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 Experiment Video

Updated: May 29, 2026

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

Unsupervised machine learning for scientific discovery: workflow and best practices.

Andersen Chang1, Tiffany Tang2, Tarek Zikry3

  • 1Department of Neuroscience, Baylor College of Medicine, Houston, TX, USA.

Philosophical Transactions. Series A, Mathematical, Physical, and Engineering Sciences
|May 28, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Assessing peripheral oxytocin and cortisol levels and epigenetic variations of oxytocin receptor and glucocorticoid receptor genes in school-aged preterm-born children.

Progress in neurobiology·2026
Same author

Optimal pain management: epidural or locoregional nerve blocks for canine stifle surgery?

Veterinary evidence·2026
Same author

Non-Genetic Mechanisms of Fractional Resistance to Abemaciclib in Dedifferentiated Liposarcoma.

bioRxiv : the preprint server for biology·2026
Same author

Author Correction: Foundation model of neural activity predicts response to new stimulus types.

Nature·2026
Same author

Functional bipartite invariance in mouse primary visual cortex receptive fields.

Nature neuroscience·2026
Same author

Taste Changes in a Rat Model of Spinal Cord Injury: Impact of High-Fat Diet and Weight Loss Surgery.

Nutrients·2026
Same journal

Correction to: 'Stokes settling and particle-laden plumes: implications for deep-sea mining and volcanic eruption plumes' (2020), by Mingotti et al.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

A stable hothouse triggered by a tipping mechanism.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Beyond distance: quantifying point cloud dynamics with persistent homology and dynamic optimal transport.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Global stability of the Atlantic overturning circulation: edge state, long transients and boundary crisis under CO2 forcing.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Morse index classification and landscape of Kuramoto system for Hebbian-based binary pattern recognition.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same journal

Interpretable and equation-free response theory for complex systems.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
See all related articles

This study introduces a standardized workflow for unsupervised machine learning in science, enhancing data-driven discovery. It emphasizes best practices for reliable and reproducible scientific research using large datasets.

Area of Science:

  • Unsupervised machine learning applications in climate science, biomedicine, astronomy, and chemistry.
  • Data-driven discovery from large, unlabelled datasets.

Background:

  • Widespread use of unsupervised machine learning in various scientific domains.
  • Lack of standardization in unsupervised learning workflows hinders reliable and reproducible scientific discoveries.

Purpose of the Study:

  • To present a structured workflow for unsupervised learning techniques in scientific research.
  • To highlight best practices for ensuring reliable and reproducible scientific discoveries.
  • To illustrate the workflow with an astronomy case study.

Main Methods:

  • Formulating validatable scientific questions.
  • Robust data preparation and exploration.
  • Utilizing diverse modeling techniques.
Keywords:
astronomybest practicesclusteringdata-driven discoverydimension reductionunsupervised learningworkflow

Related Experiment Videos

Last Updated: May 29, 2026

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

  • Rigorous validation of model stability and generalizability.
  • Effective communication and documentation of results.

    • Main Results:

    • A structured workflow for unsupervised machine learning in science is proposed.
    • Best practices for data preparation, modeling, and validation are discussed.
    • An astronomy case study on refining globular clusters demonstrates the workflow's utility.

    Conclusions:

    • A standardized workflow is crucial for reliable and reproducible unsupervised machine learning in science.
    • The proposed workflow enhances the potential for data-driven scientific discovery.
    • Carefully designed workflows significantly advance scientific progress through validated machine learning approaches.