Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
#computer vision #climate science #quantum computing #human-computer interaction #data science #edge computing

ECloudGen: leveraging electron clouds as a latent variable to scale up structure-based molecular design

Odin Zhang Jieyu Jin Zhenxing Wu Jintu Zhang Po Yuan Yuntao Yu Haitao Lin Haiyang Zhong Xujun Zhang Chenqing Hua Wei-Bo Zhao Zheng-Shuo Zhang Kejun Ying Yu-Fei Huang Huifeng Zhao Yu Kang P. Pan Ji-Ke Wang Dong Guo Shuangjia Zheng Chang-Yu Hsieh Tingjun Hou
Oct 2025 · Nature Computational Science · Vol 5, pp. 1017 - 1028 · 4 citations · 58 references
Computer Science Medicine

TL;DR

This study presents ECloudGen, which uses latent diffusion to generate electron clouds from protein pockets and decodes them into molecules, and adopts two-stage training, which expands the chemical space accessible to generative drug design.

DOI PubMed Semantic Scholar
View source

Similar papers

Open access Jul 2026

Mol-CADiff: text-conditional molecule generation via causality-aware autoregressive diffusion

Mol-CADiff is introduced, a diffusion-based framework that uses causal attention mechanisms for text-conditional molecular generation and enhances dependency modeling both within and across modalities, enabling precise control over the generation process.

Md. Atik Ahamed, Qiang Ye, Q. Cheng · 0 citations
Book Open access Aug 2026

From VAEs to Diffusion and LLMs: Modern Generative Models for Molecular Discovery

Generative models are emerging as a key technology for accelerating molecular discovery in drug design, materials science, and catalysis by enabling efficient exploration of the vast chemical space of possible molecules. Recent advances in deep generative modeling—including variational autoencoders (VAEs), diffusion models, flow matching methods, and autoregressive transformer-based approaches—have produced a diverse toolkit for generating molecular structures and optimizing their properties. However, these paradigms are often studied independently, leaving many machine learning researchers without a clear understanding of their connections, strengths, and limitations in molecular applications. This tutorial provides a unified introduction to modern generative modeling approaches for molecular generation, covering their theoretical foundations, algorithmic design, and practical considerations for molecular representations such as 1D SMILES strings, 2D molecular graphs, and 3D structures. While the tutorial primarily focuses on generative models for de novo molecular design, we also briefly discuss how similar modeling paradigms extend to reaction prediction and retrosynthesis. By presenting these models within a common framework, the tutorial aims to equip ML researchers and AI-for-science practitioners with a clear conceptual map of the generative modeling landscape for molecular discovery and identify emerging research opportunities in this rapidly evolving area.

Kehan Guo, Yili Shen, Jeeyhun Hwang et al. · 0 citations
Jul 2026

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

A clear pattern is revealed in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.

Thomas MacDougall, Maksim Kuznetsov, Roman Schutski et al. · 1 citation
Open access Aug 2026

MARD-Mol: a hybrid autoregressive-diffusion paradigm for coarse-grained molecular modeling

MARD-Mol is proposed, a hybrid AR-diffusion framework based on motif-inspired units that reformulate property optimization into an iterative “diagnose-and-repair” process, enabling targeted optimization of defective motifs while preserving the global scaffold.

Sizhe Zhang, G. Luo, Wei Fan et al. · 0 citations
Jul 2026

A unified deep generative framework for surrogate-guided molecular discovery across diverse molecular spaces.

A high-accuracy surrogate predictor based on message-passing neural networks is decoupled from heterogeneous generators, and integrated into a closed-loop strategy of generate, score, select, and regenerate to progressively enrich high-performing candidates without modifying the underlying model architectures.

Zhaosheng Zhang, Yanbo Liu, Jiadong Liu et al. · 0 citations
Open access Aug 2026

OmniScore: Universal Scoring of Diverse Biomolecular Complexes via Equivariant Geometry-Aware Discrete Representation Learning

Scoring biomolecular complexes is central to structure assessment and drug discovery, yet the complexes themselves vary widely in pose, size, and molecular composition. A scoring function tuned for one interaction type rarely carries over to another, and most existing methods compound the problem by leaning heavily on task-specific labels. We introduce OmniScore, a universal structure-based framework that learns a shared geometry-aware representation of complexes once and then adapts it to downstream scoring through lightweight task-specific heads. OmniScore couples a graph view and a sequence view of each structure, encodes its three-dimensional geometry, and compresses representations into a compact latent space that a reconstruction module and prediction heads can reuse. We pretrain this backbone on diverse datasets including complexes, monomers, and small molecules with complementary objectives: coordinate recovery, correcting corrupted input tokens, predicting molecular identity, and grounding the representation in structure-level physical quantities. Across the evaluated benchmarks, OmniScore gave the best antibody-antigen and nanobody-antigen quality assessment on all reported metrics compared to state-of-the-art baselines. Its frozen residue embeddings matched the state-of-the-art protein-tokenization method with an average functional-site accuracy of 71.8% on a standard residue-level benchmark. On protein-ligand scoring and ranking benchmarks, it performed on par with methods built specifically for that single task. These results suggest that geometry-aware pretraining can provide a reusable scoring backbone for tasks that depend on interfacial and residue-level structure, within the evaluated settings.

Tien-Cuong Bui, Junsu Ko, Juyong Lee · 0 citations

Related blog posts

Microsoft Research Blog Jul 30, 2026

Echoverse: Deep, evolving environments for computer-use agents

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve. The post Echoverse: Deep, evolving environments for computer-use agents appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.