arXiv Machine Learning

Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation

arXiv AI
Sep 7

NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer

NEAT-POCKET is a pocket‑conditioned extension of the autoregressive NEAT model that generates 3D molecules atom by atom within protein binding pockets, maintaining atom permutation invariance and explicitly modeling hydrogen atoms. It outperforms existing baselines on the CrossDocked and SPINDR datasets, achieving competitive structure‑based generation performance while sampling significantly faster. The model also supports pocket‑conditioned fragment completion, a capability directly useful for lead optimization and scaffold elaboration in drug design.

By Roxane Axel Jacob, Daniel Rose, Thierry Langer, Johannes Kirchmair
arXiv AI
Jul 21

Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

arXiv:2607. 18144v1 Announce Type: cross Abstract: Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules.

By Thomas MacDougall, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Maxim Malkov, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
arXiv Machine Learning
2d ago

Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation

The paper introduces PolyLatentFlow, a continuous‑time flow‑matching framework for polymer generation, and LlamaUni, a multimodal representation that fuses polymer sequences with 3D structural data. In unconditional generation, the combination yields the highest number of valid, novel candidates while preserving diversity, and in conditional settings it systematically shifts property distributions across a 200 °C target range. Across multi‑property tasks, the representation choice affects validity, training‑set replay, and structural proximity, with PolyLatentFlow + LlamaUni achieving the best balance of high validity, low replay, and high target hit yield.

By Tianren Zhang
arXiv Machine Learning
Jul 2

SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles

arXiv:2607. 01105v1 Announce Type: new Abstract: We present SynLaD, a latent diffusion framework for small-molecule generation that unifies ligand-based drug design objectives (what to make) with synthetic accessibility (how to make it).

By Miruna Cretu, John Bradshaw, Patricia Suriana, Saeed Saremi, Omar Mahmood, Kirill Shmilovich, Kangway Chuang, Vishnu Sresht, Colin Grambow
arXiv Machine Learning
Jun 10

Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors

arXiv:2602. 04119v2 Announce Type: replace Abstract: The application of generative models for experimental drug discovery campaigns is severely limited by the difficulty of designing molecules de novo that can be synthesized in practice.

By Hyeonah Kim, Minsu Kim, Celine Roget, Dionessa Biton, Louis Vaillancourt, Yves V. Brun, Yoshua Bengio, Alex Hernandez-Garcia
arXiv AI
Aug 19

Leveraging generative hallucination and biophysics-informed modeling for unified biomolecular sequence-structure co-design

The paper introduces MCTH (Monte Carlo Tree Hallucination), an inference-only framework that performs all‑atom biomolecular sequence‑structure co‑design by treating pretrained folding and inverse‑folding models as black‑box operators. MCTH uses Monte Carlo Tree Search to allocate a fixed inference budget across competing design trajectories, incorporating model confidence, uncertainty, and cross‑expert consensus. Experiments across protein‑RNA, protein‑DNA, protein‑protein, and protein‑ligand design show that adaptive search outperforms simpler sampling strategies, and evaluations with AlphaFold3 and Chai‑1 demonstrate transferability beyond the search‑time oracle.

By Xuefeng Liu, Mingxuan Cao, Xiao Luo, Songhao Jiang, Tobin Sosnick, Jinbo Xu, Louis Maher, Rick Stevens
arXiv Machine Learning
Sep 10

PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion

PocketVE is a protein-pocket-conditioned variance‑exploding diffusion framework that integrates stable 3D coordinate denoising, classifier‑free property guidance, and adaptive protein perturbation. It improves 3D validity from 58.6% to 80.6% and reduces strain energy from 457.4 to 127.9 on CrossDocked2020 while maintaining competitive docking and property scores. The study shows moderate guidance balances target objectives with geometric quality, and diagnostics confirm enhanced pocket compatibility.

By Peining Zhang, Jinbo Bi