Machine learning and deep learning applications in microbiome research (2022-10-06T00:00:00.000000Z)

TL;DR

An overview of how the latest microbiome studies harness the inductive prowess of artificial intelligence methods is provided, highlighting that microbiome data – being compositional, sparse, and high-dimensional – necessitates special treatment.

Abstract

The many microbial communities around us form interactive and dynamic ecosystems called microbiomes. Though concealed from the naked eye, microbiomes govern and influence macroscopic systems including human health, plant resilience, and biogeochemical cycling. Such feats have attracted interest from the scientific community, which has recently turned to machine learning and deep learning methods to interrogate the microbiome and elucidate the relationships between its composition and function. Here, we provide an overview of how the latest microbiome studies harness the inductive prowess of artificial intelligence methods. We start by highlighting that microbiome data – being compositional, sparse, and high-dimensional – necessitates special treatment. We then introduce traditional and novel methods and discuss their strengths and applications. Finally, we discuss the outlook of machine and deep learning pipelines, focusing on bottlenecks and considerations to address them.

Authors

Ricardo Hernández Medina

1 papers

S. Kutuzova

1 papers

Knud Nor Nielsen

1 papers

TL;DR

Abstract

Authors

References100 items

Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data

Cross-cohort gut microbiome associations with immune checkpoint inhibitor response in advanced melanoma

Microbiome differential abundance methods produce different results across 38 datasets

Disentangling host–microbiota complexity through hologenomics

Uniform Manifold Approximation and Projection (UMAP) Reveals Composite Patterns and Resolves Visualization Artifacts in Microbiome Data

A mixture-of-experts deep generative model for integrated analysis of single-cell multiomics data

Solutions in microbiome engineering: prioritizing barriers to organism establishment

Geographic differences in gut microbiota composition impact susceptibility to enteric infection

Genome binning of viral entities from bulk metagenomics data

phyLoSTM: a novel deep learning model on disease prediction from longitudinal microbiome data

Human host status inference from temporal microbiome changes via recurrent neural networks

Microbiome-based disease prediction with multimodal variational information bottlenecks

Individuals with substance use disorders have a distinct oral microbiome pattern

Survey of artificial intelligence approaches in the study of anthropogenic impacts on symbiotic organisms – a holistic view

Generalized Multimodal ELBO

Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment

A survey on data‐efficient algorithms in big data era

Multimodal Variational Autoencoders for Semi-Supervised Learning: In Defense of Product-of-Experts

Improved metagenome binning and assembly using deep variational autoencoders

Harnessing machine learning for development of microbiome therapeutics

A t-SNE Based Classification Approach to Compositional Microbiome Data

Innovations to culturing the uncultured microbial majority

Microbiome definition re-visited: old concepts and new challenges

DeepCoDA: personalized interpretability for compositional health data

TaxoNN: ensemble of neural networks on stratified microbiome data for disease prediction

A practical guide to amplicon and metagenomic analysis of microbiome data

PopPhy-CNN: A Phylogenetic Tree Embedded Architecture for Convolutional Neural Networks to Predict Host Phenotype From Metagenomic Data

Decoding the language of microbiomes using word-embedding techniques, and applications in inflammatory bowel disease

Predicting microbiomes through a deep latent space

Robust biomarker discovery for microbiome-wide association studies.

Viruses in the Built Environment (VIBE) meeting report

mlr3: A modern object-oriented machine learning framework in R

Multimodal Generative Models for Compositional Representation Learning

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Graph Embedding Deep Learning Guides Microbial Biomarkers' Identification

Using Autoencoders for Predicting Latent Microbiome Community Shifts Responding to Dietary Changes

Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

DeepMicro: deep representation learning for disease prediction based on microbiome data

Learning accurate representations of microbe-metabolite interactions

MetaPheno: A critical evaluation of deep learning and machine learning in metagenome-based disease prediction.

Deep in the Bowel: Highly Interpretable Neural Encoder-Decoder Networks Predict Gut Metabolites from Gut Microbiome

MetaBAT 2: an adaptive binning algorithm for robust and efficient genome reconstruction from metagenome assemblies

How Microbes Shape Their Communities? A Microbial Community Model Based on Functional Genes

Utilizing longitudinal microbiome taxonomic profiles to predict food allergy via Long Short-Term Memory networks

Definitions, methods, and applications in interpretable machine learning

An Ensemble Feature Selection Method Based on Deep Forest for Microbiome-Wide Association Studies

Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis

MetaNN: accurate classification of host phenotypes from metagenomic data using neural networks

Escaping the Curse of Dimensionality in Similarity Learning: Efficient Frank-Wolfe Algorithm and Generalization Bounds

Disease Classification in Metagenomics with 2D Embeddings and Deep Learning

Core microbiomes for sustainable agroecosystems

CAMISIM: simulating metagenomes and microbial communities

The sponge holobiont in a changing ocean: from microbes to ecosystems

Environment dominates over host genetics in shaping human gut microbiota

A Survey of Methods for Explaining Black Box Models

Multimodal Generative Models for Scalable Weakly-Supervised Learning

Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks

Using convolutional neural networks to explore the microbiome

Opportunities and obstacles for deep learning in biology and medicine

Predicting the HMA-LMA Status in Marine Sponges by Machine Learning

Metagenome-Wide Association Study and Machine Learning Prediction of Bulk Soil Microbiome and Crop Productivity

Exact sequence variants should replace operational taxonomic units in marker-gene data analysis

Normalization and microbial differential abundance strategies depend upon data characteristics

The Plant Microbiota: Systems-Level Insights and Perspectives.

Joint Multimodal Learning with Deep Generative Models

Editorial: Anthropogenic Impacts on the Microbial Ecology and Function of Aquatic Environments

Machine Learning Meta-analysis of Large Metagenomic Datasets: Tools and Biological Insights

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Fizzy: feature subset selection for metagenomics

Phylogenetic approaches to microbial community classification

The dynamics of the human infant gut microbiome in development and in progression toward type 1 diabetes.

21st century agriculture: integration of plant microbiomes for improved crop production and food security

Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints

GloVe: Global Vectors for Word Representation

Which is more important for classifying microbial communities: who's there or what they can do?