More Like this

1. Evolution-Informed Neural Networks for Microbiome Data Analysis

   https://doi.org/10.1109/BIBM52615.2021.9669640  

   Ito, Michael; Glaser, Yannik; Sadowski, Peter (December 2021, IEEE)

   Advances in metagenomic sequencing have provided an unprecedented view of the microbial world, but untangling the web of microbe interdependencies and the complex relationship between microbiome and host is a major challenge in biology. New statistical methods are needed to analyze metagenomic data and infer these relationships. Focusing on amplicon sequencing data, we present methods for leveraging phylogenetic information in deep neural network models and for transfer learning from large data repositories. This approach is demonstrated in experiments using data from the Earth Microbiome Project (EMP) and a dataset of 1500 samples from Waimea Valley on the island of Oahu, Hawaii. 

   more » « less
2. Direct covariance matrix estimation with compositional data

   https://doi.org/10.1214/24-EJS2222  

   Molstad, Aaron J; Ekvall, Karl Oskar; Suder, Piotr M (January 2024, Electronic Journal of Statistics)

   Compositional data arise in many areas of research in the natural and biomedical sciences. One prominent example is in the study of the human gut microbiome, where one can measure the relative abundance of many distinct microorganisms in a subject’s gut. Often, practitioners are interested in learning how the dependencies between microbes vary across distinct populations or experimental conditions. In statistical terms, the goal is to estimate a covariance matrix for the (latent) log-abundances of the microbes in each of the populations. However, the compositional nature of the data prevents the use of standard estimators for these covariance matrices. In this article, we propose an estimator of multiple covariance matrices which allows for information sharing across distinct populations of samples. Compared to some existing estimators, which estimate the covariance matrices of interest indirectly, our estimator is direct, ensures positive definiteness, and is the solution to a convex optimization problem. We compute our estimator using a proximal-proximal gradient descent algorithm. Asymptotic properties of our estimator reveal that it can perform well in high-dimensional settings. We show that our method provides more reliable estimates than competitors in an analysis of microbiome data from subjects with myalgic encephalomyelitis/chronic fatigue syndrome and through simulation studies. 

   more » « less
3. TADA: phylogenetic augmentation of microbiome samples enhances phenotype classification

   https://doi.org/10.1093/bioinformatics/btz394  

   Sayyari, Erfan; Kawas, Ban; Mirarab, Siavash (July 2019, Bioinformatics)

   Abstract MotivationLearning associations of traits with the microbial composition of a set of samples is a fundamental goal in microbiome studies. Recently, machine learning methods have been explored for this goal, with some promise. However, in comparison to other fields, microbiome data are high-dimensional and not abundant; leading to a high-dimensional low-sample-size under-determined system. Moreover, microbiome data are often unbalanced and biased. Given such training data, machine learning methods often fail to perform a classification task with sufficient accuracy. Lack of signal is especially problematic when classes are represented in an unbalanced way in the training data; with some classes under-represented. The presence of inter-correlations among subsets of observations further compounds these issues. As a result, machine learning methods have had only limited success in predicting many traits from microbiome. Data augmentation consists of building synthetic samples and adding them to the training data and is a technique that has proved helpful for many machine learning tasks. ResultsIn this paper, we propose a new data augmentation technique for classifying phenotypes based on the microbiome. Our algorithm, called TADA, uses available data and a statistical generative model to create new samples augmenting existing ones, addressing issues of low-sample-size. In generating new samples, TADA takes into account phylogenetic relationships between microbial species. On two real datasets, we show that adding these synthetic samples to the training set improves the accuracy of downstream classification, especially when the training data have an unbalanced representation of classes. Availability and implementationTADA is available at https://github.com/tada-alg/TADA. Supplementary informationSupplementary data are available at Bioinformatics online. 

   more » « less
4. Leveraging Scheme for Cross-Study Microbiome Machine Learning Prediction and Feature Evaluations

   https://doi.org/10.3390/bioengineering10020231  

   Song, Kuncheng; Zhou, Yi-Hui (February 2023, Bioengineering)

   The microbiota has proved to be one of the critical factors for many diseases, and researchers have been using microbiome data for disease prediction. However, models trained on one independent microbiome study may not be easily applicable to other independent studies due to the high level of variability in microbiome data. In this study, we developed a method for improving the generalizability and interpretability of machine learning models for predicting three different diseases (colorectal cancer, Crohn’s disease, and immunotherapy response) using nine independent microbiome datasets. Our method involves combining a smaller dataset with a larger dataset, and we found that using at least 25% of the target samples in the source data resulted in improved model performance. We determined random forest as our top model and employed feature selection to identify common and important taxa for disease prediction across the different studies. Our results suggest that this leveraging scheme is a promising approach for improving the accuracy and interpretability of machine learning models for predicting diseases based on microbiome data. 

   more » « less
5. Organelles in the ointment: improved detection of cryptic mitochondrial reads resolves many unknown sequences in cross-species microbiome analyses

   https://doi.org/10.1093/ismeco/ycae114  

   Sonett, Dylan; Brown, Tanya; Bengtsson-Palme, Johan; Padilla-Gamiño, Jacqueline_L; Zaneveld, Jesse_R (September 2024, ISME Communications)

   Abstract The genomes of mitochondria and chloroplasts contain ribosomal RNA (rRNA) genes, reflecting their ancestry as free-living bacteria. These organellar rRNAs are often amplified in microbiome studies of animals and plants. If identified, they can be discarded, merely reducing sequencing depth. However, we identify certain high-abundance organeller RNAs not identified by common pipelines, which may compromise statistical analysis of microbiome structure and diversity. We quantified this by reanalyzing 7459 samples from seven 16S rRNA studies, including microbiomes from 927 unique animal genera. We find that under-annotation of cryptic mitochondrial and chloroplast reads affects multiple of these large-scale cross-species microbiome comparisons, and varies between host species, biasing comparisons. We offer a straightforward solution: supplementing existing taxonomies with diverse organelle rRNA sequences. This resolves up to 97% of unique unclassified sequences in some entire studies as mitochondrial (14% averaged across all studies), without increasing false positive annotations in mitochondria-free mock communities. Improved annotation decreases the proportion of unknown sequences by ≥10-fold in 2262 of 7459 samples (30%), spanning five of seven major studies examined. We recommend leveraging organelle sequence diversity to better identify organelle gene sequences in microbiome studies, and provide code, data resources and tutorials that implement this approach. 

   more » « less