Back to AI News
arxiv

Chem World: A Large-Scale Benchmark and Physics-Aware Framework for Trustworthy Molecular Property Prediction

Chem World is a large-scale benchmark that integrates 17 public datasets covering over 800,000 molecular and chemical-system instances across 10 property tracks, spanning single-molecule and multi-component systems including drug solubility. The work aims to unify fragmented evaluation by providing a single testbed for molecular representations and compositional modeling. Building on the benchmark, the authors propose PACM, a physics-aware compositional modeling approach that combines molecular representations with composition-aware modeling and domain-specific physical constraints. Experiments report that molecular language models provide strong, transferable representations while PACM improves prediction across diverse chemical systems, and the authors release a drug-property prediction agent built on PACM.

AI Brief

It gives AI-for-science researchers a consolidated, large-scale molecular property benchmark plus a physics-aware modeling framework, which is directly useful for comparing and improving chemistry models.

arXiv:2611.13945v1 Announce Type: cross Abstract: Molecular property prediction is fundamental to computational chemistry and drug formulation research, yet existing benchmarks remain fragmented across datasets, properties, and evaluation protocols, limiting systematic evaluation of model generalization. We introduce Chem World, a large-scale benchmark integrating 17 public datasets with over 800,000 molecular and chemical-system instances across 10 property tracks, covering single-molecule and multi-component systems, including drug solubility. Chem World provides a unified testbed for evaluating molecular representations and compositional modeling across diverse chemical properties. Building on the benchmark, we propose PACM (Physics-Aware Compositional Modeling), which combines molecular representations with composition-aware modeling and domain-specific physical constraints. Extensive experiments show that molecular language models provide strong and transferable representations, while PACM consistently improves prediction across diverse chemical systems. Chem World and our PACM-powered drug-property prediction Agent support generalizable chemical modeling and offer a foundation for AI-assisted biomedical research and drug formulation development.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!