When Biology Meets Medicine: A Perspective on Foundation Models

Foundation models (FMs) are reshaping artificial intelligence and are now poised to transform life sciences and medicine. Here, we review biological FMs across multiple hierarchical scales, spanning from molecules and sequences to cells and tissues, and medical FMs across diverse data modalities. We analyze the core technical advances enabling these systems, alongside the domain‐specific data challenges that currently limit their practical impact. We argue that progress in biomedical FMs depends not only on architectural innovation but also, critically, on addressing the constraints imposed by biological and medical data. We highlight public health insurance claims as a valuable yet underutilized data resource capable of bridging biological mechanisms with real‐world clinical outcomes. Finally, we outline a paradigm in which insurance‐informed FMs are embedded within agent systems, enabling more robust reasoning, adaptive experimentation, and decision support across biomedical domains.

Authors

Institutions

Publication Details

Journal
Advanced Intelligent Discovery
Published
2026-03-27
DOI
https://doi.org/10.1002/aidi.202500245
Primary Topic
Gene Regulatory Network Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

When Biology Meets Medicine: A Perspective on Foundation Models

Yuxuan Wang, Kunying Niu, Jun Huang, Limin Zou
Advanced Intelligent Discovery
Gene Regulatory Network Analysis
article

When Biology Meets Medicine: A Perspective on Foundation Models

Yuxuan Wang, Kunying Niu, Jun Huang, Limin Zou
article en

Abstract

Foundation models (FMs) are reshaping artificial intelligence and are now poised to transform life sciences and medicine. Here, we review biological FMs across multiple hierarchical scales, spanning from molecules and sequences to cells and tissues, and medical FMs across diverse data modalities. We analyze the core technical advances enabling these systems, alongside the domain‐specific data challenges that currently limit their practical impact. We argue that progress in biomedical FMs depends not only on architectural innovation but also, critically, on addressing the constraints imposed by biological and medical data. We highlight public health insurance claims as a valuable yet underutilized data resource capable of bridging biological mechanisms with real‐world clinical outcomes. Finally, we outline a paradigm in which insurance‐informed FMs are embedded within agent systems, enabling more robust reasoning, adaptive experimentation, and decision support across biomedical domains.

Advanced Intelligent Discovery
Westlake University (CN)
Openalex Percentile: Top 6%
Gene Regulatory Network Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

When Biology Meets Medicine: A Perspective on Foundation Models — Yuxuan Wang, Kunying Niu, et al. · Advanced Intelligent Discovery (2026) | TGRS Research Map | TGRS