Multimodal deep learning applied to classify healthy and disease states of human microbiome

Seung Jae Lee,Mina Rho

doi:10.1038/s41598-022-04773-3

Abstract

Metagenomic sequencing methods provide considerable genomic information regarding human microbiomes, enabling us to discover and understand microbial diseases. Compositional differences have been reported between patients and healthy people, which could be used in the diagnosis of patients. Despite significant progress in this regard, the accuracy of these tools needs to be improved for applications in diagnostics and therapeutics. MDL4Microbiome, the method developed herein, demonstrated high accuracy in predicting disease status by using various features from metagenome sequences and a multimodal deep learning model. We propose combining three different features, i.e., conventional taxonomic profiles, genome-level relative abundance, and metabolic functional characteristics, to enhance classification accuracy. This deep learning model enabled the construction of a classifier that combines these various modalities encoded in the human microbiome. We achieved accuracies of 0.98, 0.76, 0.84, and 0.97 for predicting patients with inflammatory bowel disease, type 2 diabetes, liver cirrhosis, and colorectal cancer, respectively; these are comparable or higher than classical machine learning methods. A deeper analysis was also performed on the resulting sets of selected features to understand the contribution of their different characteristics. MDL4Microbiome is a classifier with higher or comparable accuracy compared with other machine learning methods, which offers perspectives on feature generation with metagenome sequences in deep learning models and their advantages in the classification of host disease status.

Highlights

Metagenomic sequencing methods provide considerable genomic information regarding human microbiomes, enabling us to discover and understand microbial diseases
Using a probability threshold of 0.5, the model achieved an accuracy of 79.5%, 70.3%, 77.4%, and 94.1% for the inflammatory bowel disease (IBD), Type 2 diabetes (T2D), liver cirrhosis (LC), and colorectal cancer (CRC) datasets, respectively (Table 2)
MDL4Microbiome showed higher or comparable accuracy for predicting the phenotypes of the hosts by combining features that were extracted on the basis of three different ways from metagenome sequencing data, i.e., on the basis of the conventional composition profiles, genome-level abundance, and metabolic functional abundance

Summary

Introduction

Metagenomic sequencing methods provide considerable genomic information regarding human microbiomes, enabling us to discover and understand microbial diseases. MDL4Microbiome, the method developed demonstrated high accuracy in predicting disease status by using various features from metagenome sequences and a multimodal deep learning model. We propose combining three different features, i.e., conventional taxonomic profiles, genome-level relative abundance, and metabolic functional characteristics, to enhance classification accuracy. This deep learning model enabled the construction of a classifier that combines these various modalities encoded in the human microbiome. MDL4Microbiome is a classifier with higher or comparable accuracy compared with other machine learning methods, which offers perspectives on feature generation with metagenome sequences in deep learning models and their advantages in the classification of host disease status. Using well-curated databases, such as KEGG9,10, COG11,12, and subsystems[13], metabolic functions are annotated for specific microbiomes using various a lgorithms[14]

Methods

Results

Conclusion