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

Abstract

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.

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

“…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.…”

“…The novel procedure to extract features from CNNs was developed in our previous learning framework PopPhy-CNN [26]. We included the details on the full algorithm of feature importance scoring in Additional File 1 ( Fig.…”

“…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…”

“…tree and their quantitative characteristics in metagenomic data. PopPhy-CNN was shown competitive using nine metagenomic datasets of moderate size including the IBD dataset [26].…”

Multiclass Disease Classification from Microbial Whole-Community Metagenomes using Graph Convolutional Neural Networks

“…Reiman et al implemented a CNN by embedding phylogenetic trees into R 2 and used two-dimensional convolutional layers to construct a body-site classifier. 4 Fioravanti et al developed a model to diagnose inflammatory bowel disease (IBD) by projecting samples into a two-dimensional space using Mul-tiDimensional Scaling with the patristic distance between phylogenetic trees as the distance metric. 5 Both papers mapped phylogenetic data to a Euclidean domain to perform convolutions instead of operating in the original tree topology, as we do in this study.…”