Scaling DEPP phylogenetic placement to ultra-large reference trees: a tree-aware ensemble approach.

MOTIVATION: Phylogenetic placement of a query sequence on a backbone tree is increasingly used across biomedical sciences to identify the content of a sample from its DNA content. The accuracy of such analyses depends on the density of the backbone tree, making it crucial that placement methods scale to very large trees. Moreover, a new paradigm has been recently proposed to place sequences on the species tree using single-gene data. The goal is to better characterize the samples and to enable combined analyses of marker-gene (e.g., 16S rRNA gene amplicon) and genome-wide data. The recent method DEPP enables performing such analyses using metric learning. However, metric learning is hampered by a need to compute and save a quadratically growing matrix of pairwise distances during training. Thus, the training phase of DEPP does not scale to more than roughly 10 000 backbone species, a problem that we faced when trying to use our recently released Greengenes2 (GG2) reference tree containing 331 270 species. RESULTS: This paper explores divide-and-conquer for training ensembles of DEPP models, culminating in a method called C-DEPP. While divide-and-conquer has been extensively used in phylogenetics, applying divide-and-conquer to data-hungry machine-learning methods needs nuance. C-DEPP uses carefully crafted techniques to enable quasi-linear scaling while maintaining accuracy. C-DEPP enables placing 20 million 16S fragments on the GG2 reference tree in 41 h of computation. AVAILABILITY AND IMPLEMENTATION: The dataset and C-DEPP software are freely available at https://github.com/yueyujiang/dataset_cdepp/.

DEPP: Deep Learning Enables Extending Species Trees using Single Genes.

Placing new sequences onto reference phylogenies is increasingly used for analyzing environmental samples, especially microbiomes. Existing placement methods assume that query sequences have evolved under specific models directly on the reference phylogeny. For example, they assume single-gene data (e.g., 16S rRNA amplicons) have evolved under the GTR model on a gene tree. Placement, however, often has a more ambitious goal: extending a (genome-wide) species tree given data from individual genes without knowing the evolutionary model. Addressing this challenging problem requires new directions. Here, we introduce Deep-learning Enabled Phylogenetic Placement (DEPP), an algorithm that learns to extend species trees using single genes without prespecified models. In simulations and on real data, we show that DEPP can match the accuracy of model-based methods without any prior knowledge of the model. We also show that DEPP can update the multilocus microbial tree-of-life with single genes with high accuracy. We further demonstrate that DEPP can combine 16S and metagenomic data onto a single tree, enabling community structure analyses that take advantage of both sources of data. [Deep learning; gene tree discordance; metagenomics; microbiome analyses; neural networks; phylogenetic placement.].

Generation of accurate, expandable phylogenomic trees with uDance.

Phylogenetic trees provide a framework for organizing evolutionary histories across the tree of life and aid downstream comparative analyses such as metagenomic identification. Methods that rely on single-marker genes such as 16S rRNA have produced trees of limited accuracy with hundreds of thousands of organisms, whereas methods that use genome-wide data are not scalable to large numbers of genomes. We introduce updating trees using divide-and-conquer (uDance), a method that enables updatable genome-wide inference using a divide-and-conquer strategy that refines different parts of the tree independently and can build off of existing trees, with high accuracy and scalability. With uDance, we infer a species tree of roughly 200,000 genomes using 387 marker genes, totaling 42.5 billion amino acid residues.

Greengenes2 unifies microbial data in a single reference tree.

Studies using 16S rRNA and shotgun metagenomics typically yield different results, usually attributed to PCR amplification biases. We introduce Greengenes2, a reference tree that unifies genomic and 16S rRNA databases in a consistent, integrated resource. By inserting sequences into a whole-genome phylogeny, we show that 16S rRNA and shotgun metagenomic data generated from the same samples agree in principal coordinates space, taxonomy and phenotype effect size when analyzed with the same tree.

Multi-level analysis of the gut-brain axis shows autism spectrum disorder-associated molecular and microbial profiles.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by heterogeneous cognitive, behavioral and communication impairments. Disruption of the gut-brain axis (GBA) has been implicated in ASD although with limited reproducibility across studies. In this study, we developed a Bayesian differential ranking algorithm to identify ASD-associated molecular and taxa profiles across 10 cross-sectional microbiome datasets and 15 other datasets, including dietary patterns, metabolomics, cytokine profiles and human brain gene expression profiles. We found a functional architecture along the GBA that correlates with heterogeneity of ASD phenotypes, and it is characterized by ASD-associated amino acid, carbohydrate and lipid profiles predominantly encoded by microbial species in the genera Prevotella, Bifidobacterium, Desulfovibrio and Bacteroides and correlates with brain gene expression changes, restrictive dietary patterns and pro-inflammatory cytokine profiles. The functional architecture revealed in age-matched and sex-matched cohorts is not present in sibling-matched cohorts. We also show a strong association between temporal changes in microbiome composition and ASD phenotypes. In summary, we propose a framework to leverage multi-omic datasets from well-defined cohorts and investigate how the GBA influences ASD.

Learning Hyperbolic Embedding for Phylogenetic Tree Placement and Updates.

Phylogenetic placement, used widely in ecological analyses, seeks to add a new species to an existing tree. A deep learning approach was previously proposed to estimate the distance between query and backbone species by building a map from gene sequences to a high-dimensional space that preserves species tree distances. They then use a distance-based placement method to place the queries on that species tree. In this paper, we examine the appropriate geometry for faithfully representing tree distances while embedding gene sequences. Theory predicts that hyperbolic spaces should provide a drastic reduction in distance distortion compared to the conventional Euclidean space. Nevertheless, hyperbolic embedding imposes its own unique challenges related to arithmetic operations, exponentially-growing functions, and limited bit precision, and we address these challenges. Our results confirm that hyperbolic embeddings have substantially lower distance errors than Euclidean space. However, these better-estimated distances do not always lead to better phylogenetic placement. We then show that the deep learning framework can be used not just to place on a backbone tree but to update it to obtain a fully resolved tree. With our hyperbolic embedding framework, species trees can be updated remarkably accurately with only a handful of genes.

Fast and accurate distance-based phylogenetic placement using divide and conquer.

Phylogenetic placement of query samples on an existing phylogeny is increasingly used in molecular ecology, including sample identification and microbiome environmental sampling. As the size of available reference trees used in these analyses continues to grow, there is a growing need for methods that place sequences on ultra-large trees with high accuracy. Distance-based placement methods have recently emerged as a path to provide such scalability while allowing flexibility to analyse both assembled and unassembled environmental samples. In this study, we introduce a distance-based phylogenetic placement method, APPLES-2, that is more accurate and scalable than existing distance-based methods and even some of the leading maximum-likelihood methods. This scalability is owed to a divide-and-conquer technique that limits distance calculation and phylogenetic placement to parts of the tree most relevant to each query. The increased scalability and accuracy enables us to study the effectiveness of APPLES-2 for placing microbial genomes on a data set of 10,575 microbial species using subsets of 381 marker genes. APPLES-2 has very high accuracy in this setting, placing 97% of query genomes within three branches of the optimal position in the species tree using 50 marker genes. Our proof-of-concept results show that APPLES-2 can quickly place metagenomic scaffolds on ultra-large backbone trees with high accuracy as long as a scaffold includes tens of marker genes. These results pave the path for a more scalable and widespread use of distance-based placement in various areas of molecular ecology.