Using convolutional neural networks to explore the microbiome

Reiman, Derek; Dai, Yang

doi:10.1109/embc.2017.8037799

Cited by 38 publications

(26 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this way, the constructed matrices provide a better spatial and quantitative information in the metagenomic data to CNNs, compared to the vectors of relative microbial taxa abundances in an arbitrary order. Our preliminary analysis has revealed encouraging predictive ability of CNNs based on metagenomic data taken from different parts of body [11,17].…”

Section: Introductionmentioning

confidence: 84%

“…We have proposed a prototype of a novel architecture for convolution neural networks (CNNs) for the prediction of host phenotype from the microbial taxonomic abundance profiles [17]. CNNs were originally developed based on the visual cortex in images and have been successful in image processing and speech recognition [18].…”

Section: Introductionmentioning

confidence: 99%

“…To empower CNNs in metagenomic phenotype prediction, it is important to provide structural input with certain distance metric among the microbial taxas. In our preliminary work, we constructed a phylogenetic tree, a natural structure representing the relationship among the microbial taxa in the profiles [17]. The tree is embedded in a 2D matrix after populating with the observed relative abundance of microbial taxa in each individual profile.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PopPhy-CNN: A Phylogenetic Tree Embedded Architecture for Convolution Neural Networks for Metagenomic Data

Reiman

Dai

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation: Accurate prediction of the host phenotype from a metgenomic sample and identification of the associated bacterial markers are important in metagenomic studies. We introduce PopPhy-CNN, a novel convolutional neural networks (CNN) learning architecture that effectively exploits phylogentic structure in microbial taxa. PopPhy-CNN provides an input format of 2D matrix created by embedding the phylogenetic tree that is populated with the relative abundance of microbial taxa in a metagenomic sample. This conversion empowers CNNs to explore the spatial relationship of the taxonomic annotations on the tree and their quantitative characteristics in metagenomic data. Results: PopPhy-CNN is evaluated using three metagenomic datasets of moderate size. We show the superior performance of PopPhy-CNN compared to random forest, support vector machines, LASSO and a baseline 1D-CNN model constructed with relative abundance microbial feature vectors. In addition, we design a novel scheme of feature extraction from the learned CNN models and demonstrate the improved performance when the extracted features are used to train support vector machines. Conclusion: PopPhy-CNN is a novel deep learning framework for the prediction of host phenotype from metagenomic samples. PopPhy-CNN can efficiently train models and does not require excessive amount of data. PopPhy-CNN facilities not only retrieval of informative microbial taxa from the trained CNN models but also visualization of the taxa on the phynogenetic tree.

show abstract

Section: Introductionmentioning

confidence: 84%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PopPhy-CNN: A Phylogenetic Tree Embedded Architecture for Convolution Neural Networks for Metagenomic Data

Reiman

Dai

2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…PopPhy-CNN was originally designed by our group [25,26]. PopPhy-CNN explores relationship between taxa by treating a populated taxonomic tree as a type of image.…”

Section: Learning Modulementioning

confidence: 99%

“…Their approach, i.e., Ph-CNN, was reported to outperform linear SVMs, RF and a baseline fully connected MLPNN on synthetic data using gut metagenomic data from 222 inflammatory bowel disease (IBD) patients and 38 healthy subjects. Another CNN-based framework (PopPhy-CNN) was developed by our group by designing an input format of a 2D matrix representing the taxonomic tree populated with the relative abundance of microbial taxa in a metagenomic sample [25,26]. This conversion empowers CNNs to explore the spatial relationship of the taxonomic annotations on the Not applicable…”

mentioning

confidence: 99%

Meta-Signer: Metagenomic Signature Identifier based on Rank Aggregation of Features

Reiman

Sun

Dai

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background: The advance of metagenomic studies provides the opportunity to identify microbial taxa that are associated to 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 introduce 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, LASSO, Multi-Layer Perceptron Neural Networks, and our recently developed Convolutional Neural Network framework (PopPhy-CNN). Meta-Signer generates ranked taxa lists by training individual machine learning models over multiple training partitions and aggregates them into a single ranked list by an optimization procedure to represent the most informative and robust microbial features. Meta-Signer can rank taxa using two input forms of the data: the relative abundances of the original taxa and taxa from the populated taxonomic trees generated from the original taxa. The latter form allows the evaluation of the association of microbial features at different taxonomic levels to the disease, which is attributed to our novel model of PopPhy-CNN. Results: We evaluate Mega-Signer on five different human gut-microbiome datasets. We demonstrate that the features derived from Meta-Signer were more informative compared to those obtained from other available feature ranking methods. The highly ranked features are strongly supported by published literature. Conclusion: Meta-Signer is capable of deriving a robust set of microbial features at multiple taxonomic levels for the prediction of host phenotype. Meta-Signer is user-friendly and customizable, allowing users to explore their datasets quickly and efficiently. BackgroundRecent metagenomic studies of the gut microbiome have linked dysbiosis to many human diseases [1,2,3]. A metagenomic sample is typically represented by its microbial taxonomic composition using microbial taxa at one of the taxonomic levels, i.e., Super-kingdom, Phylum, Class, Order, Family, Genus, and Species. The identification of microbial taxa associated with the human disease has been one of important efforts in metagenomics data analysis [4]. Procedures used in various metagenomic studies use parametric or non-parametric statistical tests to detect differentially abundant individual taxa between disease and control groups [5,6,7,8,9]. These type of methods can potentially miss taxa with weak associations which can together present strong statistical association. In order to capture group association, several methods are proposed by exploring related taxa on a phylogenetic taxonomic tree. For example, a concept of variable fusion was introduced to bring two closely related taxa on the tree into a Lasso linear regression model [10]. OMiAT, a statistical framework, combines tests of all upper-and lower-level taxa to generate a microbiome comprehensive association mapping (MiC...

show abstract

Predicting microbiome compositions from species assemblages through deep learning

Michel‐Mata

Wang

Liu

et al. 2022

iMeta

View full text Add to dashboard Cite

Microbes can form complex communities that perform critical functions in maintaining the integrity of their environment or their hosts' wellbeing. Rationally managing these microbial communities requires improving our ability to predict how different species assemblages affect the final species composition of the community. However, making such a prediction remains challenging because of our limited knowledge of the diverse physical, biochemical, and ecological processes governing microbial dynamics. To overcome this challenge, we present a deep learning framework that automatically learns the map between species assemblages and community compositions from training data only, without knowing any of the above processes. First, we systematically validate our framework using synthetic data generated by classical population dynamics models. Then, we apply our framework to data from in vitro and in vivo microbial communities, including ocean and soil microbiota, Drosophila melanogaster gut microbiota, and human gut and oral microbiota. We find that our framework learns to perform accurate out‐of‐sample predictions of complex community compositions from a small number of training samples. Our results demonstrate how deep learning can enable us to understand better and potentially manage complex microbial communities.

show abstract

Using convolutional neural networks to explore the microbiome

Cited by 38 publications

References 9 publications

PopPhy-CNN: A Phylogenetic Tree Embedded Architecture for Convolution Neural Networks for Metagenomic Data

PopPhy-CNN: A Phylogenetic Tree Embedded Architecture for Convolution Neural Networks for Metagenomic Data

Meta-Signer: Metagenomic Signature Identifier based on Rank Aggregation of Features

Predicting microbiome compositions from species assemblages through deep learning

Contact Info

Product

Resources

About