Year: 2026
Type: article
Abstract: As the integration of artificial intelligence (AI) with life sciences is accelerating, its conceptual boundaries, methodological foundations, and future trajectories remain actively debated.Drawing on perspectives from frontline researchers active in AI research in multiple sub-fields of biology, this article examines the evolution, current states, and future directions of AI biology.We identify a paradigm shift from observation-driven inquiry toward discovery-and design-oriented research.We discuss the relationship between predictive modeling and mechanistic understanding, the relative importance of terminology, and the future relation of experiments and computation.We argue that future AI biology will require not only algorithmic adaptation or data accumulation, but more fundamental innovations in AI models, biological experiments, and construction of closed-loop systems that couple prediction with feedback.Furthermore, we appeal to the cultivation of nextgeneration scientists who are better equipped with critical thinking and can navigate both domains with equal fluency.This article is intended for a broad range of readers who may care about, work on, prepare for, evaluate, or sponsor future AI biology studies.
Source: Quantitative Biology
DOI: 10.1002/qub2.70061
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7223003215
