Predicting the role of the human gut microbiome in type 1 diabetes using machine-learning methods.

Autor:	Liu XW; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China., Li HL; School of Basic Medical Sciences, Southwest Medical University, Luzhou 646000, China., Ma CY; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China., Shi TY; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China., Wang TY; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China., Yan D; Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China.; Beijing Institute of Clinical Pharmacy, Beijing 100050, China., Tang H; School of Basic Medical Sciences, Southwest Medical University, Luzhou 646000, China.; Basic Medicine Research Innovation Center for Cardiometabolic diseases, Ministry of Education, Luzhou 646000, China.; Central Nervous System Drug Key Laboratory of Sichuan Province, Luzhou 646000, China., Lin H; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China., Deng KJ; School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China.
Jazyk:	angličtina
Zdroj:	Briefings in functional genomics [Brief Funct Genomics] 2024 Jul 19; Vol. 23 (4), pp. 464-474.
DOI:	10.1093/bfgp/elae004
Abstrakt:	Gut microbes is a crucial factor in the pathogenesis of type 1 diabetes (T1D). However, it is still unclear which gut microbiota are the key factors affecting T1D and their influence on the development and progression of the disease. To fill these knowledge gaps, we constructed a model to find biomarker from gut microbiota in patients with T1D. We first identified microbial markers using Linear discriminant analysis Effect Size (LEfSe) and random forest (RF) methods. Furthermore, by constructing co-occurrence networks for gut microbes in T1D, we aimed to reveal all gut microbial interactions as well as major beneficial and pathogenic bacteria in healthy populations and type 1 diabetic patients. Finally, PICRUST2 was used to predict Kyoto Encyclopedia of Genes and Genomes (KEGG) functional pathways and KO gene levels of microbial markers to investigate the biological role. Our study revealed that 21 identified microbial genera are important biomarker for T1D. Their AUC values are 0.962 and 0.745 on discovery set and validation set. Functional analysis showed that 10 microbial genera were significantly positively associated with D-arginine and D-ornithine metabolism, spliceosome in transcription, steroid hormone biosynthesis and glycosaminoglycan degradation. These genera were significantly negatively correlated with steroid biosynthesis, cyanoamino acid metabolism and drug metabolism. The other 11 genera displayed an inverse correlation. In summary, our research identified a comprehensive set of T1D gut biomarkers with universal applicability and have revealed the biological consequences of alterations in gut microbiota and their interplay. These findings offer significant prospects for individualized management and treatment of T1D. (© The Author(s) 2024. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu