NMFGOT: a Multi-view Learning Framework for the Microbiome and Metabolome Integrative Analysis with Optimal Transport Plan

Overview

Journal NPJ Biofilms Microbiomes

Date 2024 Nov 24

PMID 39582023

Authors

Yuanyuan Ma

Lifang Liu

Affiliations

Soon will be listed here.

Abstract

The rapid development of high-throughput sequencing techniques provides an unprecedented opportunity to generate biological insights into microbiome-related diseases. However, the relationships among microbes, metabolites and human microenvironment are extremely complex, making data analysis challenging. Here, we present NMFGOT, which is a versatile toolkit for the integrative analysis of microbiome and metabolome data from the same samples. NMFGOT is an unsupervised learning framework based on nonnegative matrix factorization with graph regularized optimal transport, where it utilizes the optimal transport plan to measure the probability distance between microbiome samples, which better dealt with the nonlinear high-order interactions among microbial taxa and metabolites. Moreover, it also includes a spatial regularization term to preserve the spatial consistency of samples in the embedding space across different data modalities. We implemented NMFGOT in several multi-omics microbiome datasets from multiple cohorts. The experimental results showed that NMFGOT consistently performed well compared with several recently published multi-omics integrating methods. Moreover, NMFGOT also facilitates downstream biological analysis, including pathway enrichment analysis and disease-specific metabolite-microbe association analysis. Using NMFGOT, we identified the significantly and stable metabolite-microbe associations in GC and ESRD diseases, which improves our understanding for the mechanisms of human complex diseases.

References

Priya S, Burns M, Ward T, Mars R, Adamowicz B, Lock E . Identification of shared and disease-specific host gene-microbiome associations across human diseases using multi-omic integration. Nat Microbiol. 2022; 7(6):780-795. PMC: 9159953. DOI: 10.1038/s41564-022-01121-z. View

Lee D, Seung H . Learning the parts of objects by non-negative matrix factorization. Nature. 1999; 401(6755):788-91. DOI: 10.1038/44565. View

Dona A, Jimenez B, Schafer H, Humpfer E, Spraul M, Lewis M . Precision high-throughput proton NMR spectroscopy of human urine, serum, and plasma for large-scale metabolic phenotyping. Anal Chem. 2014; 86(19):9887-94. DOI: 10.1021/ac5025039. View

Wang B, Mezlini A, Demir F, Fiume M, Tu Z, Brudno M . Similarity network fusion for aggregating data types on a genomic scale. Nat Methods. 2014; 11(3):333-7. DOI: 10.1038/nmeth.2810. View

Pollen A, Nowakowski T, Shuga J, Wang X, Leyrat A, Lui J . Low-coverage single-cell mRNA sequencing reveals cellular heterogeneity and activated signaling pathways in developing cerebral cortex. Nat Biotechnol. 2014; 32(10):1053-8. PMC: 4191988. DOI: 10.1038/nbt.2967. View

Ludington W . Higher-order microbiome interactions and how to find them. Trends Microbiol. 2022; 30(7):618-621. DOI: 10.1016/j.tim.2022.03.011. View

Visconti A, Le Roy C, Rosa F, Rossi N, Martin T, Mohney R . Interplay between the human gut microbiome and host metabolism. Nat Commun. 2019; 10(1):4505. PMC: 6776654. DOI: 10.1038/s41467-019-12476-z. View

Becht E, McInnes L, Healy J, Dutertre C, Kwok I, Ng L . Dimensionality reduction for visualizing single-cell data using UMAP. Nat Biotechnol. 2018; . DOI: 10.1038/nbt.4314. View

Cai D, He X, Han J, Huang T . Graph Regularized Nonnegative Matrix Factorization for Data Representation. IEEE Trans Pattern Anal Mach Intell. 2010; 33(8):1548-60. DOI: 10.1109/TPAMI.2010.231. View

10.

Cang Z, Nie Q . Inferring spatial and signaling relationships between cells from single cell transcriptomic data. Nat Commun. 2020; 11(1):2084. PMC: 7190659. DOI: 10.1038/s41467-020-15968-5. View

11.

Erawijantari P, Mizutani S, Shiroma H, Shiba S, Nakajima T, Sakamoto T . Influence of gastrectomy for gastric cancer treatment on faecal microbiome and metabolome profiles. Gut. 2020; 69(8):1404-1415. PMC: 7398469. DOI: 10.1136/gutjnl-2019-319188. View

12.

Cang Z, Zhao Y, Almet A, Stabell A, Ramos R, Plikus M . Screening cell-cell communication in spatial transcriptomics via collective optimal transport. Nat Methods. 2023; 20(2):218-228. PMC: 9911355. DOI: 10.1038/s41592-022-01728-4. View

13.

Amer A, Hamdy B, Mahmoud D, Elanany M, Rady M, Alahmadi T . Antagonistic Activity of Bacteria Isolated from the L. Gut against Some Multidrug-Resistant Human Pathogens. Antibiotics (Basel). 2021; 10(3). PMC: 7999104. DOI: 10.3390/antibiotics10030294. View

14.

Sanchez-Gorostiaga A, Bajic D, Osborne M, Poyatos J, Sanchez A . High-order interactions distort the functional landscape of microbial consortia. PLoS Biol. 2019; 17(12):e3000550. PMC: 6932822. DOI: 10.1371/journal.pbio.3000550. View

15.

Singh A, Shannon C, Gautier B, Rohart F, Vacher M, Tebbutt S . DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays. Bioinformatics. 2019; 35(17):3055-3062. PMC: 6735831. DOI: 10.1093/bioinformatics/bty1054. View

16.

Franzosa E, Sirota-Madi A, Avila-Pacheco J, Fornelos N, Haiser H, Reinker S . Gut microbiome structure and metabolic activity in inflammatory bowel disease. Nat Microbiol. 2018; 4(2):293-305. PMC: 6342642. DOI: 10.1038/s41564-018-0306-4. View

17.

Zierer J, Jackson M, Kastenmuller G, Mangino M, Long T, Telenti A . The fecal metabolome as a functional readout of the gut microbiome. Nat Genet. 2018; 50(6):790-795. PMC: 6104805. DOI: 10.1038/s41588-018-0135-7. View

18.

Al-Kuhali H, Shan M, Hael M, Al-Hada E, Al-Murisi S, Al-Kuhali A . Multiview clustering of multi-omics data integration by using a penalty model. BMC Bioinformatics. 2022; 23(1):288. PMC: 9306064. DOI: 10.1186/s12859-022-04826-4. View

19.

Jing F, Hu X, Cao Y, Xu M, Wang Y, Jing Y . Discriminating gastric cancer and gastric ulcer using human plasma amino acid metabolic profile. IUBMB Life. 2018; 70(6):553-562. DOI: 10.1002/iub.1748. View

20.

Wang X, Yang S, Li S, Zhao L, Hao Y, Qin J . Aberrant gut microbiota alters host metabolome and impacts renal failure in humans and rodents. Gut. 2020; 69(12):2131-2142. PMC: 7677483. DOI: 10.1136/gutjnl-2019-319766. View