1980/01/01 by Albert P. Bartók, Albert P. Bartok, Sandip De +8 · 1 citation
Arts and Humanities · Computer Science · Materials Science · Physics and Astronomy · #Art #Artificial intelligence #Biology #Computational Drug Discovery Methods #Computational biology #Computer science #Data science #History #Machine Learning in Materials Science #Themes in Literature Analysis #X-ray Diffraction in Crystallography #cond-mat.mtrl-sci #physics.chem-ph
paper · pdf · open access · doi:10.1126/sciadv.1701816
published in Science Advances 3(12), e1701816 (American Association for the Advancement of Science)
openalex publication_date 1980/01/01 · arxiv created 2017/12/16 · arxiv updated 2017/12/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/24
Determining the stability of molecules and condensed phases is the cornerstone of atomistic modeling, underpinning our understanding of chemical and materials properties and transformations. We show that a machine-learning model, based on a local description of chemical environments and Bayesian statistical learning, provides a unified framework to predict atomic-scale properties. It captures the quantum mechanical effects governing the complex surface reconstructions of silicon, predicts the stability of different classes of molecules with chemical accuracy, and distinguishes active and inactive protein ligands with more than 99% reliability. The universality and the systematic nature of our framework provide new insight into the potential energy surface of materials and molecules.