Machine Learning Meta-analysis of Large Metagenomic Datasets: Tools and Biological Insights

By Edoardo Pasolli, Duy Tin Truong, Faizan Malik, Levi Waldron, Nicola Segata. 2016

568 citations recorded by the source corpus.

Shotgun metagenomic analysis of the human associated microbiome provides a rich set of microbial features for prediction and biomarker discovery in the context of human diseases and health conditions. However, the use of such high-resolution microbial features presents new challenges, and validated computational tools for learning tasks are lacking. Moreover, classification rules have scarcely been validated in independent studies, posing questions about the generality and generalization of disease-predictive models across cohorts. In this paper, we comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of the strength of potential microbiome-phenotype associations. We develop a computational framework for prediction tasks using quantitative microbiome profiles, including species-level relative abundances and presence of strain-specific markers. A comprehensive meta-analysis, with particular emphasis on generalization across cohorts, was performed in a collection of 2424 publicly available metagenomic samples from eight large-scale studies. Cross-validation revealed good disease-prediction capabilities, which were in general improved by feature selection and use of strain-specific markers instead of species-level taxonomic abundance. In cross-study analysis, models transferred between studies were in some cases less accurate than models tested by within-study cross-validation. Interestingly, the addition of healthy (control) samples from other studies to training sets improved disease prediction capabilities. Some microbial species (most notably Streptococcus anginosus) seem to characterize general dysbiotic states of the microbiome rather than connections with a specific disease. Our results in modelling features of the “healthy” microbiome can be considered a first step toward defining general microbial dysbiosis. The software framework, microbiome profiles, and metadata for thousands of samples are publicly available at http://segatalab.cibio.unitn.it/tools/metaml.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Also, researchers have looked into how feature selection can improve classification [237,239], and techniques have been proposed that are classifier-independent [240,241].”
QIIME 2 Enables Comprehensive End‐to‐End Analysis of Diverse Microbiome Data and Comparative Studies with Publicly Available Data (2020, background): “…(GSC) has created the “Minimum Information about any (x) Sequence” (MIxS) and “Minimum Information about a MARKer gene Sequence” (MIMARKS) specifications (Yilmaz et al., 2011) as well as 15 “environmental packages” that extend and refine these standards for samples from environments ranging from…”
Tracking microbial colonization in fecal microbiota transplantation experiments via genome-resolved metagenomics (2017, methodology): “We used 151 Human Microbiome Project (HMP) gut metagenomes [50] to estimate the detection of our MAGs and to compare the taxonomic profiles of our metagenomes in the context of the HMP participants.”
Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment (2021, methodology): “Pasolli et al. (2016) used the SVM, RF classiﬁers, LASSO and elastic net regularized multiple logistic regression, Neural Networks and Bayesian logistic regression, and assessed the prediction power of metagenomic data in linking the gut microbiome with disease states (Pasolli et al., 2016).”
Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3 (2020, methodology): “We used MetAML (Pasolli et al., 2016) to feed species-level and pathway-level relative abundances to a Random Forest model (Breiman, 2001).”
The Human Gut Microbiome: From Association to Modulation. (2018, background): “Two recent meta-analyses of microbiome-disease association studies found that between-study variation required explicit or implicit batch effect correction (Duvallet et al., 2017; Pasolli et al., 2016).”
Extensive impact of non-antibiotic drugs on human gut bacteria (2018, unknown): “This suggests that human-targeted drugs have an even larger impact to the gut microbiome with key species related to healthy status 15, such as major butyrate-(E. rectale, R. intestinalis, Coprococcus comes) and propionate-producers (B. vulgatus, Prevotella copri, Blautia obeum) 16, and enterotype…”
Microbial indicators as a diagnostic tool for assessing water quality and climate stress in coral reef ecosystems (2017, background): “Machine learning is a powerful tool and a current state-ofthe-art approach to identify dysbiosis of the human microbiome and to predict human diseases (Pasolli et al. 2016).”