Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Methods to Assess Microbial Communities01:19

Methods to Assess Microbial Communities

Microbial communities, comprising bacteria, archaea, and eukaryotic microorganisms, inhabit diverse ecosystems and play crucial roles in environmental and biological processes. Their diversity is defined by three main parameters: species richness (the number of distinct species), species abundance (the relative quantity of each species), and species evenness (how uniformly individual species are distributed in various locations). These factors together shape the structure and ecological balance...
Methods to Assess Microbial Populations01:30

Methods to Assess Microbial Populations

Assessing microbial populations is crucial for understanding microbial roles in health, ecology, and industry. Various complementary techniques—both culture-based and molecular—enable detailed analysis of microbial abundance, diversity, and function.Viable Plate CountThe viable plate count is a traditional culture-based method used to estimate the number of living microbes in a sample. After serial dilution, the sample is spread onto nutrient agar plates. Each viable cell forms a visible...
Microbial Growth Measurement: Indirect Methods01:27

Microbial Growth Measurement: Indirect Methods

Estimating microbial growth is essential for understanding population dynamics and environmental adaptations. Indirect methods provide valuable insights by measuring parameters such as turbidity, metabolic activity, and biomass, enabling efficient and reproducible assessments.During exponential growth, microbial cells scatter light proportionally to their biomass, a principle used in turbidity measurements. About one million cells per milliliter produce detectable scattering, which a...
Modern Molecular Taxonomy01:29

Modern Molecular Taxonomy

Advancements in molecular biology have revolutionized the identification and characterization of bacteria, with multiple methods leveraging DNA sequencing for enhanced precision. As sequencing technologies improve and costs decline, these approaches are increasingly used in clinical, environmental, and evolutionary studies.Multilocus Sequence Typing (MLST) examines several housekeeping genes, essential chromosomal genes encoding cellular functions, to distinguish strains. Approximately...
Phylogenetic Species Concept in Microbiology01:22

Phylogenetic Species Concept in Microbiology

The phylogenetic species concept (PSC) is a framework used to delineate species based on evolutionary relationships, emphasizing shared ancestry and diagnosable genetic traits. Unlike morphological or biological species concepts, the PSC is particularly advantageous for microbial taxonomy, where traditional reproductive or phenotypic criteria often fall short due to the prevalence of asexual reproduction, minimal morphological differentiation, and widespread horizontal gene transfer among...
Microbial Growth Measurement: Direct Methods01:23

Microbial Growth Measurement: Direct Methods

Direct methods for measuring microbial populations in a culture are essential tools in microbiology, providing quantitative data for various applications. Among these, microscopic counts, plate counts, and serial dilution are widely used techniques, each with unique principles and applications.Microscopic CountsMicroscopic counting involves the use of a Petroff-Hausser chamber, a specialized microscope slide with a grid and defined depth. By observing a liquid culture under a microscope,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Bacterial Communities Identified by Standard Culture and 16S rRNA Amplicon Sequencing in Ophthalmic Preservative-Free Dexamethasone SP Used in Canine Cataract Surgery.

Veterinary ophthalmology·2026
Same author

Stroke-induced gut microbiome dysbiosis accelerates Alzheimer's disease progression.

Journal of cerebral blood flow and metabolism : official journal of the International Society of Cerebral Blood Flow and Metabolism·2026
Same author

Eco-tank Housing Maintains Wild-Type Microbiota and Rewilds the Laboratory Mouse Gut Microbiome to Restore Natural Immune Tone.

bioRxiv : the preprint server for biology·2026
Same author

MeLSI: Metric Learning for Statistical Inference in Microbiome Community Composition Analysis.

bioRxiv : the preprint server for biology·2026
Same author

Exploring the Interplay Between Fatigue and the Oral Microbiome: A Longitudinal Approach.

Microorganisms·2025
Same author

Biological and technical variability in mouse microbiota analysis and implications for sample size determination.

Lab animal·2025

Related Experiment Video

Updated: Jun 30, 2026

Divergence of Root Microbiota in Different Habitats based on Weighted Correlation Networks
09:49

Divergence of Root Microbiota in Different Habitats based on Weighted Correlation Networks

Published on: September 25, 2021

MeLSI: Metric Learning for Statistical Inference in microbiome community composition analysis.

Nathan Bresette1,2, Aaron C Ericsson3,4, Carter Woods1

  • 1Roy Blunt NextGen Precision Health, University of Missouri, Columbia, Missouri, USA.

Msystems
|June 29, 2026
PubMed
Summary

Metric Learning for Statistical Inference (MeLSI) enhances microbiome analysis by learning data-adaptive distance metrics. This approach improves detection of subtle community shifts and identifies key microbial drivers, unlike fixed metrics.

Keywords:
PERMANOVAbeta diversitycommunity compositiondistance metricsmetric learningmicrobiome analysispermutation testing

More Related Videos

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing
11:22

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

Related Experiment Videos

Last Updated: Jun 30, 2026

Divergence of Root Microbiota in Different Habitats based on Weighted Correlation Networks
09:49

Divergence of Root Microbiota in Different Habitats based on Weighted Correlation Networks

Published on: September 25, 2021

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing
11:22

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

Area of Science:

  • Microbiome research
  • Computational biology
  • Statistical inference

Background:

  • Current microbiome beta diversity analysis uses fixed distance metrics (e.g., Bray-Curtis, Jaccard) that treat all taxa equally.
  • This "one-size-fits-all" approach may overlook subtle, biologically significant patterns in complex microbial communities.
  • Identifying key microbial taxa driving community differences is crucial for biomarker discovery and understanding disease states.

Purpose of the Study:

  • To introduce Metric Learning for Statistical Inference (MeLSI), a novel machine learning framework for data-adaptive distance metric learning in microbiome analysis.
  • To develop a statistically rigorous method that optimizes detection of community composition differences.
  • To provide interpretable feature-weight profiles for identifying key taxa driving group separation.

Main Methods:

  • MeLSI employs an ensemble of weak learners with bootstrap sampling and feature subsampling.
  • Gradient-based optimization is used to learn optimal feature weights for distance metrics.
  • Learned metrics are integrated with permutational multivariate analysis of variance (PERMANOVA) for hypothesis testing and principal coordinates analysis (PCoA) for visualization.

Main Results:

  • MeLSI demonstrated proper type I error control and superior statistical power in detecting subtle community shifts across synthetic and real datasets.
  • On the DietSwap dataset, MeLSI uniquely identified significant diet-induced community shifts missed by fixed metrics.
  • Learned feature weights successfully identified biologically relevant taxa, offering interpretable insights into group separation drivers.

Conclusions:

  • MeLSI offers a statistically rigorous and data-driven approach to augment beta diversity analysis with enhanced interpretability.
  • The framework effectively detects subtle community shifts and identifies key microbial drivers, surpassing the limitations of fixed distance metrics.
  • MeLSI accelerates the translation of microbiome data into testable biological hypotheses and potential clinical applications by providing actionable insights.