Deep Learning Enables Design of Multifunctional Synthetic Human Gut Microbiome Dynamics
Authors:
- Alfred O. HeroAHAlfred O. Hero
- Ophelia S VenturelliOVOphelia S Venturelli
Preprint
Abstract
Predicting the dynamics and functions of microbiomes constructed from the bottom-up is a key challenge in exploiting them to our benefit. Current ordinary differential equation-based models fail to capture complex behaviors that fall outside of a predetermined ecological theory and do not scale well with increasing community complexity and in considering multiple functions. We develop and apply a long short-term memory (LSTM) framework to advance our understanding of community assembly and health-relevant metabolite production using a synthetic human gut community. A mainstay of deep learning, the LSTM learns a high dimensional data-driven non-linear dynamical system model used to design communities with desired metabolite profiles. We show that the LSTM model can outperform the widely used generalized Lotka-Volterra model. We build methods decipher microbe-microbe and microbe-metabolite interactions from an otherwise black-box model. These methods highlight that Actinobacteria, Firmicutes and Proteobacteria are significant drivers of metabolite production whereas Bacteroides shape community dynamics. We use the LSTM model to navigate a large multidimensional functional landscape to identify communities with unique health-relevant metabolite profiles and temporal behaviors. In sum, the accuracy of the LSTM model can be exploited for experimental planning and to guide the design of synthetic microbiomes with target dynamic functions.Keywords
All Related Versions
- Published version: eLife, 11.
This publication has 51 references indexed in Scilit:
- Fitting Imidazole 1H NMR Titration Data to the Henderson–Hasselbalch EquationJournal of Chemical Education, 2012
- Eating For Two: How Metabolism Establishes Interspecies Interactions in the GutCell Host & Microbe, 2011
- Introducing mothur: Open-Source, Platform-Independent, Community-Supported Software for Describing and Comparing Microbial CommunitiesApplied and Environmental Microbiology, 2009
- Microbial Interactions within a Cheese Microbial CommunityApplied and Environmental Microbiology, 2008
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Patterning and short-term predictions of benthic macroinvertebrate community dynamics by using a recurrent artificial neural networkEcological Modelling, 2001
- Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent artificial neural networkEcological Modelling, 2001
- Data clusteringACM Computing Surveys, 1999
- Long Short-Term MemoryNeural Computation, 1997
- Cluster validation using graph theoretic conceptsPattern Recognition, 1997