paper-with-me

Papers

GEOM-Drugs Revisited: Toward More Chemically Accurate Benchmarks for 3D Molecule Generation

2025-04-30 · Filipp Nikitin, Ian Dunn, David Ryan Koes, Olexandr Isayev

Deep generative models have shown significant promise in generating valid 3D molecular structures, with the GEOM-Drugs dataset serving as a key benchmark. However, current evaluation protocols suffer from critical flaws, including incorrect valency definitions, bugs in bond order calculations, and reliance on force fields inconsistent with the reference data. In this work, we revisit GEOM-Drugs and propose a corrected evaluation framework: we identify and fix issues in data preprocessing, construct chemically accurate valency tables, and introduce a GFN2-xTB-based geometry and energy benchmark. We retrain and re-evaluate several leading models under this framework, providing updated performance metrics and practical recommendations for future benchmarking. Our results underscore the need for chemically rigorous evaluation practices in 3D molecular generation. Our recommended evaluation methods and GEOM-Drugs processing scripts are available at https://github.com/isayevlab/geom-drugs-3dgen-evaluation.

📄 PDF Abstract BibTeX arXiv:2505.00169

Code (1)

isayevlab/geom-drugs-3dgen-evaluation 공식 구현 pytorch

Tasks

3D Molecule GenerationBenchmarkingvalid

Similar Papers 제목 키워드 기반

VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics

2026-08-26 · Fan-Sheng Chuang, Xuchen Li, Yujing Bian, Kaixiong Zhou arxiv

Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers …

Smoothing Dark Areas in Molecular Latent Diffusion

2026-06-11 · Xi Wang, Jiahan Li, Yuxuan Xia, Yingcheng Wu 외 arxiv

Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. Existing molecular VAEs, however, are typ…

Image Generation

Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation

2026-03-28 · Urvi Awasthi, Alexander Arjun Lobo, Leonid Zhukov arxiv

Generating chemically valid 3D molecules is hindered by discrete bond topology: small local bond errors can cause global failures (valence violations, disconnections, implausible rings), especially for drug-like molecule…

Graph Generation

DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory

2020-08-01 · Yixiao Chen, Linfeng Zhang, Han Wang, E Weinan

We propose a general machine learning-based framework for building an accurate and widely-applicable energy functional within the framework of generalized Kohn-Sham density functional theory. To this end, we develop a wa…

BIG-bench Machine Learning

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

2021-10-04 · NeurIPS 2021 12 · Soojung Yang, Doyeong Hwang, Seul Lee, Seongok Ryu 외

Recently, utilizing reinforcement learning (RL) to generate molecules with desired properties has been highlighted as a promising strategy for drug design. A molecular docking program - a physical simulation that estimat…

Drug DesignMolecular DockingReinforcement Learning (RL)