yet machine learning systems typically address these capabilities with separate task-specific models. We introduce CAGenMol-2, a masked diffusion molecular language model that represents molecules, continuous scalar properties, and 3D protein pockets within a single wrapped sequence. Within this pretrained interface, downstream operations are selected by which sequence regions are observed or masked at inference, allowing one checkpoint to perform property prediction, property- and pocket-conditioned generation, and partial-constraint design without task-specific architectures or backbone fine-tuning. We further propose Adaptive Fragment Optimization (AdaFO), a gradient-free mask-and-refill search that turns the masked decoder into an iterative local molecular optimizer. On CrossDocked2020, AdaFO increases Success Rate from 30.2\% to 70.8\%, the best reported under this protocol, while largely preserving drug-likeness and diversity. Finally, scaffold-preserving directional editing and CRBN/VHL case studies demonstrate its use in compound design workflows spanning local molecular editing, structure-based prioritization, and downstream simulation-based screening.
HelixDTA is introduced, a deep learning framework featuring a parallel dual-branch architecture that independently learns representations from two distinct but complementary modalities: sequence context and complete target structures that demonstrates significant potential to empower precision drug design and accelerat...
Shang Lou, Xu-Hua Li, Yu-Jie Peng et al.· Journal of Chemical Informat...· 0 citations
Abstract Motivation Designing molecules with predefined properties remains a critical yet challenging task in drug discovery. Recent advances in deep learning have demonstrated strong potential in accelerating the identification of novel compounds with desired properties and activities. However, the implementation and...
Packora is presented, a flow-based generative model for molecular CSP that jointly predicts atomic coordinates and the lattice from molecular graphs that outperforms the baselines on both structure generation and ranking benchmarks.
Nayoung Kim, Kiyoung Seong, Sungsoo Ahn· 0 citations
LinkLlama is presented, a fine-tuned Meta Llama 3 model that bridges the gap between text-based generation and 3D spatial awareness, offering a highly controllable and chemically robust framework to accelerate linker design and drug discovery in general.
Kun-Yang Sun, Ying-Ze Wang, Justin Purnomo et al.· Journal of Chemical Informat...· 0 citations
PockLigGPT achieves competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility, favorable physicochemical profiles, and Lipinski-based drug-likeness.
Pablo Varas Pardo, Guillermo Marcos-Ayuso, Eugenia Ulzurrun et al.· Journal of Chemical Informat...· 0 citations
The results suggest that geometric stability and inference-time property guidance should be considered as coupled design objectives, whereas stronger guidance can degrade geometry and distributional fidelity.
Pei-Ning Zhang, Jin-Bo Bi· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.