Scientific hypothesis generation by large language models: laboratory validation in breast cancer treatment
Journal of The Royal Society Interface · 2025-06 · 22 (227)
DOI: 10.1098/rsif.2024.0674 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of The Royal Society Interface, online erschienen am 04.06.2025. Verfasst von Abbi Abdel-Rehim und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK. Hauptthemen laut MEDLINE: Breast Neoplasms, Artificial Intelligence, Models, Biological. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UK Engineering and Physical Sciences Research Council (EPSRC), the Wallenberg AI, Autonomous Systems and Software Program.
Abstract (Originalsprache)
Large language models (LLMs) have transformed artificial intelligence (AI) and achieved breakthrough performance on a wide range of tasks. In science, the most interesting application of LLMs is for hypothesis formation. A feature of LLMs, which results from their probabilistic structure, is that the output text is not necessarily a valid inference from the training text. These are termed ‘hallucinations’, and are harmful in many applications. In science, some hallucinations may be useful: novel hypotheses whose validity may be tested by laboratory experiments. Here, we experimentally test the application of LLMs as a source of scientific hypotheses using the domain of breast cancer treatment. We applied the LLM GPT4 to hypothesize novel synergistic pairs of US Food and Drug Administration (FDA)-approved non-cancer drugs that target the MCF7 breast cancer cell line relative to the non-tumorigenic breast cell line MCF10A. In the first round of laboratory experiments, GPT4 succeeded in discovering three drug combinations (out of 12 tested) with synergy scores above the positive controls. GPT4 then generated new combinations based on its initial results, this generated three more combinations with positive synergy scores (out of four tested). We conclude that LLMs are a valuable source of scientific hypotheses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK.
- Algorithmic Dynamics Lab, Research Departments of Biomedical Computing and Digital Twins, School of Biomedical Engineering and Imaging Sciences, King's Institute for AI, King's College London, London, England, UK.
- Oxford Immune Algorithmics, Oxford University Innovation and London Institute for Healthcare Engineering, London, England, UK.
- Cancer Interest Group, The Francis Crick Institute, London, England, UK.
- Defence and National Security, The Alan Turing Institute, British Library, London, England, UK.
- Arctoris Ltd, Oxford, UK.
ORCID-Profile: Hector Zenil, Ross King
Förderung
- UK Engineering and Physical Sciences Research Council (EPSRC)
- the Wallenberg AI, Autonomous Systems and Software Program
Zitieren
APA
Abdel-Rehim, A., Zenil, H., Orhobor, O., Fisher, M., Collins, R. J., Bourne, E., Fearnley, G. W., Tate, E., Smith, H. X., Soldatova, L. N., & King, R. (2025). Scientific hypothesis generation by large language models: laboratory validation in breast cancer treatment. Journal of The Royal Society Interface, 22(227). https://doi.org/10.1098/rsif.2024.0674
Vancouver
Abdel-Rehim A, Zenil H, Orhobor O, Fisher M, Collins RJ, Bourne E, et al. Scientific hypothesis generation by large language models: laboratory validation in breast cancer treatment. Journal of The Royal Society Interface. 2025;22(227). doi:10.1098/rsif.2024.0674
BibTeX
@article{AbdelRehim2025,
author = {Abdel-Rehim, Abbi and Zenil, Hector and Orhobor, Oghenejokpeme and Fisher, Marie and Collins, Ross J and Bourne, Elizabeth and Fearnley, Gareth W and Tate, Emma and Smith, Holly X and Soldatova, Larisa N and King, Ross},
title = {Scientific hypothesis generation by large language models: laboratory validation in breast cancer treatment},
journal = {Journal of The Royal Society Interface},
year = {2025},
volume = {22},
number = {227},
doi = {10.1098/rsif.2024.0674}
}
EUVIMED