DGCNN approach links metagenome-derived taxon and functional information providing insight into global soil organic carbon DOI Creative Commons
Laura‐Jayne Gardiner, Matthew M. Marshall,

Katharina Reusch

et al.

npj Biofilms and Microbiomes, Journal Year: 2024, Volume and Issue: 10(1)

Published: Oct. 26, 2024

Abstract Metagenomics can provide insight into the microbial taxa present in a sample and, through gene identification, functional potential of community. However, taxonomic and information are typically considered separately downstream analyses. We develop interpretable machine learning (ML) approaches for modelling metagenomic data, combining biological representation species with their associated genetically encoded functions within models. apply our methods to investigate soil organic carbon (SOC) stocks. First, we combine diverse global set microbiome samples environmental improving predictive performance classic ML providing new insights role microbiomes cycling. Our network analysis identified by classical models provides context ecological significance, extending focus beyond just most ‘hidden’ features model that might be less using standard explainability. next unique graph representations individual microbiomes, linking directly, enabling predictions SOC via deep convolutional neural networks (DGCNNs). Interpretation DGCNNs distinguished between importance key species, genome sequence differences, e.g., loss/acquisition, associate SOC. These identify several members Verrucomicrobiaceae family range functions, related carbohydrate metabolism, as important stocks effective predictors. relatively understudied but widespread organisms could play an dynamics globally.

Language: Английский

Synergizing Artificial Intelligence and Probiotics: A Comprehensive Review of Emerging Applications in Health Promotion and Industrial Innovation DOI
Xin Han,

Q. D. Liu,

Yun Li

et al.

Trends in Food Science & Technology, Journal Year: 2025, Volume and Issue: unknown, P. 104938 - 104938

Published: Feb. 1, 2025

Language: Английский

Citations

5
Deep learning in microbiome analysis: a comprehensive review of neural network models DOI Creative Commons
Piotr Przymus, Krzysztof Rykaczewski, Adrián Martín‐Segura

et al.

Frontiers in Microbiology, Journal Year: 2025, Volume and Issue: 15

Published: Jan. 22, 2025

Microbiome research, the study of microbial communities in diverse environments, has seen significant advances due to integration deep learning (DL) methods. These computational techniques have become essential for addressing inherent complexity and high-dimensionality microbiome data, which consist different types omics datasets. Deep algorithms shown remarkable capabilities pattern recognition, feature extraction, predictive modeling, enabling researchers uncover hidden relationships within ecosystems. By automating detection functional genes, interactions, host-microbiome dynamics, DL methods offer unprecedented precision understanding composition its impact on health, disease, environment. However, despite their potential, approaches face challenges research. Additionally, biological variability datasets requires tailored ensure robust generalizable outcomes. As research continues generate vast complex datasets, these will be crucial advancing microbiological insights translating them into practical applications with DL. This review provides an overview models discussing strengths, uses, implications future studies. We examine how are being applied solve key problems highlight potential pathways overcome current limitations, emphasizing transformative could field moving forward.

Language: Английский

Citations

1
Artificial intelligence tools for the identification of antibiotic resistance genes DOI Creative Commons

Isaac T Olatunji,

Danae Kala Rodriguez Bardaji,

Renata Rezende Miranda

et al.

Frontiers in Microbiology, Journal Year: 2024, Volume and Issue: 15

Published: July 12, 2024

The fight against bacterial antibiotic resistance must be given critical attention to avert the current and emerging crisis of treating infections due inefficacy clinically relevant antibiotics. Intrinsic genetic mutations transferrable genes (ARGs) are at core development resistance. However, traditional alignment methods for detecting ARGs have limitations. Artificial intelligence (AI) approaches can potentially augment detection identify targets antagonistic bactericidal bacteriostatic molecules that or developed as This review delves into literature regarding various AI identifying annotating ARGs, highlighting their potential Specifically, we discuss (1) direct identification classification from genome DNA sequences, (2) plasmid (3) putative feature selection.

Language: Английский

Citations

7
Metagenomic Analysis and Their Application DOI
Arpita Ghosh,

Aditya Metha,

Asif M. Khan

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Introduction DOI
Röbbe Wünschiers

Computational biology, Journal Year: 2025, Volume and Issue: unknown, P. 3 - 10

Published: Jan. 1, 2025

Citations

0
Atmospheric detection, prevalence, transmission, health and ecological consequences of antibiotic resistance genes and resistant bacteria: A comprehensive review DOI Creative Commons

Fan Liang,

Chun Chen,

Haijie Zhang

et al.

Emerging contaminants, Journal Year: 2025, Volume and Issue: unknown, P. 100514 - 100514

Published: May 1, 2025

Language: Английский

Citations

0
Exploring the frontier of microbiome biomarker discovery with artificial intelligence DOI Creative Commons
Liwen Xiao, Fangqing Zhao

National Science Review, Journal Year: 2024, Volume and Issue: 11(11)

Published: Sept. 13, 2024

Language: Английский

Citations

3
LineageFilter: Improved Proteotyping of Complex Samples Using Metaproteomics and Machine Learning DOI

Hamid Hachemi,

Jean Armengaud, Lucia Grenga

et al.

Journal of Proteome Research, Journal Year: 2024, Volume and Issue: 23(11), P. 5203 - 5208

Published: Oct. 19, 2024

Metaproteomics is a powerful tool to characterize how microbiota function by analyzing their proteic content tandem mass spectrometry. Given the complexity of these samples, accurately assessing taxonomical composition without prior information based solely on peptide sequences remains challenge. Here, we present LineageFilter, new python-based AI software for refined proteotyping complex samples using metaproteomics interpreted data and machine learning. tentative list taxa, abundances, scores associated with identified peptides, LineageFilter computes comprehensive set features each taxon at all ranks. Its machine-learning model then assesses likelihood taxon's presence features, enabling improved sample-specific database construction.

Language: Английский

Citations

2
DGCNN approach links metagenome-derived taxon and functional information providing insight into global soil organic carbon DOI Creative Commons
Laura‐Jayne Gardiner, Matthew M. Marshall,

Katharina Reusch

et al.

npj Biofilms and Microbiomes, Journal Year: 2024, Volume and Issue: 10(1)

Published: Oct. 26, 2024

Abstract Metagenomics can provide insight into the microbial taxa present in a sample and, through gene identification, functional potential of community. However, taxonomic and information are typically considered separately downstream analyses. We develop interpretable machine learning (ML) approaches for modelling metagenomic data, combining biological representation species with their associated genetically encoded functions within models. apply our methods to investigate soil organic carbon (SOC) stocks. First, we combine diverse global set microbiome samples environmental improving predictive performance classic ML providing new insights role microbiomes cycling. Our network analysis identified by classical models provides context ecological significance, extending focus beyond just most ‘hidden’ features model that might be less using standard explainability. next unique graph representations individual microbiomes, linking directly, enabling predictions SOC via deep convolutional neural networks (DGCNNs). Interpretation DGCNNs distinguished between importance key species, genome sequence differences, e.g., loss/acquisition, associate SOC. These identify several members Verrucomicrobiaceae family range functions, related carbohydrate metabolism, as important stocks effective predictors. relatively understudied but widespread organisms could play an dynamics globally.

Language: Английский

Citations

1