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

Learning biophysically-motivated parameters for alpha helix prediction.

Blaise Gassend1, Charles W O'Donnell, William Thies

  • 1Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA. gassend@mit.edu

BMC Bioinformatics
|July 13, 2007
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

Granular soil densification using expansive resins.

Scientific reports·2026
Same author

The evolution of therapy for chronic osteoarthritic knee pain: Feasibility, safety and clinical outcomes of transpedal access for genicular artery embolization.

European journal of radiology·2026
Same author

Risk of thrombosis with thrombocytopaenia syndrome (TTS) after vaccination with AZD1222: a European VAC4EU post-authorisation safety study.

Vaccine·2026
Same author

Optometrist attitudes towards delivering intravitreal injections in Aotearoa New Zealand.

Clinical & experimental optometry·2026
Same author

Microbiome education at under-resourced institutions: current status, barriers, and approaches to successful implementation.

Journal of microbiology & biology education·2026
Same author

Trajectory of weight regain after cessation of GLP-1 receptor agonists: a systematic review and nonlinear meta-regression.

EClinicalMedicine·2026
Same journal

Research on multi-trait genome association study method based on Shannon information entropy.

BMC bioinformatics·2026
Same journal

A multi-view feature fusion framework with interpretable graph convolution for predicting microbe-drug associations.

BMC bioinformatics·2026
Same journal

Covariance decomposition for distance based species tree estimation.

BMC bioinformatics·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
See all related articles

This study introduces a novel protein secondary structure predictor using a biophysically-motivated energy model. Machine learning optimizes parameters for accurate protein structure prediction, achieving high performance without external databases.

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning in Biology

Background:

  • Developing advanced protein secondary structure predictors is crucial for understanding protein function.
  • Current methods often rely on extensive databases, limiting their applicability.
  • A need exists for predictors with intuitive, biophysically-grounded energy models.

Purpose of the Study:

  • To create a state-of-the-art protein secondary structure predictor.
  • To develop an intuitive and biophysically-motivated energy model for structure prediction.
  • To utilize machine learning for parameter estimation in predicting protein structures.

Main Methods:

  • Protein structure prediction framed as an optimization problem.
  • Employing parameterizable cost functions representing biological pseudo-energies.

Related Experiment Videos

  • Applying machine learning (specifically SVMs) to learn energy function parameters.

    • Main Results:

    • Achieved 77.6% Qalpha and 73.4% SOValpha for alpha helix prediction using a 302-parameter model.
    • Performance rivals state-of-the-art methods not relying on external databases.
    • The model's limited parameters facilitate extraction of biological significance.

    Conclusions:

    • The presented method shows significant promise for protein secondary structure prediction.
    • Learned biophysically-motivated free energies via SVMs yield a competitive energy cost function.
    • The approach is general and extensible to other protein structure prediction tasks.