Abstract
BackgroundTechnological advances in next-generation sequencing (NGS) and chromatographic assays [e.g., liquid chromatography mass spectrometry (LC-MS)] have made it possible to identify thousands of microbe and metabolite species, and to measure their relative abundance. In this paper, we propose a sparse neural encoder-decoder network to predict metabolite abundances from microbe abundances.ResultsUsing paired data from a cohort of inflammatory bowel disease (IBD) patients, we show that our neural encoder-decoder model outperforms linear univariate and multivariate methods in terms of accuracy, sparsity, and stability. Importantly, we show that our neural encoder-decoder model is not simply a black box designed to maximize predictive accuracy. Rather, the network’s hidden layer (i.e., the latent space, comprised only of sparsely weighted microbe counts) actually captures key microbe-metabolite relationships that are themselves clinically meaningful. Although this hidden layer is learned without any knowledge of the patient’s diagnosis, we show that the learned latent features are structured in a way that predicts IBD and treatment status with high accuracy.ConclusionsBy imposing a non-negative weights constraint, the network becomes a directed graph where each downstream node is interpretable as the additive combination of the upstream nodes. Here, the middle layer comprises distinct microbe-metabolite axes that relate key microbial biomarkers with metabolite biomarkers. By pre-processing the microbiome and metabolome data using compositional data analysis methods, we ensure that our proposed multi-omics workflow will generalize to any pair of -omics data. To the best of our knowledge, this work is the first application of neural encoder-decoders for the interpretable integration of multi-omics biological data.
Highlights
Technological advances in next-generation sequencing (NGS) and chromatographic assays [e.g., liquid chromatography mass spectrometry (LC-MS)] have made it possible to identify thousands of microbe and metabolite species, and to measure their relative abundance
The network’s hidden layer captures key microbe-metabolite relationships that are themselves clinically meaningful. This hidden layer is learned without any knowledge of the patient’s diagnosis, we show that the learned latent features are structured in a way that predicts inflammatory bowel disease (IBD) and treatment status with high accuracy
We replaced the remaining zeros with a very small number using the cmultRepl zero-replacement function implemented in zCompositions, an imputation tool which explicitly models the relative nature of NGS and LC-MS data [23]
Summary
Technological advances in next-generation sequencing (NGS) and chromatographic assays [e.g., liquid chromatography mass spectrometry (LC-MS)] have made it possible to identify thousands of microbe and metabolite species, and to measure their relative abundance. By applying NGS and LC-MS on fecal samples, one gains two complementary “views” on the complex ecosystem in which gut bacteria produce, consume, and induce the metabolic milieu. These data modalities have each advanced our understanding of elusive gut pathologies like inflammatory bowel disease [1], and are increasingly being collected in parallel [2,3,4]. The inflammation in IBD does not have an infectious origin, patients with CD and UC exhibit an irregular gut microbiome, having less bacterial diversity, a depletion of healthy bacteria, and an excess of unhealthy bacteria [5, 9, 10] These changes have been partly attributed to an abnormal immune response to benign commensual organisms [5]. Marchesi et al found low levels of short chain fatty acids in IBD fecal samples [13], which may be related to changes in how the gut bacteria metabolize carbohydrates [1]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call