aiqbench analysis
NEAT-POCKET advances structure-based drug discovery by integrating autoregressive generation with explicit protein pocket conditioning, enabling faster sampling of novel ligands while preserving atomic invariance. This method demonstrates significant speed improvements over existing baselines on standard benchmarks, offering a practical framework for lead optimization tasks that are critical to early-stage pharmaceutical research.
NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer
arXiv:2609.05097v1 Announce Type: cross Abstract: AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discovery by generating novel ligands directly within target protein binding pockets. We present NEAT-POCKET, a pocket-conditioned extension of the autoregressive NEAT model for 3D molecular generation. NEAT-POCKET generates molecules atom by atom in protein pocket environments while preserving atom permutation invariance and explicitly modeling hydrogen atoms. Benchmarks on the CrossDocked and SPINDR datasets show that NEAT-POCKET achieves competitive structure-based generation performance while sampling substantially faster than existing baselines. Beyond full-molecule generation, NEAT-POCKET naturally enables pocket-conditioned fragment completion, a task directly relevant to lead optimization and scaffold elaboration. These results position NEAT-POCKET as a fast, flexible, and practical framework for structure-based drug design.
Abstract:AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discovery by generating novel ligands directly within target protein binding pockets. We present NEAT-POCKET, a pocket-conditioned extension of the autoregressive NEAT model for 3D molecular generation. NEAT-POCKET generates molecules atom by atom in protein pocket environments while preserving atom permutation invariance and explicitly modeling hydrogen atoms. Benchmarks on the CrossDocked and SPINDR datasets show that NEAT-POCKET achieves competitive structure-based generation performance while sampling substantially faster than existing baselines. Beyond full-molecule generation, NEAT-POCKET naturally enables pocket-conditioned fragment completion, a task directly relevant to lead optimization and scaffold elaboration. These results position NEAT-POCKET as a fast, flexible, and practical framework for structure-based drug design.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.05097 [cs.LG]
(or arXiv:2609.05097v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.05097 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 212 words
Related coverage
Autoregressive latent diffusion for 3D molecule generation
arXiv · Oct 5, 2026
CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions
arXiv · Sep 30, 2026
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
arXiv · Jul 21, 2026
TreeRef-BFN: Equivariance-Free De Novo Molecule Generation based on 2D Topology and Internal 3D Geometry
arXiv · Sep 30, 2026