GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model

doi:10.1038/s41422-024-01034-y

	GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model
	Yang, Xiaodong 1,2,3,13; Liu, Guole 4,5,10; Feng, Guihai 1,6,7,12; Bu, Dechao 2,3,8,13; Wang, Pengfei 3,9; Jiang, Jie 10; Chen, Shubai 2,3,13; Yang, Qinmeng 9; Miao, Hefan 1; Zhang, Yiyang 3,11,14; Man, Zhenpeng 3,11,14; Liang, Zhongming 3,11,14; Wang, Zichen 4,5,10; Li, Yaning 2,3,13; Li, Zheng 9; Liu, Yana 1,12; Tian, Yao 1,12; Liu, Wenhao 1,12; Li, Cong 1,3,12; Li, Ao 4,5,10; Dong, Jingxi 1,12; Hu, Zhilong 3,9; Fang, Chen 1,12; Cui, Lina 1,3; Deng, Zixu 2,3; Jiang, Haiping 1,3; Cui, Wentao 3,9; Zhang, Jiahao 3,11,14; Yang, Zhaohui 2,3,8,13; Li, Handong 5,10; He, Xingjian 10; Zhong, Liqun 4,5,10; Zhou, Jiaheng 4,5,10; Wang, Zijian 9; Long, Qingqing 9; Xu, Ping 3,9; Wang, Hongmei 1,6,7,12; Meng, Zhen 3,9; Wang, Xuezhi 3,9; Wang, Yangang 3,9; Wang, Yong 3,11,14; Zhang, Shihua 3,11,14; Guo, Jingtao 1,3,6,7,12; Zhao, Yi 2,3,8,13; Zhou, Yuanchun 3,9; Li, Fei 3,9; Liu, Jing 5,10; Chen, Yiqiang 3,13; Yang, Ge 4,5,10; Li, Xin 1,3,6,7,12
	2024-10-08
发表期刊	CELL RESEARCH
ISSN	1001-0602
页码	16
摘要	Deciphering universal gene regulatory mechanisms in diverse organisms holds great potential for advancing our knowledge of fundamental life processes and facilitating clinical applications. However, the traditional research paradigm primarily focuses on individual model organisms and does not integrate various cell types across species. Recent breakthroughs in single-cell sequencing and deep learning techniques present an unprecedented opportunity to address this challenge. In this study, we built an extensive dataset of over 120 million human and mouse single-cell transcriptomes. After data preprocessing, we obtained 101,768,420 single-cell transcriptomes and developed a knowledge-informed cross-species foundation model, named GeneCompass. During pre-training, GeneCompass effectively integrated four types of prior biological knowledge to enhance our understanding of gene regulatory mechanisms in a self-supervised manner. By fine-tuning for multiple downstream tasks, GeneCompass outperformed state-of-the-art models in diverse applications for a single species and unlocked new realms of cross-species biological investigations. We also employed GeneCompass to search for key factors associated with cell fate transition and showed that the predicted candidate genes could successfully induce the differentiation of human embryonic stem cells into the gonadal fate. Overall, GeneCompass demonstrates the advantages of using artificial intelligence technology to decipher universal gene regulatory mechanisms and shows tremendous potential for accelerating the discovery of critical cell fate regulators and candidate drug targets.
DOI	10.1038/s41422-024-01034-y
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (National Science Foundation of China)[YSBR-076] ; National Natural Science Foundation of China (National Science Foundation of China)[YSBR-034] ; CAS Project for Young Scientists in Basic Research[31971289] ; CAS Project for Young Scientists in Basic Research[32341013] ; CAS Project for Young Scientists in Basic Research[91954201] ; CAS Project for Young Scientists in Basic Research[62202455] ; CAS Project for Young Scientists in Basic Research[32341019] ; National Natural Science Foundation of China[CAS-WX2021SF-0101] ; Informatization Plan of Chinese Academy of Sciences
WOS研究方向	Cell Biology
WOS类目	Cell Biology
WOS记录号	WOS:001327618200001
出版者	SPRINGERNATURE
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39522
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Yi; Zhou, Yuanchun; Li, Fei; Liu, Jing; Chen, Yiqiang; Yang, Ge; Li, Xin
作者单位	1.Chinese Acad Sci, Inst Zool, State Key Lab Stem Cell & Reprod Biol, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Laboratoryof Multimodal Artificial Intel, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 6.Chinese Acad Sci, Inst Stem Cell & Regenerat Med, Beijing, Peoples R China 7.Beijing Inst Stem Cell & Regenerat Med, Beijing, Peoples R China 8.Chinese Acad Sci, Res Ctr Ubiquitous Comp Syst, Inst Comp Technol, Beijing, Peoples R China 9.Chinese Acad Sci, Comp Network Informat Ctr, Beijing, Peoples R China 10.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 11.Chinese Acad Sci, Acad Math & Syst Sci, CEMS,MDIS, NCMIS, Beijing, Peoples R China 12.Chinese Acad Sci, Inst Zool, Beijing, Peoples R China 13.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 14.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yang, Xiaodong,Liu, Guole,Feng, Guihai,et al. GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model[J]. CELL RESEARCH,2024:16.
APA	Yang, Xiaodong.,Liu, Guole.,Feng, Guihai.,Bu, Dechao.,Wang, Pengfei.,...&Li, Xin.(2024).GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model.CELL RESEARCH,16.
MLA	Yang, Xiaodong,et al."GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model".CELL RESEARCH (2024):16.