当前位置: X-MOL 学术Brief. Funct. Genomics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Predicting the role of the human gut microbiome in type 1 diabetes using machine-learning methods
Briefings in Functional Genomics ( IF 4 ) Pub Date : 2024-02-20 , DOI: 10.1093/bfgp/elae004
Xiao-Wei Liu 1 , Han-Lin Li 2 , Cai-Yi Ma 1 , Tian-Yu Shi 1 , Tian-Yu Wang 1 , Dan Yan 3, 4 , Hua Tang 2, 5, 6 , Hao Lin 1 , Ke-Jun Deng 1
Affiliation  

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.

中文翻译:

使用机器学习方法预测人类肠道微生物组在 1 型糖尿病中的作用

肠道微生物是 1 型糖尿病 (T1D) 发病机制的关键因素。然而,目前尚不清楚哪些肠道菌群是影响T1D的关键因素及其对疾病发生和进展的影响。为了填补这些知识空白,我们构建了一个模型,从 1 型糖尿病患者的肠道微生物群中寻找生物标志物。我们首先使用线性判别分析效应大小 (LEfSe) 和随机森林 (RF) 方法鉴定微生物标记。此外,通过构建 T1D 肠道微生物的共现网络,我们旨在揭示健康人群和 1 型糖尿病患者中所有肠道微生物相互作用以及主要有益菌和致病菌。最后,利用PICRUST2预测京都基因与基因组百科全书(KEGG)功能途径和微生物标记的KO基因水平,以研究其生物学作用。我们的研究表明,21 个已鉴定的微生物属是 T1D 的重要生物标志物。它们在发现集和验证集上的 AUC 值为 0.962 和 0.745。功能分析显示,10个微生物属与D-精氨酸和D-鸟氨酸代谢、转录剪接体、类固醇激素生物合成和糖胺聚糖降解呈显着正相关。这些属与类固醇生物合成、氰基氨基酸代谢和药物代谢显着负相关。其他 11 个属呈负相关。总之,我们的研究确定了一套全面的具有普遍适用性的 T1D 肠道生物标志物,并揭示了肠道微生物群改变及其相互作用的生物学后果。这些发现为 T1D 的个体化管理和治疗提供了重要前景。
更新日期:2024-02-20
down
wechat
bug