Three-dimensional facial-image analysis to predict heterogeneity of the human ageing rate and the impact of lifestyle

被引：75

作者：

Xia, Xian ^{[1
,2
,3
]}

Chen, Xingwei ^{[1
,2
,3
]}

Wu, Gang ^{[1
]}

Li, Fang ^{[1
]}

Wang, Yiyang ^{[1
,2
,3
]}

Chen, Yang ^{[1
,2
,3
]}

Chen, Mingxu ^{[1
,2
,3
]}

Wang, Xinyu ^{[1
,2
,4
]}

Chen, Weiyang ^{[1
]}

Xian, Bo ^{[1
]}

Chen, Weizhong ^{[1
]}

Cao, Yaqiang ^{[1
]}

Xu, Chi ^{[1
]}

Gong, Wenxuan ^{[1
,2
,3
]}

Chen, Guoyu ^{[1
,2
,3
]}

Cai, Donghong ^{[1
,2
,3
]}

Wei, Wenxin ^{[5
]}

Yan, Yizhen ^{[1
,2
,3
]}

Liu, Kangping ^{[2
]}

Qiao, Nan ^{[6
]}

Zhao, Xiaohui ^{[6
]}

Jia, Jin ^{[6
]}

Wang, Wei ^{[7
]}

Kennedy, Brian K. ^{[8
,9
,10
,11
,12
]}

Zhang, Kang ^{[13
]}

Cannistraci, Carlo, V ^{[14
,15
,16
]}

Zhou, Yong ^{[17
]}

Han, Jing-Dong J. ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, CAS MPG Partner Inst Computat Biol, Shanghai Inst Biol Sci,Shanghai Inst Nutr & Hlth, Ctr Excellence Mol Cell Sci,Collaborat Innovat Ct, Shanghai, Peoples R China

[2] Peking Univ, Acad Adv Interdisciplinary Studies, Peking Tsinghua Ctr Life Sci, Ctr Quantitat Biol CQB, Beijing, Peoples R China

[3] Univ Chinese Acad Sci, Beijing, Peoples R China

[4] ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai, Peoples R China

[5] Second Mil Med Univ, Eastern Hepatobiliary Surg Hosp, Dept Hepat Surg, Shanghai, Peoples R China

[6] Accenture China Artificial Intelligence Lab, Shenzhen, Peoples R China

[7] Edith Cowan Univ, Sch Med & Hlth Sci, Perth, WA, Australia

[8] Natl Univ Singapore, Dept Biochem, Singapore, Singapore

[9] Natl Univ Singapore, Dept Physiol, Singapore, Singapore

[10] Natl Univ Hlth Syst, Ctr Hlth Ageing, Singapore, Singapore

[11] ASTAR, Singapore Inst Clin Sci, Singapore, Singapore

[12] Buck Inst Res Aging, Novato, CA USA

[13] Macau Univ Sci & Technol, Fac Med, Macau, Peoples R China

[14] Tech Univ Dresden, Cluster Excellence Phys Life PoL, Dept Phys,Ctr Syst Biol Dresden CSBD, Biomed Cybernet Grp,Biotechnol Ctr BIOTEC,Ctr Mol, Dresden, Germany

[15] Tsinghua Univ, Tsinghua Lab Brain & Intelligence THBI, Ctr Complex Network Intelligence CCNI, Beijing, Peoples R China

[16] Tsinghua Univ, Dept Bioengn, Beijing, Peoples R China

[17] Shanghai Jiao Tong Univ, Shanghai Gen Hosp, Clin Res Inst, Sch Med, Shanghai, Peoples R China

来源：

NATURE METABOLISM | 2020年 / 2卷 / 09期

基金：

中国国家自然科学基金;

关键词：

DNA METHYLATION; EXPRESSION; GENE; PROGRANULIN; CLASSIFICATION; BIOMARKERS; PHENOTYPE; PROFILES;

D O I：

10.1038/s42255-020-00270-x

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Not all individuals age at the same rate. Methods such as the 'methylation clock' are invasive, rely on expensive assays of tissue samples and infer the ageing rate by training on chronological age, which is used as a reference for prediction errors. Here, we develop models based on convoluted neural networks through training on non-invasive three-dimensional (3D) facial images of approximately 5,000 Han Chinese individuals that achieve an average difference between chronological or perceived age and predicted age of +/- 2.8 and 2.9 yr, respectively. We further profile blood transcriptomes from 280 individuals and infer the molecular regulators mediating the impact of lifestyle on the facial-ageing rate through a causal-inference model. These relationships have been deposited and visualized in the Human Blood Gene Expression-3D Facial Image (HuB-Fi) database. Overall, we find that humans age at different rates both in the blood and in the face, but do so coherently and with heterogeneity peaking at middle age. Our study provides an example of how artificial intelligence can be leveraged to determine the perceived age of humans as a marker of biological age, while no longer relying on prediction errors of chronological age, and to estimate the heterogeneity of ageing rates within a population.

引用

页码：946 / +

页数：24

共 44 条

[1] Accelerated Lipofuscinosis and Ubiquitination in Granulin Knockout Mice Suggest a Role for Progranulin in Successful Aging [J].