A0622
Title: Mbtransfer: Microbiome intervention analysis using transfer functions and mirror statistics
Authors: Kris Sankaran - University of Wisconsin (United States) [presenting]
Abstract: Time series studies of microbiome interventions provide valuable data about microbial ecosystem structure. Unfortunately, existing models of microbial community dynamics have limited temporal memory and expressivity, relying on Markov or linearity assumptions. To address this, a new class of models is introduced based on transfer functions. These models learn impulse responses, capturing the potentially delayed effects of environmental changes on the microbial community. This allows the simulation of trajectories under hypothetical interventions and the selection of significantly perturbed taxa with false discovery rate guarantees. Through simulations, it is shown that the approach effectively reduces forecasting errors compared to strong baselines and accurately pinpoints taxa of interest. Case studies highlight the interpretability of the resulting differential response trajectories.
