How to build the virtual cell with artificial intelligence: Priorities and opportunities

Charlotte Bunne¹, Yusuf Roohani², Yanay Rosen³, Ankit Gupta⁴, Xikun Zhang⁵, Marcel Roed³, Theo Alexandrov⁶, Mohammed AlQuraishi⁷, Patricia Brennan⁸, Daniel B Burkhardt⁹, Andrea Califano¹⁰, Jonah Cool⁸, Abby F Dernburg¹¹, Kirsty Ewing⁸, Emily B Fox¹², Matthias Haury¹³, Amy E Herr¹⁴, Eric Horvitz¹⁵, Patrick D Hsu¹⁶, Viren Jain¹⁷, Gregory R Johnson¹⁸, Thomas Kalil¹⁹, David R Kelley²⁰, Shana O Kelley²¹, Anna Kreshuk²², Tim Mitchison²³, Stephani Otte¹³, Jay Shendure²⁴, Nicholas J Sofroniew²⁵, Fabian Theis²⁶, Christina V Theodoris²⁷, Srigokul Upadhyayula²⁸, Marc Valer⁸, Bo Wang²⁹, Eric Xing³⁰, Serena Yeung-Levy³¹, Marinka Zitnik³², Theofanis Karaletsos³³, Aviv Regev³⁴, Emma Lundberg³⁵, Jure Leskovec³⁶, Stephen R Quake³⁷

Affiliations

¹ Department of Computer Science, Stanford University, Stanford, CA, USA; Genentech, South San Francisco, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; School of Computer and Communication Sciences and School of Life Sciences, EPFL, Lausanne, Switzerland.
² Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Arc Institute, Palo Alto, CA, USA.
³ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA.
⁴ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden.
⁵ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA.
⁶ Department of Pharmacology, University of California, San Diego, San Diego, CA, USA; Department of Bioengineering, University of California, San Diego, San Diego, CA, USA.
⁷ Department of Bioengineering, University of California, San Diego, San Diego, CA, USA.
⁸ Chan Zuckerberg Initiative, Redwood City, CA, USA.
⁹ Cellarity, Somerville, MA, USA.
¹⁰ Department of Systems Biology, Columbia University, New York, NY, USA; Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, NY, USA; Chan Zuckerberg Biohub, New York, NY, USA.
¹¹ Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA.
¹² Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Statistics, Stanford University, Stanford, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA.
¹³ Chan Zuckerberg Institute for Advanced Biological Imaging, Redwood City, CA, USA.
¹⁴ Chan Zuckerberg Biohub, San Francisco, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA.
¹⁵ Microsoft Research, Redmond, WA, USA.
¹⁶ Arc Institute, Palo Alto, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Center for Computational Biology, University of California, Berkeley, Berkeley, CA, USA.
¹⁷ Google Research, Mountain View, CA, USA.
¹⁸ NewLimit, San Francisco, CA, USA.
¹⁹ Schmidt Futures, New York, NY, USA.
²⁰ Calico Life Sciences LLC, San Francisco, CA, USA.
²¹ Chan Zuckerberg Biohub, Chicago, IL, USA; Northwestern University, Evanston, IL, USA.
²² Cell Biology and Biophysics Unit, European Molecular Biology Laboratory, Heidelberg, Germany.
²³ Department of Systems Biology, Harvard Medical School, Boston, MA, USA.
²⁴ Department of Genome Sciences, University of Washington, Seattle, WA, USA; Brotman Baty Institute for Precision Medicine, Seattle, WA, USA; Seattle Hub for Synthetic Biology, Seattle, WA, USA; Howard Hughes Medical Institute, Seattle, WA, USA.
²⁵ EvolutionaryScale, PBC, New York, NY, USA.
²⁶ Institute of Computational Biology, Helmholtz Center Munich, Munich, Germany; School of Computing, Information and Technology, Technical University of Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany.
²⁷ Gladstone Institute of Cardiovascular Disease, Gladstone Institute of Data Science and Biotechnology, San Francisco, CA, USA; Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA.
²⁸ Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA; Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
²⁹ Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada.
³⁰ Carnegie Mellon University, School of Computer Science, Pittsburgh, PA, USA; Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates.
³¹ Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.
³² Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA; Broad Institute of MIT and Harvard, Cambridge, MA, USA.
³³ Chan Zuckerberg Initiative, Redwood City, CA, USA. Electronic address: tkaraletsos@chanzuckerberg.com.
³⁴ Genentech, South San Francisco, CA, USA. Electronic address: regev.aviv@gene.com.
³⁵ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Pathology, Stanford University, Stanford, CA, USA. Electronic address: emmalu@stanford.edu.
³⁶ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA. Electronic address: jure@cs.stanford.edu.
³⁷ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Applied Physics, Stanford University, Stanford, CA, USA. Electronic address: steve@czbiohub.org.

PMID: 39672099
PMCID: PMC12148494
DOI: 10.1016/j.cell.2024.11.015

How to build the virtual cell with artificial intelligence: Priorities and opportunities

Charlotte Bunne et al. Cell. 2024.

. 2024 Dec 12;187(25):7045-7063.

doi: 10.1016/j.cell.2024.11.015.

Authors

Affiliations

¹ Department of Computer Science, Stanford University, Stanford, CA, USA; Genentech, South San Francisco, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; School of Computer and Communication Sciences and School of Life Sciences, EPFL, Lausanne, Switzerland.
² Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Arc Institute, Palo Alto, CA, USA.
³ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA.
⁴ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden.
⁵ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA.
⁶ Department of Pharmacology, University of California, San Diego, San Diego, CA, USA; Department of Bioengineering, University of California, San Diego, San Diego, CA, USA.
⁷ Department of Bioengineering, University of California, San Diego, San Diego, CA, USA.
⁸ Chan Zuckerberg Initiative, Redwood City, CA, USA.
⁹ Cellarity, Somerville, MA, USA.
¹⁰ Department of Systems Biology, Columbia University, New York, NY, USA; Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, NY, USA; Chan Zuckerberg Biohub, New York, NY, USA.
¹¹ Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA.
¹² Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Statistics, Stanford University, Stanford, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA.
¹³ Chan Zuckerberg Institute for Advanced Biological Imaging, Redwood City, CA, USA.
¹⁴ Chan Zuckerberg Biohub, San Francisco, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA.
¹⁵ Microsoft Research, Redmond, WA, USA.
¹⁶ Arc Institute, Palo Alto, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Center for Computational Biology, University of California, Berkeley, Berkeley, CA, USA.
¹⁷ Google Research, Mountain View, CA, USA.
¹⁸ NewLimit, San Francisco, CA, USA.
¹⁹ Schmidt Futures, New York, NY, USA.
²⁰ Calico Life Sciences LLC, San Francisco, CA, USA.
²¹ Chan Zuckerberg Biohub, Chicago, IL, USA; Northwestern University, Evanston, IL, USA.
²² Cell Biology and Biophysics Unit, European Molecular Biology Laboratory, Heidelberg, Germany.
²³ Department of Systems Biology, Harvard Medical School, Boston, MA, USA.
²⁴ Department of Genome Sciences, University of Washington, Seattle, WA, USA; Brotman Baty Institute for Precision Medicine, Seattle, WA, USA; Seattle Hub for Synthetic Biology, Seattle, WA, USA; Howard Hughes Medical Institute, Seattle, WA, USA.
²⁵ EvolutionaryScale, PBC, New York, NY, USA.
²⁶ Institute of Computational Biology, Helmholtz Center Munich, Munich, Germany; School of Computing, Information and Technology, Technical University of Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany.
²⁷ Gladstone Institute of Cardiovascular Disease, Gladstone Institute of Data Science and Biotechnology, San Francisco, CA, USA; Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA.
²⁸ Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA; Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
²⁹ Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada.
³⁰ Carnegie Mellon University, School of Computer Science, Pittsburgh, PA, USA; Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates.
³¹ Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.
³² Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA; Broad Institute of MIT and Harvard, Cambridge, MA, USA.
³³ Chan Zuckerberg Initiative, Redwood City, CA, USA. Electronic address: tkaraletsos@chanzuckerberg.com.
³⁴ Genentech, South San Francisco, CA, USA. Electronic address: regev.aviv@gene.com.
³⁵ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Pathology, Stanford University, Stanford, CA, USA. Electronic address: emmalu@stanford.edu.
³⁶ Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA. Electronic address: jure@cs.stanford.edu.
³⁷ Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Applied Physics, Stanford University, Stanford, CA, USA. Electronic address: steve@czbiohub.org.

PMID: 39672099
PMCID: PMC12148494
DOI: 10.1016/j.cell.2024.11.015

Abstract

Cells are essential to understanding health and disease, yet traditional models fall short of modeling and simulating their function and behavior. Advances in AI and omics offer groundbreaking opportunities to create an AI virtual cell (AIVC), a multi-scale, multi-modal large-neural-network-based model that can represent and simulate the behavior of molecules, cells, and tissues across diverse states. This Perspective provides a vision on their design and how collaborative efforts to build AIVCs will transform biological research by allowing high-fidelity simulations, accelerating discoveries, and guiding experimental studies, offering new opportunities for understanding cellular functions and fostering interdisciplinary collaborations in open science.

Keywords: AI; ML; cell biology; virtual cell.

PubMed Disclaimer

Conflict of interest statement

Declaration of interests C.B. and A.V.R. are employees of Genentech, a member of the Roche Group. A.V.R. has equity in Roche. A.V.R. was a co-founder and equity holder of Celsius Therapeutics and is an equity holder in Immunitas. Until July 31, 2020, A.V.R. was an S.A.B. member of ThermoFisher Scientific, Syros Pharmaceuticals, Neogene Therapeutics, and Asimov. A.V.R. is a named inventor on multiple filed patents related to single-cell and spatial genomics, including for scRNA-seq, spatial transcriptomics, Perturb-Seq, compressed experiments, and PerturbView. E.L. is an advisor for the Chan-Zuckerberg Initiative Foundation, Element Biosciences, Cartography Biosciences, Pfizer, Santa Ana Bio, and Pixelgen Technologies. N.J.S. is an employee of EvolutionaryScale, PBC.

Figures

**Figure 1.. Capabilities of the AIVC**
(A) The AIVC provides a universal representation (UR) of a cell state that can be obtained across species and conditions and generated from different data modalities across scales (molecular, cellular, and multicellular). (B) The AIVC possesses capabilities to represent and predict cell biology. This universality allows the representation to act as a reference that can generalize to previously unobserved cell states, providing guidance for future data generation. Because the representation is shared across modalities, it also remains invariant to the specific data type used to generate it, serving as a virtual representation for unified analysis across modalities. The AIVC also allows modeling the dynamics of cells as they transition between different states, whether naturally due to processes such as differentiation or due to genetic variation or artificially through engineered perturbations. Thus, the AIVC enables *in silico* experimentation that would otherwise be cost-prohibitive or impossible in a lab. (C) The utility of the AIVC depends on its interactions with humans at different levels. At the individual scientist level, it must be accessible through open licenses and the democratization of computing resources. Interpretability can be established through intermediary layers, such as language models that allow the virtual cell to communicate its results effectively. At the scientific community level, evaluating the AIVC should focus on core capabilities that move beyond narrow benchmarks. Community development will be crucial for ongoing improvements to the virtual cell that remain accessible. At the societal level, the AIVC must ensure the privacy of its contents to protect sensitive data.

**Figure 2.. Overview of the AIVC**
(A and B) (A) Similar to biological cells, (B) the AIVC models cell biology across different physical scales, including molecular, cellular, and multicellular. Along the physical dimension, the first scale models the state and interactions of individual molecules, such as those of the central dogma, as well as additional molecules, such as metabolites. Molecules can be represented as sequences or atomic structures. The next scale represents cells as collections of these molecules. For example, such cells contain a genetic sequence, RNA transcripts, and some quantities of proteins. Molecules within cells have specific locations that may be related to their function. The final scale models the interactions between cells and how they communicate and form complex tissues. Each scale relies on universal representations that are learned from multi-modal data and are integrating URs from the previous scale. (C and D) (C) To capture the behavior and dynamics of physical cells, its components, or collections, (D) the AIVC comprises virtual instruments. On the cellular scale, for example, manipulator VIs simulate how cell states change as cells divide, migrate, develop from progenitor states, or respond to perturbations through learned transitions in the URs. Decoder VIs allow for the decoding of the cell UR, e.g., to understand phenotypic properties.

See this image and copyright information in PMC

Update of

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities.
Bunne C, Roohani Y, Rosen Y, Gupta A, Zhang X, Roed M, Alexandrov T, AlQuraishi M, Brennan P, Burkhardt DB, Califano A, Cool J, Dernburg AF, Ewing K, Fox EB, Haury M, Herr AE, Horvitz E, Hsu PD, Jain V, Johnson GR, Kalil T, Kelley DR, Kelley SO, Kreshuk A, Mitchison T, Otte S, Shendure J, Sofroniew NJ, Theis F, Theodoris CV, Upadhyayula S, Valer M, Wang B, Xing E, Yeung-Levy S, Zitnik M, Karaletsos T, Regev A, Lundberg E, Leskovec J, Quake SR. Bunne C, et al. ArXiv [Preprint]. 2024 Oct 14:arXiv:2409.11654v2. ArXiv. 2024. Update in: Cell. 2024 Dec 12;187(25):7045-7063. doi: 10.1016/j.cell.2024.11.015. PMID: 39398201 Free PMC article. Updated. Preprint.

References

1. Slepchenko BM, Schaff JC, Macara I, and Loew LM (2003). Quantitative cell biology with the Virtual Cell. Trends Cell Biol. 13, 570–576. - PubMed
1. Johnson GT, Agmon E, Akamatsu M, Lundberg E, Lyons B, Ouyang W, Quintero-Carmona OA, Riel-Mehan M, Rafelski S, and Horwitz R (2023). Building the next generation of virtual cells to understand cellular biology. Biophys. J 122, 3560–3569. - PMC - PubMed
1. Marx V (2023). How to build a virtual embryo. Nat. Methods 20, 1838–1843. - PubMed
1. Goldberg AP, Szigeti B, Chew YH, Sekar JA, Roth YD, and Karr JR (2018). Emerging whole-cell modeling principles and methods. Curr. Opin. Biotechnol 51, 97–102. - PMC - PubMed
1. Georgouli K, Yeom J-S, Blake RC, and Navid A (2023). Multi-scale models of whole cells: progress and challenges. Front. Cell Dev. Biol 11, 1260507. - PMC - PubMed

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
- Elsevier Science
- PubMed Central

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

How to build the virtual cell with artificial intelligence: Priorities and opportunities

Affiliations

How to build the virtual cell with artificial intelligence: Priorities and opportunities

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

Update of

References

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources