Enhanced metagenomic deep learning for disease prediction and consistent signature recognition by restructured microbiome 2D representations.

Autor:	Shen WX; The State Key Laboratory of Chemical Oncogenomics, Key Laboratory of Chemical Biology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China.; Bioinformatics and Drug Design Group, Department of Pharmacy, and Center for Computational Science and Engineering, National University of Singapore, Singapore 117543, Singapore., Liang SR; The State Key Laboratory of Chemical Oncogenomics, Key Laboratory of Chemical Biology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China., Jiang YY; The State Key Laboratory of Chemical Oncogenomics, Key Laboratory of Chemical Biology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China., Chen YZ; The State Key Laboratory of Chemical Oncogenomics, Key Laboratory of Chemical Biology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China.; Shenzhen Bay Laboratory, Shenzhen 518000, China.
Jazyk:	angličtina
Zdroj:	Patterns (New York, N.Y.) [Patterns (N Y)] 2022 Dec 15; Vol. 4 (1), pp. 100658. Date of Electronic Publication: 2022 Dec 15 (Print Publication: 2023).
DOI:	10.1016/j.patter.2022.100658
Abstrakt:	Metagenomic analysis has been explored for disease diagnosis and biomarker discovery. Low sample sizes, high dimensionality, and sparsity of metagenomic data challenge metagenomic investigations. Here, an unsupervised microbial embedding, grouping, and mapping algorithm (MEGMA) was developed to transform metagenomic data into individualized multichannel microbiome 2D representation by manifold learning and clustering of microbial profiles (e.g., composition, abundance, hierarchy, and taxonomy). These 2D representations enable enhanced disease prediction by established ConvNet-based AggMapNet models, outperforming the commonly used machine learning and deep learning models in metagenomic benchmark datasets. These 2D representations combined with AggMapNet explainable module robustly identified more reliable and replicable disease-prediction microbes (biomarkers). Employing the MEGMA-AggMapNet pipeline for biomarker identification from 5 disease datasets, 84% of the identified biomarkers have been described in over 74 distinct works as important for these diseases. Moreover, the method also discovered highly consistent sets of biomarkers in cross-cohort colorectal cancer (CRC) patients and microbial shifts in different CRC stages. Competing Interests: The authors declare no competing interests. (© 2022 The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu