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

You might also read

Related Articles

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

Sort by
Same author

Molecular identification of Kudoa thyrsites parasite isolated from Atlantic mackerel (Scomber scombrus) landed in Ireland.

Parasitology research·2026
Same author

Translational barriers to digital twins in radiation oncology.

Physics and imaging in radiation oncology·2026
Same author

Sickle cell disease 115 years later: improving health outcomes through policy, research, and collaboration, to achieve health equity.

Frontiers in health services·2026
Same author

Scalable Boltzmann generators for equilibrium sampling of large-scale materials.

Nature communications·2026
Same author

Assessing generative modeling approaches for free energy estimates in condensed matter.

The Journal of chemical physics·2026
Same author

Geographic and Temporal Differences in Sickle Cell Disease Hospitalizations in New York State.

JAMA network open·2026

Related Experiment Video

Updated: Jul 5, 2025

High-Speed Atomic Force Microscopy Imaging of DNA Three-Point-Star Motif Self Assembly Using Photothermal Off-Resonance Tapping
08:59

High-Speed Atomic Force Microscopy Imaging of DNA Three-Point-Star Motif Self Assembly Using Photothermal Off-Resonance Tapping

Published on: March 22, 2024

792

Improved motif-scaffolding with SE(3) flow matching.

Jason Yim, Andrew Campbell, Emile Mathieu

    Arxiv
    |January 23, 2024
    PubMed
    Summary

    This study enhances protein design by improving motif-scaffolding with FrameFlow, a generative model. The new method generates more diverse and designable protein scaffolds, overcoming limitations of previous approaches.

    More Related Videos

    Ensemble Force Spectroscopy by Shear Forces
    07:30

    Ensemble Force Spectroscopy by Shear Forces

    Published on: July 26, 2022

    1.5K
    Stepwise Cell Seeding on Tessellated Scaffolds to Study Sprouting Blood Vessels
    07:49

    Stepwise Cell Seeding on Tessellated Scaffolds to Study Sprouting Blood Vessels

    Published on: January 14, 2021

    3.5K

    Related Experiment Videos

    Last Updated: Jul 5, 2025

    High-Speed Atomic Force Microscopy Imaging of DNA Three-Point-Star Motif Self Assembly Using Photothermal Off-Resonance Tapping
    08:59

    High-Speed Atomic Force Microscopy Imaging of DNA Three-Point-Star Motif Self Assembly Using Photothermal Off-Resonance Tapping

    Published on: March 22, 2024

    792
    Ensemble Force Spectroscopy by Shear Forces
    07:30

    Ensemble Force Spectroscopy by Shear Forces

    Published on: July 26, 2022

    1.5K
    Stepwise Cell Seeding on Tessellated Scaffolds to Study Sprouting Blood Vessels
    07:49

    Stepwise Cell Seeding on Tessellated Scaffolds to Study Sprouting Blood Vessels

    Published on: January 14, 2021

    3.5K

    Area of Science:

    • Computational Biology
    • Protein Engineering
    • Artificial Intelligence in Biology

    Background:

    • Protein design relies on creating functional proteins around specific motifs.
    • Generative models show promise but often produce scaffolds lacking structural diversity.
    • This limits their success in experimental validation.

    Purpose of the Study:

    • To extend the FrameFlow model for advanced motif-scaffolding.
    • To address the lack of structural diversity in generated protein scaffolds.
    • To improve the designability and uniqueness of motif-scaffolds.

    Main Methods:

    • Extended FrameFlow, an SE(3) flow matching model, for protein backbone generation.
    • Implemented two motif-scaffolding approaches: motif amortization and motif guidance.
    • Trained FrameFlow with motifs using data augmentation (amortization) and used score estimation (guidance).

    Main Results:

    • Achieved 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art methods.
    • Demonstrated improved structural diversity in generated scaffolds.
    • Validated performance on a benchmark of 24 biologically relevant motifs.

    Conclusions:

    • The extended FrameFlow model significantly advances motif-scaffolding capabilities.
    • The proposed methods enhance the generation of diverse and designable protein scaffolds.
    • This work offers a promising computational tool for protein engineering and design.