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 Videos

Segway 2.0: Gaussian mixture models and minibatch training.

Rachel C W Chan1,2, Maxwell W Libbrecht3, Eric G Roberts1

  • 1Princess Margaret Cancer Centre, Toronto, ON M5G 1L7, Canada.

Bioinformatics (Oxford, England)
|October 14, 2017
PubMed
Summary

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

EpiATLAS - a reference for human epigenomic research.

bioRxiv : the preprint server for biology·2026
Same author

Pan-cell type continuous chromatin state annotation of all epigenomes from the International Human Epigenome Consortium.

Genome biology·2026
Same author

Prioritizing peptides for targeted mass spectrometry experiments using deep learning.

bioRxiv : the preprint server for biology·2026
Same author

Embryo-scale Visual Cell Sorting reveals a conserved transcriptomic signature of nucleolar size linked to proteostasis.

bioRxiv : the preprint server for biology·2026
Same author

Detection and classification of lymphoma from cell-free methylome data.

NPJ precision oncology·2026
Same author

Segzoo: a turnkey system that summarizes genome annotations.

Bioinformatics (Oxford, England)·2026

Segway 2.0 enhances genome annotation by modeling complex genomic signal distributions with greater accuracy. This new version improves parameter learning through Gaussian mixture modeling and minibatch training for more precise pattern discovery.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Genome annotation is crucial for understanding genomic function.
  • Existing methods struggle with complex, multi-dataset genomic signals.
  • Accurate modeling of genomic data is essential for biological discovery.

Purpose of the Study:

  • To introduce Segway 2.0, a significantly enhanced version of the Segway genome annotation tool.
  • To improve the accuracy and capability of modeling diverse genomic signal datasets.
  • To enable the discovery of joint patterns across multiple genomic signals with higher precision.

Main Methods:

  • Utilizing a mixture of Gaussians to model complex signal distributions.
  • Implementing minibatch training for improved parameter learning.

Related Experiment Videos

  • Semi-automated genome annotation across multiple genomic signal datasets.

    • Main Results:

    • Segway 2.0 demonstrates substantially greater accuracy in modeling genomic data.
    • The new enhancements allow for the capture of arbitrarily complex signal distributions.
    • Improved learned parameters lead to more robust genome annotation.

    Conclusions:

    • Segway 2.0 represents a major advancement in semi-automated genome annotation.
    • The tool's enhanced modeling capabilities facilitate more accurate biological insights.
    • Freely available code and data support reproducible research in genomics.