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

Shen, Wanxiang; Liang, Shu Ran; Jiang, Yu; Chen, Yu Zong

doi:10.1016/j.patter.2022.100658

Cited by 5 publications

(9 citation statements)

References 53 publications

(149 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the method of Met2Img, the more recent MEGMA method [ 161 ] uses manifold embedding to create a data embedding based on co-abundance patterns between microbes. Five manifold embedding methods were tested, as well as random-guided uniform embedding: MDS, LLE, ISOMAP, t-SNE and UMAP.…”

Section: Resultsmentioning

confidence: 99%

Deep learning methods in metagenomics: a review

Roy,

Prifti,

Belda

et al. 2024

Microbial Genomics

View full text Add to dashboard Cite

The ever-decreasing cost of sequencing and the growing potential applications of metagenomics have led to an unprecedented surge in data generation. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome plays a crucial role in human health, providing vital information for patient diagnosis and prognosis. However, analysing metagenomic data remains challenging due to several factors, including reference catalogues, sparsity and compositionality. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification and disease prediction. Beyond generating predictive models, a key aspect of these methods is also their interpretability. This article reviews DL approaches in metagenomics, including convolutional networks, autoencoders and attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the microbiome’s key role in our health.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep learning methods in metagenomics: a review

Roy,

Prifti,

Belda

et al. 2024

Microbial Genomics

View full text Add to dashboard Cite

show abstract

“…A great advantage of this method is its interpretability, because genera that were useful for prediction of disease (here Type 2 Diabetes) can be easily traced. However, this method works at the genus level, at best, and by taking into account only the most represented genera in the data, therefore potentially omitting information coming from less represented bacteria. Following the method of Met2Img, the more recent MEGMA method ([142]) uses Manifold Embedding to create a data embedding based on co-abundance patterns between microbes. 5 Manifold Embedding methods were tested, as well as Random-guided Uniform Embedding: MDS, LLE, ISOMAP, t-SNE, and UMAP.…”

Section: Resultsmentioning

confidence: 99%

“…Following the method of Met2Img, the more recent MEGMA method ( [142]) uses Manifold Embedding to create a data embedding based on co-abundance patterns between microbes. 5 Manifold Embedding methods were tested, as well as Random-guided Uniform Embedding : MDS, LLE, ISOMAP, t-SNE, and UMAP.…”

Section: Sequence-based Approachesmentioning

confidence: 99%

Deep learning methods in metagenomics: a review

Roy

Prifti

Zucker

2023

Preprint

View full text Add to dashboard Cite

The ever decreasing cost of sequencing and the multiplication of potential applications for the study of metagenomes have led to an unprecedented increase in the volume of data generated. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome has been shown to play an important role in human health, providing critical information for patient diagnosis and prognosis. However, the analysis of metagenomic data remains challenging for many reasons, including reference catalogs, sparsity and compositionality of the data, to name a few. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. In fact, DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification, and disease prediction. Beyond the generation of predictive models, a key aspect of such methods remains their interpretability. In this article, we provide a systematic review of deep learning approaches in metagenomics, whether based on convolutional networks, autoencoders, or attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the key role the microbiome plays in our health.

show abstract

“…Recently, we tried to construct feature relations from the perspective of information theory: using an unsupervised approach to map unordered feature points (data chaos) into a 2D feature map with patterns to enhance the learning efficiency of data. 1 , 2 The effectiveness of machine learning depends on both the model and the data, and although the model is important, I would love to see a diversity of the data level exploration in the data science community.…”

Section: Main Textmentioning

confidence: 99%