Acta Phys. -Chim. Sin.

Previous Articles     Next Articles

From knowledge tree to knowledge forest: Harnessing chemical understanding with machine learning

Dongbo Zhao1, Yilin Zhao2, Chunying Rong3, He Zhang4,5, Chang Liu4,5, Shubin Liu6,7   

  1. 1 Institute of Biomedical Research, Yunnan University, Kunming 650500, Yunnan Province, China;
    2 Department of Chemistry and Chemical Biology, McMaster University, Hamilton Ontario L8S 4M1, Canada.;
    3 College of Chemistry and Chemical Engineering, Hunan Normal University, Changsha 410081, Hunan Province, China;
    4 Zhongguancun Institute of Artificial Intelligence, Beijing 100094, China;
    5 Zhongguancun Academy, Beijing 100094, China;
    6 Research Computing Center, University of North Carolina, Chapel Hill, NC 27599-3420, USA.;
    7 Department of Chemistry, University of North Carolina, Chapel Hill, NC 27599-3290, USA.
  • Received:2025-10-16 Revised:2025-12-13 Accepted:2025-12-18
  • Contact: Chunying Rong, Chang Liu, Shubin Liu E-mail:rongchunying@aliyun.com;liuchang@bjzgca.edu.cn;shubin@email.unc.edu

Abstract: The 2024 Physics and Chemistry Nobel Prizes to machine learning (ML) breakthroughs marked “Year 1 of AI for Science,” underscoring their transformative role in physical sciences. Yet data are not the same as understanding—a distinction central to chemistry, which has long relied on concepts such as bond, aromaticity, and reactivity as scaffolds for understanding and explanation. Building on our recent perspectives (ACS Phys. Chem. Au 2024, 4, 135-142; J. Chem. Theory Comput. 2025, 21, 10068-10079), this article explores how ML can become engines of chemical understanding. We introduce a quintet of chemical knowledge— ontology, epistemology, theory, concept, and understanding—and develop the metaphors of the Knowledge Tree and Knowledge Forest to show how diverse epistemologies interact and recursively enrich one another. Case studies on aromaticity, catalysis, orbital-free density functional theory, and protein folding illustrate how ML features, when interpreted as conceptual roots, yield fruits of understanding. Contrasting multiscale modeling with hierarchical modeling, we argue that ML enables emergent, concept-driven integration across levels. Cultivating this plural and hierarchical ecosystem may guide theoretical chemistry toward its next breakthroughs, resolving Dirac’s dilemma not by brute force but by forests of concepts that transform data into enduring understanding.

Key words: Machine learning (ML), Artificial intelligence (AI), Chemical concepts, Chemical understanding, Ontology, Epistemology, Knowledge tree, Knowledge forest