• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

TransOrGAN:一种在器官、年龄和性别之间对大鼠转录组图谱进行人工智能映射的方法。

TransOrGAN: An Artificial Intelligence Mapping of Rat Transcriptomic Profiles between Organs, Ages, and Sexes.

机构信息

National Center for Toxicological Research, Food and Drug Administration, Jefferson, Arkansas 72079, United States.

ApconiX Ltd, Alderley Park, Alderley Edge SK10 4TG, United Kingdom.

出版信息

Chem Res Toxicol. 2023 Jun 19;36(6):916-925. doi: 10.1021/acs.chemrestox.3c00037. Epub 2023 May 18.

DOI:10.1021/acs.chemrestox.3c00037
PMID:37200521
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10433534/
Abstract

Animal studies are required for the evaluation of candidate drugs to ensure patient and volunteer safety. Toxicogenomics is often applied in these studies to gain understanding of the underlying mechanisms of toxicity, which is usually focused on critical organs such as the liver or kidney in young male rats. There is a strong ethical reason to reduce, refine and replace animal use (the 3Rs), where the mapping of data between organs, sexes and ages could reduce the cost and time of drug development. Herein, we proposed a generative adversarial network (GAN)-based framework entitled TransOrGAN that allowed the molecular mapping of gene expression profiles in different rodent organ systems and across sex and age groups. We carried out a proof-of-concept study based on rat RNA-seq data from 288 samples in 9 different organs of both sexes and 4 developmental stages. First, we demonstrated that TransOrGAN could infer transcriptomic profiles between any 2 of the 9 organs studied, yielding an average cosine similarity of 0.984 between synthetic transcriptomic profiles and their corresponding real profiles. Second, we found that TransOrGAN could infer transcriptomic profiles observed in females from males, with an average cosine similarity of 0.984. Third, we found that TransOrGAN could infer transcriptomic profiles in juvenile, adult, and aged animals from adolescent animals with an average cosine similarity of 0.981, 0.983, and 0.989, respectively. Altogether, TransOrGAN is an innovative approach to infer transcriptomic profiles between ages, sexes, and organ systems, offering the opportunity to reduce animal usage and to provide an integrated assessment of toxicity in the whole organism irrespective of sex or age.

摘要

动物研究对于评估候选药物是必需的,以确保患者和志愿者的安全。毒理基因组学通常应用于这些研究中,以了解毒性的潜在机制,这些研究通常集中在年轻雄性大鼠的关键器官,如肝脏或肾脏。有强烈的伦理理由来减少、优化和替代动物使用(3Rs),其中器官、性别和年龄之间的数据映射可以降低药物开发的成本和时间。在此,我们提出了一个基于生成对抗网络(GAN)的框架,称为 TransOrGAN,它允许在不同的啮齿动物器官系统和性别和年龄组之间进行基因表达谱的分子映射。我们进行了一项概念验证研究,基于 288 个样本的大鼠 RNA-seq 数据,这些样本来自 9 种不同器官的雌雄两性和 4 个发育阶段。首先,我们证明了 TransOrGAN 可以在研究的 9 个器官中的任意两个之间推断转录组谱,生成的合成转录组谱与真实谱之间的余弦相似度平均为 0.984。其次,我们发现 TransOrGAN 可以从雄性推断雌性的转录组谱,平均余弦相似度为 0.984。第三,我们发现 TransOrGAN 可以从青少年推断出幼年、成年和老年动物的转录组谱,平均余弦相似度分别为 0.981、0.983 和 0.989。总之,TransOrGAN 是一种在年龄、性别和器官系统之间推断转录组谱的创新方法,它提供了减少动物使用的机会,并提供了对整个生物体的毒性进行综合评估的机会,而不受性别或年龄的影响。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/a30a7ecfec37/tx3c00037_0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/20c2af69cc34/tx3c00037_0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/7476b9fdc514/tx3c00037_0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/e7c90640fffd/tx3c00037_0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/00db0da75cd8/tx3c00037_0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/42e709296f65/tx3c00037_0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/f7453f0749ec/tx3c00037_0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/a30a7ecfec37/tx3c00037_0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/20c2af69cc34/tx3c00037_0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/7476b9fdc514/tx3c00037_0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/e7c90640fffd/tx3c00037_0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/00db0da75cd8/tx3c00037_0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/42e709296f65/tx3c00037_0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/f7453f0749ec/tx3c00037_0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a337/10433534/a30a7ecfec37/tx3c00037_0007.jpg

相似文献

1
TransOrGAN: An Artificial Intelligence Mapping of Rat Transcriptomic Profiles between Organs, Ages, and Sexes.TransOrGAN:一种在器官、年龄和性别之间对大鼠转录组图谱进行人工智能映射的方法。
Chem Res Toxicol. 2023 Jun 19;36(6):916-925. doi: 10.1021/acs.chemrestox.3c00037. Epub 2023 May 18.
2
Tox-GAN: An Artificial Intelligence Approach Alternative to Animal Studies-A Case Study With Toxicogenomics.毒理生成对抗网络:一种替代动物实验的人工智能方法——毒理基因组学案例研究
Toxicol Sci. 2022 Mar 28;186(2):242-259. doi: 10.1093/toxsci/kfab157.
3
A rat RNA-Seq transcriptomic BodyMap across 11 organs and 4 developmental stages.一项涵盖11个器官和4个发育阶段的大鼠RNA测序转录组人体图谱。
Nat Commun. 2014;5:3230. doi: 10.1038/ncomms4230.
4
Comprehensive RNA-Seq transcriptomic profiling across 11 organs, 4 ages, and 2 sexes of Fischer 344 rats.对 Fischer 344 大鼠的 11 种器官、4 个年龄和 2 个性别进行全面的 RNA-Seq 转录组谱分析。
Sci Data. 2014 Jun 24;1:140013. doi: 10.1038/sdata.2014.13. eCollection 2014.
5
Landscape of circRNAs Across 11 Organs and 4 Ages in Fischer 344 Rats.费希尔344大鼠11个器官和4个年龄段的环状RNA图谱
Chem Res Toxicol. 2021 Feb 15;34(2):240-246. doi: 10.1021/acs.chemrestox.0c00144. Epub 2020 Aug 4.
6
Multigenerational reproductive study of genistein (Cas No. 446-72-0) in Sprague-Dawley rats (feed study).染料木黄酮(化学物质登录号:446-72-0)对斯普拉格-道利大鼠的多代生殖研究(饲料喂养研究)
Natl Toxicol Program Tech Rep Ser. 2008 Mar(539):1-266.
7
Transorgan fluxes in a porcine model reveal a central role for liver in acylcarnitine metabolism.猪模型中转细胞器通量揭示了肝脏在酰基辅酶 A 代谢中的核心作用。
Am J Physiol Endocrinol Metab. 2015 Aug 1;309(3):E256-64. doi: 10.1152/ajpendo.00503.2014. Epub 2015 Jun 2.
8
A generative adversarial network model alternative to animal studies for clinical pathology assessment.一种替代动物研究的生成对抗网络模型,用于临床病理学评估。
Nat Commun. 2023 Nov 6;14(1):7141. doi: 10.1038/s41467-023-42933-9.
9
Breaking the ageing paradigm in endometrium: endometrial gene expression related to cilia and ageing hallmarks in women over 35 years.打破子宫内膜衰老范式:35 岁以上女性与纤毛和衰老标志相关的子宫内膜基因表达。
Hum Reprod. 2022 Apr 1;37(4):762-776. doi: 10.1093/humrep/deac010.
10
Expression profiling and functional annotation of noncoding genes across 11 distinct organs in rat development.在大鼠发育的 11 个不同器官中进行非编码基因的表达谱分析和功能注释。
Sci Rep. 2016 Dec 9;6:38575. doi: 10.1038/srep38575.

引用本文的文献

1
Application of a metabolic network-based graph neural network for the identification of toxicant-induced perturbations.基于代谢网络的图神经网络在识别毒物诱导扰动中的应用。
Toxicol Sci. 2025 Jul 1;206(1):19-29. doi: 10.1093/toxsci/kfaf065.
2
Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World.利用化学结构进行毒性预测的机器学习:在现实世界中取得成功的支柱。
Chem Res Toxicol. 2025 May 19;38(5):759-807. doi: 10.1021/acs.chemrestox.5c00033. Epub 2025 May 2.
3
Bridging organ transcriptomics for advancing multiple organ toxicity assessment with a generative AI approach.

本文引用的文献

1
scGGAN: single-cell RNA-seq imputation by graph-based generative adversarial network.scGGAN:基于图的生成对抗网络的单细胞RNA测序数据插补
Brief Bioinform. 2023 Mar 19;24(2). doi: 10.1093/bib/bbad040.
2
Tox-GAN: An Artificial Intelligence Approach Alternative to Animal Studies-A Case Study With Toxicogenomics.毒理生成对抗网络:一种替代动物实验的人工智能方法——毒理基因组学案例研究
Toxicol Sci. 2022 Mar 28;186(2):242-259. doi: 10.1093/toxsci/kfab157.
3
DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation.
利用生成式人工智能方法构建器官转录组学以推进多器官毒性评估
NPJ Digit Med. 2024 Nov 5;7(1):310. doi: 10.1038/s41746-024-01317-z.
4
Progress in toxicogenomics to protect human health.毒理基因组学在保护人类健康方面的进展。
Nat Rev Genet. 2025 Feb;26(2):105-122. doi: 10.1038/s41576-024-00767-1. Epub 2024 Sep 2.
5
Computational models for predicting liver toxicity in the deep learning era.深度学习时代预测肝脏毒性的计算模型。
Front Toxicol. 2024 Jan 19;5:1340860. doi: 10.3389/ftox.2023.1340860. eCollection 2023.
6
Multiorgan locked-state model of chronic diseases and systems pharmacology opportunities.多器官锁定状态模型与慢性疾病和系统药理学机遇
Drug Discov Today. 2024 Jan;29(1):103825. doi: 10.1016/j.drudis.2023.103825. Epub 2023 Nov 13.
深度癌症预测:使用模型级表示的深度学习驱动的致癌性预测
Front Artif Intell. 2021 Nov 18;4:757780. doi: 10.3389/frai.2021.757780. eCollection 2021.
4
DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment.DeepCellState:一种基于自动编码器的框架,用于预测药物处理诱导的细胞类型特异性转录状态。
PLoS Comput Biol. 2021 Oct 5;17(10):e1009465. doi: 10.1371/journal.pcbi.1009465. eCollection 2021 Oct.
5
Structure and Illumination Constrained GAN for Medical Image Enhancement.结构和光照约束生成对抗网络在医学图像增强中的应用。
IEEE Trans Med Imaging. 2021 Dec;40(12):3955-3967. doi: 10.1109/TMI.2021.3101937. Epub 2021 Nov 30.
6
Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology.利用高通量筛选数据、深度神经网络和条件生成对抗网络来推进预测毒理学。
PLoS Comput Biol. 2021 Jul 2;17(7):e1009135. doi: 10.1371/journal.pcbi.1009135. eCollection 2021 Jul.
7
Transcriptome Analysis Reveals the AhR, Smad2/3, and HIF-1α Pathways as the Mechanism of Ochratoxin A Toxicity in Kidney Cells.转录组分析揭示芳烃受体、Smad2/3和缺氧诱导因子-1α信号通路是赭曲霉毒素A对肾细胞毒性作用的机制。
Toxins (Basel). 2021 Mar 6;13(3):190. doi: 10.3390/toxins13030190.
8
scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses.scGNN 是一种用于单细胞 RNA-Seq 分析的新型图神经网络框架。
Nat Commun. 2021 Mar 25;12(1):1882. doi: 10.1038/s41467-021-22197-x.
9
RNA-Seq analysis of the protection by Dendrobium nobile alkaloids against carbon tetrachloride hepatotoxicity in mice.铁皮石斛生物碱抗四氯化碳致小鼠肝损伤的 RNA-Seq 分析。
Biomed Pharmacother. 2021 May;137:111307. doi: 10.1016/j.biopha.2021.111307. Epub 2021 Feb 6.
10
Eight ways machine learning is assisting medicine.机器学习助力医学的八种方式。
Nat Med. 2021 Jan;27(1):2-3. doi: 10.1038/s41591-020-01197-2.