The data-only illusion in materials discovery

Subjects Computational methodsMetal–organic frameworks Artificial intelligence may have transformed image and language generation, but in materials science, data scarcity and synthesis complexity demand a different approach. Only by coupling artificial intelligence with deep chemical insight can we turn virtual predictions into real materials. Access through your institution Buy or subscribe This is a preview of subscription content, access via your institution Access options Access through your institution Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription $32.99 / 30 days cancel any time Learn more Subscribe to this journal Receive 12 print issues and online access $259.00 per year only $21.58 per issue Learn more Buy this articlePurchase on SpringerLinkInstant access to the full article PDF.USD 39.95Prices may be subject to local taxes which are calculated during checkout Fig. 1: The PriSMa platform.The alternative text for this image may have been generated using AI.Fig. 2: Schematic illustrating how domain knowledge is integrated into AI-driven materials design.The alternative text for this image may have been generated using AI. ReferencesLeCun, Y., Bengio, Y. & Hinton, G. Nature 521, 436–444 (2015).Article CAS PubMed Google Scholar Merchant, A. et al. Nature 624, 80–85 (2023).Article CAS PubMed PubMed Central Google Scholar Cheetham, A. K. & Seshadri, R. Chem. Mater. 36, 3490–3495 (2024).Article CAS PubMed PubMed Central Google Scholar Falkowski, A. R. & Sparks, T. D. Digit. Discov. 4, 1833–1843 (2025).Article Google Scholar Charalambous, C. et al. Nature 632, 89–94 (2024).Article CAS PubMed PubMed Central Google Scholar Boyd, P. G. et al. Nature 576, 253–256 (2019).Article CAS PubMed Google Scholar Trickett, C. A. et al. Nat. Rev. Mater. 2, 17045 (2017).Article CAS Google Scholar Park, J., Kim, H., Kang, Y., Lim, Y. & Kim, J. JACS Au 4, 3727–3743 (2024).Article CAS PubMed PubMed Central Google Scholar Xie, E., Wang, X., Siepmann, J. I., Chen, H. & Snurr, R. Q. Digit. Discov. 4, 2336–2363 (2025).Article Google Scholar Mohanty, T. et al. Integr. Mater. Manuf. Innov. https://doi.org/10.1007/s40192-026-00451-8 (2026).Behler, J. Chem. Rev. 121, 10037–10072 (2021).Article CAS PubMed Google Scholar Kang, Y. H., Park, H., Smit, B. & Kim, J. Nat. Mach. Intell. 5, 309–318 (2023).Article Google Scholar Sanchez-Lengeling, B. & Aspuru-Guzik, A. Science 361, 360–365 (2018).Article CAS PubMed Google Scholar Zheng, Z., Zhang, O., Borgs, C., Chayes, J. T. & Yaghi, O. M. J. Am. Chem. Soc. 145, 18048–18062 (2023).Article CAS PubMed PubMed Central Google Scholar Burger, B. et al. Nature 583, 237–241 (2020).Article CAS PubMed Google Scholar Download referencesAuthor informationAuthors and AffiliationsLaboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingénierie Chimiques, Ecole Polytechnique Fédérale de Lausanne (EPFL), Sion, SwitzerlandBerend SmitThe Research Centre for Carbon Solutions (RCCS), School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UKSusana GarciaAuthorsBerend SmitView author publicationsSearch author on:PubMed Google ScholarSusana GarciaView author publicationsSearch author on:PubMed Google ScholarCorresponding authorsCorrespondence to Berend Smit or Susana Garcia.Ethics declarations Competing interests The authors declare no competing interests. Rights and permissionsReprints and permissionsAbout this articleCite this articleSmit, B., Garcia, S. The data-only illusion in materials discovery. Nat. Mater. (2026). https://doi.org/10.1038/s41563-026-02578-7Download citationPublished: 17 April 2026Version of record: 17 April 2026DOI: https://doi.org/10.1038/s41563-026-02578-7Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy shareable link to clipboard Provided by the Springer Nature SharedIt content-sharing initiative