International
The Morning Science

What science found today

‹
 

Research

Minimizing data requirements for chemical and material property prediction via cluster-based training set selection

Nature · By Quinn M. Gallagher ·

The Brief

  • A survey of 100 algorithms across 60 chemical and materials property prediction tasks was conducted.
  • Cluster-based selection of training data outperformed active learning in the study.
  • The paper is published in Nature Computational Science (doi:10.1038/s43588-026-01076-9).

Why it matters

The findings suggest that choosing training sets by clustering can reduce the data needed to train property prediction models, which can lower the cost of generating chemical and materials data.

Who’s affected

  • researchers in computational chemistry and materials science
  • machine learning practitioners working on chemical and materials property prediction

Nature Computational Science, Published online: 18 November 2026; doi:10.1038/s43588-026-01076-9 A survey of 100 algorithms across 60 chemical and materials property prediction tasks finds that cluster-based selection of training data outperforms active learning, and a…

Timeline

  1. Published online in Nature Computational Science

  2. nature.com

    Minimizing data requirements for chemical and material property prediction via cluster-based training set selection

How do you feel about this?

0 Comments

    Minimizing data requirements for chemical and material property prediction via cluster-based training set selection – The Morning Science