Scalable Estimation of Microbial Co-Occurrence Networks with Variational Autoencoders

• Activity Number: 360 - New Areas in Complex High-Dimensional Data Analysis
• Type: Invited
• Date/Time: Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
• Sponsor: International Indian Statistical Association
• Author(s): James Morton* and Justin Silverman and Gleb Tikhonov and Harri Lähdesmäki and Richard Bonneau
• Companies: National Institute of Child Health and Development and Pennsylvania State University and University of Helsinki and University of Aalto and Simons Foundation
• Keywords: variational autoencoders; compositional data analysis; multinomial logistic normal; microbiome

Abstract

Elucidating microbial interactions are key for understanding the ecological laws governing microbial communities. High-throughput sequencing promises new opportunities to observe interactions across thousands of uncultured, unknown microbes. However, microbiome datasets are high dimensional and accurate estimation of microbial correlations requires thousands of samples, exceeding the computational capabilities of existing methodologies. Furthermore, sequencing count data is compositional which confounds microbial correlation inference. The Multinomial Logistic Normal (MLN) distribution has been shown to be effective at inferring microbial correlations, but scalable estimation remains challenging. We show that Variational Autoencoders (VAEs) augmented with the ILR transform can estimate MLN distributions thousands of times faster than existing methods. These VAEs can be trained on thousands of samples, enabling co-occurrence inference across thousands of microbes. These VAEs are competitive with existing beta-diversity methods across a variety of mouse and human microbiome classification tasks, with improvements on longitudinal studies.