How to build an AI-driven digital organism
Nature Medicine, Published online: 13 August 2026; doi:10.1038/s41591-026-04595-0 Manipulating biology in the physical world is complex; the authors envision an AI-driven digital organism—a system of integrated multiscale foundation models—detailing how to construct and use such a model to advance biological and medical research.
Biology plays a crucial role in medicine, pharmacy, public health and longevity. Modeling and simulating biology in the physical world is complex, expensive and risky. An AI-driven digital organism (AIDO) could provide a safe, affordable and high-throughput alternative platform for predicting, simulating and programming biology.
The AIDO would consist of integrated multiscale foundation models, reflecting biological scales, connectedness and complexities. It could help guide wet-lab experiments and inform first-principle reasoning, ultimately aiding in decoding and improving life. Several recent studies have explored foundation models for various aspects of biology, including genomics, protein structure prediction, single-cell transcriptomics, and biomedical text generation.
These efforts demonstrate the potential for AI to revolutionize our understanding and manipulation of biological systems.
Written by urgent.news from Nature Medicine's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
