Efficient and accurate inference of microbial trajectories from longitudinal count data
Joseph, T. A.; Pasarkar, A. P.; Pe'er, I.
Show abstract
The recently completed second phase of the Human Microbiome Project has highlighted the relationship between dynamic changes in the microbiome and disease, motivating new microbiome study designs based on longitudinal sampling. Yet, analysis of such data is hindered by presence of technical noise, high dimensionality, and data sparsity. To address these challenges, we propose LUMINATE (LongitUdinal Microbiome INference And zero deTEction), a fast and accurate method for inferring relative abundances from noisy read count data. We demonstrate on synthetic data that LUMINATE is orders of magnitude faster than current approaches, with better or similar accuracy. This translates to feasibility of analyzing data at the requisite dimensionality for current studies. We further show that LUMINATE can accurately distinguish biological zeros, when a taxon is absent from the community, from technical zeros, when a taxon is below the detection threshold. We conclude by demonstrating the utility of LUMINATE for downstream analysis by using estimates of latent relative abundances to fit the parameters of a dynamical system, leading to more accurate predictions of community dynamics. Code availabilityhttps://github.com/tyjo/luminate
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Linear-regression-based algorithms can succeed at identifying microbial functional groups despite the nonlinearity of ecological function 96%
- Bayesian inference of relative fitness on high-throughput pooled competition assays 95%
- Estimating repeat spectra and genome length from low-coverage genome skims with RESPECT 95%
Similar papers in this journal
Similar papers in this journal
- Common to rare transfer learning (CORAL) enables inference and prediction for a quarter million rare Malagasy arthropods 95%
- An analytical framework for interpretable and generalizable 'quasilinear' single-cell data analysis 95%
- Deep generative modeling of transcriptional dynamics for RNA velocity analysis in single cells 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.