期刊
CHEMICAL RESEARCH IN TOXICOLOGY
卷 36, 期 6, 页码 916-925出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.chemrestox.3c00037
关键词
-
Animal studies are crucial for drug evaluation to ensure safety. We have proposed a novel framework called TransOrGAN that uses a generative adversarial network to map gene expression profiles across different organ systems, sexes, and ages in rodents. Our proof-of-concept study demonstrates that TransOrGAN can accurately infer transcriptomic profiles between organs, sexes, and ages, providing an opportunity to reduce animal usage and assess overall toxicity.
Animal studies are required for the evaluation of candidatedrugsto ensure patient and volunteer safety. Toxicogenomics is often appliedin these studies to gain understanding of the underlying mechanismsof toxicity, which is usually focused on critical organs such as theliver or kidney in young male rats. There is a strong ethical reasonto reduce, refine and replace animal use (the 3Rs), where the mappingof data between organs, sexes and ages could reduce the cost and timeof drug development. Herein, we proposed a generative adversarialnetwork (GAN)-based framework entitled TransOrGAN that allowed themolecular mapping of gene expression profiles in different rodentorgan systems and across sex and age groups. We carried out a proof-of-conceptstudy based on rat RNA-seq data from 288 samples in 9 different organsof both sexes and 4 developmental stages. First, we demonstrated thatTransOrGAN could infer transcriptomic profiles between any 2 of the9 organs studied, yielding an average cosine similarity of 0.984 betweensynthetic transcriptomic profiles and their corresponding real profiles.Second, we found that TransOrGAN could infer transcriptomic profilesobserved in females from males, with an average cosine similarityof 0.984. Third, we found that TransOrGAN could infer transcriptomicprofiles in juvenile, adult, and aged animals from adolescent animalswith an average cosine similarity of 0.981, 0.983, and 0.989, respectively.Altogether, TransOrGAN is an innovative approach to infer transcriptomicprofiles between ages, sexes, and organ systems, offering the opportunityto reduce animal usage and to provide an integrated assessment oftoxicity in the whole organism irrespective of sex or age.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据