生成语法
基因组学
转化式学习
计算机科学
人工智能
生成模型
机器学习
表达式(计算机科学)
功能基因组学
基因
生物
基因组
遗传学
心理学
教育学
程序设计语言
作者
Gregory Koytiger,Alice M. Walsh,Vaishali Marar,Kayla A Johnson,Max Highsmith,Alexander R. Abbas,Andrew Stirn,Ariel R. Brumbaugh,David Alvarez‐Ponce,Hui Ding,J. Kahn,Sheng-Yong Niu,L. Ray,Candace Savonen,Stein Setvik,Jeffrey T. Leek,Robert K. Bradley
标识
DOI:10.1101/2025.09.08.674753
摘要
Realizing AI's promise to accelerate biomedical research requires AI models that are both accurate and sufficiently flexible to capture the diversity of real-life experiments. Here, we describe a generative genomics framework for AI-based experimental prediction that mirrors the process of designing and conducting an experiment in the lab or clinic. We created GEM-1 (Generate Expression Model-1), an AI system that effectively models the enormous range of bulk and single-cell gene expression experiments performed by scientists and benchmarked its performance across multiple biological axes. GEM-1's prediction of future gene expression experiments--RNA-seq data deposited in public archives after our training data cutoff--yielded accuracy comparable to the best-possible performance estimated by comparing the results of matched lab experiments. Overall, our approach illustrates the transformative potential of generative genomics for applications ranging from predicting cellular perturbations in vitro to de novo generation of data from large clinical cohorts.
科研通智能强力驱动
Strongly Powered by AbleSci AI