Identifying keystone species in microbial communities using deep learning


Por: Wang, XW, Sun, Z, Jia, HJ, Michel-Mata, S, Angulo, MT, Dai, L, He, XS, Weiss, ST, Liu, YY

Publicada: 1 ene 2024 Ahead of Print: 1 nov 2023
Resumen:
Previous studies suggested that microbial communities can harbour keystone species whose removal can cause a dramatic shift in microbiome structure and functioning. Yet, an efficient method to systematically identify keystone species in microbial communities is still lacking. Here we propose a data-driven keystone species identification (DKI) framework based on deep learning to resolve this challenge. Our key idea is to implicitly learn the assembly rules of microbial communities from a particular habitat by training a deep-learning model using microbiome samples collected from this habitat. The well-trained deep-learning model enables us to quantify the community-specific keystoneness of each species in any microbiome sample from this habitat by conducting a thought experiment on species removal. We systematically validated this DKI framework using synthetic data and applied DKI to analyse real data. We found that those taxa with high median keystoneness across different communities display strong community specificity. The presented DKI framework demonstrates the power of machine learning in tackling a fundamental problem in community ecology, paving the way for the data-driven management of complex microbial communities. Using deep learning to identify the assembly rules of microbial communities from different habitats, the authors develop a framework to quantify and predict the community-specific keystoneness of each species in any microbiome sample.

Filiaciones:
Wang, XW:
 Brigham & Womens Hosp, Channing Div Network Med, Dept Med, Boston, MA 02115 USA

 Harvard Med Sch, Boston, MA 02115 USA

Sun, Z:
 Brigham & Womens Hosp, Channing Div Network Med, Dept Med, Boston, MA 02115 USA

 Harvard Med Sch, Boston, MA 02115 USA

Jia, HJ:
 Fudan Univ, Sch Life Sci, Shanghai, Peoples R China

 Fudan Univ, Inst Precis Med Greater Bay Area Guangzhou, Guangzhou, Peoples R China

Michel-Mata, S:
 Princeton Univ, Dept Ecol & Evolutionary Biol, Princeton, NJ USA

Angulo, MT:
 Univ Nacl Autonoma Mexico, Inst Math, Juriquilla, Mexico

Dai, L:
 Shenzhen Inst Adv Technol, Shenzhen Inst Synthet Biol, CAS Key Lab Quantitat Engn Biol, Shenzhen, Peoples R China

 Univ Chinese Acad Sci, Beijing, Peoples R China

He, XS:
 Forsyth Inst, Dept Microbiol, Cambridge, MA USA

 Harvard Sch Dent Med, Dept Oral Med Infect & Immun, Boston, MA USA

Weiss, ST:
 Brigham & Womens Hosp, Channing Div Network Med, Dept Med, Boston, MA 02115 USA

 Harvard Med Sch, Boston, MA 02115 USA

Liu, YY:
 Brigham & Womens Hosp, Channing Div Network Med, Dept Med, Boston, MA 02115 USA

 Harvard Med Sch, Boston, MA 02115 USA

 Univ Illinois, Carl R Woese Inst Genom Biol, Ctr Artificial Intelligence & Modeling, Champaign, IL 61820 USA
ISSN: 2397334X
Editorial
Nature Publishing Group, MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND, Reino Unido
Tipo de documento: Article
Volumen: 8 Número: 1
Páginas: 22-31
WOS Id: 001106164400001
ID de PubMed: 37974003
imagen Green Submitted

MÉTRICAS