Fifteen challenges for generative AI applications to cell biology
Cell · 2026-09 · 189 (19) · 5870-5892
DOI: 10.1016/j.cell.2026.07.004 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Cell, 2026-09. Verfasst von Leo Dupire und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Systems Biology, Columbia University Irving Medical School, New York, NY, USA. Hauptthemen laut MEDLINE: Cell Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 149 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, The Chan Zuckerberg Initiative.
Abstract (Originalsprache)
Generative AI (Gen-AI) has shown a remarkable impact in several biological research areas, from protein folding and de novo design to pathogenic mutation prediction. However, it remains unclear whether these molecular-level successes can translate to cellular and multicellular insights relevant to fields ranging from immunology to cancer and neurodegeneration. This arises from the intricate nature of the molecular mechanisms that determine cellular and organismal behavior, the lack of sufficient training data, and the multicellular nature of most pathophysiologic phenotypes. Novel Gen-AI frameworks are likely needed to integrate prior biological knowledge, such as molecular interaction networks, as well as guiding principles focusing the community's attention on solving biologically and translationally relevant problems. Drawing inspiration from Hilbert's list of 23 mathematical problems that have focused the mathematical community's attention for more than a century, we propose fifteen grand AI challenges to focus the biomedical community's attention on critically relevant questions, most of which still lack effective predictive methodologies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Systems Biology, Columbia University Irving Medical School, New York, NY, USA.
- Biohub, Chicago, IL, USA.
- Chan Zuckerberg Initiative, Redwood City, CA, USA.
- Biohub, Chicago, IL, USA; Department of Chemistry, Northwestern University, Evanston, IL, USA; Department of Biochemistry and Molecular Genetics, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA; D…
- Department of Bioengineering, Stanford University, Stanford, CA, USA; Science for Life Laboratory, Department of Protein Science, KTH Royal Institute of Technology, Stockholm, Sweden; Biohub, San Francisco, CA, USA.
- Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Förderung
- National Institutes of Health
- The Chan Zuckerberg Initiative
Zitieren
APA
Dupire, L., Khan, A. A., Karaletsos, T., Kelley, S., Lundberg, E., Ma, J., Paull, E., Quake, S. R., Rabadan, R., Cassius, R., Sims, P., Tavazoie, S., Tsang, J. S., Zhang, M., & Califano, A. (2026). Fifteen challenges for generative AI applications to cell biology. Cell, 189(19), 5870-5892. https://doi.org/10.1016/j.cell.2026.07.004
Vancouver
Dupire L, Khan AA, Karaletsos T, Kelley S, Lundberg E, Ma J, et al. Fifteen challenges for generative AI applications to cell biology. Cell. 2026;189(19):5870-5892. doi:10.1016/j.cell.2026.07.004
BibTeX
@article{Dupire2026,
author = {Dupire, Leo and Khan, Aly A and Karaletsos, Theofanis and Kelley, Shana and Lundberg, Emma and Ma, Jian and Paull, Evan and Quake, Stephen R and Rabadan, Raul and Cassius, Rowan and Sims, Peter and Tavazoie, Sohail and Tsang, John S and Zhang, Mingxuan and Califano, Andrea},
title = {Fifteen challenges for generative AI applications to cell biology},
journal = {Cell},
year = {2026},
volume = {189},
number = {19},
pages = {5870--5892},
doi = {10.1016/j.cell.2026.07.004}
}
EUVIMED