Virtual Cells: Predict, Explain, Discover

2025-05-20

AI Summary

Current cell functional response prediction in drug discovery suffers from low accuracy, poor mechanistic interpretability, and weak therapeutic relevance. Method: We propose a unified “prediction–interpretation–discovery” virtual cell modeling paradigm, integrating multimodal AI, high-throughput live-cell imaging, lab-in-the-loop experimental iteration, and biologically constrained learning to build dynamic virtual cell models with causal interpretability and therapeutic alignment. Contribution/Results: This work formally defines the paradigm for the first time and establishes a biology-driven benchmarking framework. The model enables precise perturbation-response prediction, molecular mechanism tracing, and generation of novel therapeutic hypotheses. It provides a scalable foundation for digital twin models—such as virtual patients—significantly enhancing target identification efficiency and biological insight generation.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Drug discovery is fundamentally a process of inferring the effects of treatments on patients, and would therefore benefit immensely from computational models that can reliably simulate patient responses, enabling researchers to generate and test large numbers of therapeutic hypotheses safely and economically before initiating costly clinical trials. Even a more specific model that predicts the functional response of cells to a wide range of perturbations would be tremendously valuable for discovering safe and effective treatments that successfully translate to the clinic. Creating such virtual cells has long been a goal of the computational research community that unfortunately remains unachieved given the daunting complexity and scale of cellular biology. Nevertheless, recent advances in AI, computing power, lab automation, and high-throughput cellular profiling provide new opportunities for reaching this goal. In this perspective, we present a vision for developing and evaluating virtual cells that builds on our experience at Recursion. We argue that in order to be a useful tool to discover novel biology, virtual cells must accurately predict the functional response of a cell to perturbations and explain how the predicted response is a consequence of modifications to key biomolecular interactions. We then introduce key principles for designing therapeutically-relevant virtual cells, describe a lab-in-the-loop approach for generating novel insights with them, and advocate for biologically-grounded benchmarks to guide virtual cell development. Finally, we make the case that our approach to virtual cells provides a useful framework for building other models at higher levels of organization, including virtual patients. We hope that these directions prove useful to the research community in developing virtual models optimized for positive impact on drug discovery outcomes.

Problem

• Predicting cellular responses to drug perturbations computationally
• Explaining biomolecular mechanisms behind predicted cellular changes
• Developing therapeutically-relevant virtual cell models for drug discovery

Innovation

• AI-driven virtual cells predict cellular responses
• Lab-in-the-loop generates novel therapeutic insights
• Biologically-grounded benchmarks guide model development