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

Yu, Philip S.; Reiman, Derek; Dai, Yang; Perkins, David L.

doi:10.1371/journal.pcbi.1006693

Cited by 29 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning techniques are actively applied to microbiome research [41][42][43][44][45][46][47][48][49] such as for classifying samples that shifted to a diseased state 50 , predicting infection complications in immunocompromised patients 51 , or predicting the temporal or spatial evolution of certain species collection 52,53 . However, to the best of our knowledge, the potential of deep learning for predicting the effect of changing species collection was not explored nor validated before.…”

Section: Discussionmentioning

confidence: 99%

Predicting microbiome compositions from species assemblages through deep learning

Michel‐Mata

Wang

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Microbes can form complex communities that perform critical functions in maintaining the integrity of their environment1,2 or the well-being of their hosts3-6. Successfully managing these microbial communities requires the ability to predict the community composition based on the species assemblage7. However, making such a prediction remains challenging because of our limited knowledge of the diverse physical8, biochemical9, and ecological10,11 processes governing the microbial dynamics. To overcome this challenge, here we present a deep learning framework that automatically learns the map between species assemblages and community compositions from training data. First, we systematically validate our framework using synthetic data generated by classical population dynamics models. Then, we apply it to experimental data of both in vitro and in vivo communities, including ocean and soil microbial communities12,13, Drosophila melanogaster gut microbiota14, and human gut and oral microbiota15. Our results demonstrate how deep learning can enable us to understand better and potentially manage complex microbial communities.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting microbiome compositions from species assemblages through deep learning

Michel‐Mata

Wang

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…An expanding group of 'omics' technologies, responsible for many recent advances, are now moving from stand-alone data-generating vehicles to fully integrated, systems biology-oriented 'meta'-technologies [100]. Future and ongoing efforts will no doubt improve current bioinformatics tools for data interrogation, integration and processing, with holistic predictions being facilitated through machine learning and artificial intelligence [101][102][103].…”

Section: New Discovery and Research Methodologiesmentioning

confidence: 99%

Shaping the Future of Probiotics and Prebiotics

Cunningham¹,

Azcárate-Peril

Barnard³

et al. 2021

Trends in Microbiology

348

203

View full text Add to dashboard Cite

Recent and ongoing developments in microbiome science are enabling new frontiers of research for probiotics and prebiotics. Novel types, mechanisms, and applications currently under study have the potential to change scientific understanding as well as nutritional and healthcare applications of these interventions. The expansion of related fields of microbiome-targeted interventions, and an evolving landscape for implementation across regulatory, policy, prescriber, and consumer spheres, portends an era of significant change. In this review we examine recent, emerging, and anticipated trends in probiotic and prebiotic science, and create a vision for broad areas of developing influence in the field. HighlightsAn expanding range of candidate probiotic species and prebiotic substrates is emerging to address newly elucidated data-driven microbial niches and host targets.Overlapping with, and adjacent to, the probiotic and prebiotic fields, new variants of microbiome-modulating interventions are developing, including synbiotics, postbiotics, microbial consortia, live biotherapeutic products, and genetically modified organisms, with renewed interest in polyphenols, fibres, and fermented foods.

show abstract

“…This is motivated by the findings that a microbial signature for the host phenotype may be complex, involving simultaneous over-and under-representations of multiple microbial taxa potentially interacting with each other. Classical ML models, such as Random Forest (RF), Logistic Regression and Support Vector Machines (SVMs), and deep neural networks (DNNs) have been applied to host phenotype prediction using microbial abundance features [16][17][18][19][20][21][22] .…”

Section: Introductionmentioning

confidence: 99%

Meta-Signer: Metagenomic Signature Identifier based onrank aggregation of features

2021

Self Cite

View full text Add to dashboard Cite

The advance of metagenomic studies provides the opportunity to identify microbial taxa that are associated with human diseases. Multiple methods exist for the association analysis. However, the results could be inconsistent, presenting challenges in interpreting the host-microbiome interactions. To address this issue, we develop Meta-Signer, a novel Metagenomic Signature Identifier tool based on rank aggregation of features identified from multiple machine learning models including Random Forest, Support Vector Machines, Logistic Regression, and Multi-Layer Perceptron Neural Networks. Meta-Signer generates ranked taxa lists by training individual machine learning models over multiple training partitions and aggregates the ranked lists into a single list by an optimization procedure to represent the most informative and robust microbial features. A User will receive speedy assessment on the predictive performance of each ma-chine learning model using different numbers of the ranked features and determine the final models to be used for evaluation on external datasets. Meta-Signer is user-friendly and customizable, allowing users to explore their datasets quickly and efficiently.

show abstract

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

Cited by 29 publications

References 36 publications

Predicting microbiome compositions from species assemblages through deep learning

Predicting microbiome compositions from species assemblages through deep learning

Shaping the Future of Probiotics and Prebiotics

Meta-Signer: Metagenomic Signature Identifier based onrank aggregation of features

Contact Info

Product

Resources

About