Computational data as the fuel for AI in chemistry
- 1Department of Pure and Applied Chemistry, University of Strathclyde 295 Cathedral Street Glasgow G1 1XL UK
Abstract
The rapid growth of machine learning and generative AI in the chemical sciences has placed increasing demands on the data used to train and evaluate these models. Although algorithmic advances have attracted considerable attention, the quality, consistency, coverage and accessibility of chemical data remain major constraints on AI-driven discovery. This perspective argues that computational data should be regarded not merely as a complement to experimental data, but as deliberately designed, domain-specific infrastructure for chemical AI. This does not require exhaustive coverage of chemical space: the distinctive value of computational methods lies in their ability to generate reproducible, consistently labelled data systematically within selected regions of chemical and configurational space. Through case studies in neural-network potentials and computational peptide design, we examine how the selection, sampling, fidelity and scale of computational datasets define model capabilities and domains of applicability. We then consider how computational and experimental data can be combined, with computation enabling scalable, targeted data generation and experiment providing physical grounding and validation. We conclude by identifying priorities for deliberate dataset design, FAIR data practices and open benchmarking in chemical AI.
Related
- vibyverse: an integrated computational chemistry ecosystem developed through agentic engineering
- Making Complete-Basis-Set Extrapolation Visible: A Spreadsheet-Based Activity for Upper-Division Computational Chemistry
- Natural Product Chemistry in Sickle Cell Disease Therapeutics: Phytochemical Mechanisms, Pharmacokinetics, and Computational Docking Insights for Next-Generation Anti-Sickling Agents: A Comprehensive Review
- Development and Evaluation of an Agentic Suite of Tasks Covering a Computational Chemistry Curriculum
- Conformational Analysis of Methoxy- and Methylthio-Substituted Thiophenes by Broadband Rotational Spectroscopy and Computational Chemistry.
BibTeX
@article{urquhart2026computational,
title = {{Computational data as the fuel for AI in chemistry}},
author = {Ross James Urquhart and Tell Tuttle},
journal = {Chemical Science},
year = {2026},
month = sep,
doi = {10.1039/d6sc03659g},
url = {https://doi.org/10.1039/d6sc03659g},
note = {CC BY 3.0},
}
RIS
TY - JOUR
TI - Computational data as the fuel for AI in chemistry
AU - Ross James Urquhart
AU - Tell Tuttle
PY - 2026
DA - 2026/09/09
JO - Chemical Science
DO - 10.1039/d6sc03659g
UR - https://doi.org/10.1039/d6sc03659g
AB - The rapid growth of machine learning and generative AI in the chemical sciences has placed increasing demands on the data used to train and evaluate these models. Although algorithmic advances have attracted considerable attention, the quality, consistency, coverage and accessibility of chemical data remain major constraints on AI-driven discovery. This perspective argues that computational data should be regarded not merely as a complement to experimental data, but as deliberately designed, domain-specific infrastructure for chemical AI. This does not require exhaustive coverage of chemical space: the distinctive value of computational methods lies in their ability to generate reproducible, consistently labelled data systematically within selected regions of chemical and configurational space. Through case studies in neural-network potentials and computational peptide design, we examine how the selection, sampling, fidelity and scale of computational datasets define model capabilities and domains of applicability. We then consider how computational and experimental data can be combined, with computation enabling scalable, targeted data generation and experiment providing physical grounding and validation. We conclude by identifying priorities for deliberate dataset design, FAIR data practices and open benchmarking in chemical AI.
SN - 2041-6520
SN - 2041-6539
ER -