Loading…
This event has ended. Visit the official site or create your own event on Sched.
Welcome to the Rocky 2021 Conference. Please click on the links below to access the Rocky website and the list of posters:

CONFERENCE RESOURCES
Rocky Website
Poster Presentation List without abstracts
Poster Presentation List with abstracts
Back To Schedule
Thursday, December 2 • 10:45am - 10:55am
OP 05 - Scalable estimation of microbial co-occurrence networks with Variational Autoencoders

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

OP 05
Scalable estimation of microbial co-occurrence networks with Variational Autoencoders

Presenting Author: James Morton, Simons Foundation

Co-Author(s):
Justin Silverman, Pennsylvania State University
Gleb Tikhonov, University of Helsinki
Harri Lähdesmäki, University of Aalto
Richard Bonneau, Simons Foundation

Abstract:Estimating microbe-microbe interactions is critical for understanding the ecological laws governing microbial communities. Rapidly decreasing sequencing costs have promised new opportunities to estimate microbe-microbe interactions across thousands of uncultured, unknown microbes. However, typical microbiome datasets are very high dimensional and accurate estimating of microbial correlations requires tens of thousands of samples, exceeding the computational capabilities of existing methodologies. Furthermore, the vast majority of microbiome studies collect compositional metagenomics data which enforces a negative bias when computing microbe-microbe correlations. The Multinomial Logistic Normal (MLN) distribution has been shown to be effective at inferring microbial-microbe correlations, however scalable Bayesian inference of these distributions has remained elusive. Here, we show that carefully constructed Variational Autoencoders (VAEs) augmented with the Isometric Log-ratio (ILR) transform can estimate low-rank MLN distributions thousands of times faster than existing methods. These VAEs can be trained on tens of thousands of samples, enabling co-occurrence inference across tens of thousands of microbes without regularization. The latent embedding distances computed from these VAEs are competitive with existing beta-diversity methods across a variety of mouse and human microbiome classification and regression tasks, with notable improvements on longitudinal studies.


Presenters
JM

James Morton

Simons Foundation


Thursday December 2, 2021 10:45am - 10:55am MST
Ballroom Salon 1