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

Effective optimization algorithms for fragment-assembly based protein structure prediction.

Kevin W Deronne1, George Karypis

  • 1Department of Computer Science & Engineering, Digital Technology Center, Army HPC Research Center, University of Minnesota, Minneapolis, MN 55455, USA. deronne@cs.umn.edu

Journal of Bioinformatics and Computational Biology
|June 26, 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

PropMolFlow: property-guided molecule generation with geometry-complete flow matching.

Nature computational science·2026
Same author

TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting.

IEEE transactions on neural networks and learning systems·2022
Same author

A knowledge graph of clinical trials ([Formula: see text]).

Scientific reports·2022
Same author

Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical Spaces.

Molecular informatics·2022
Same author

DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science.

ACS omega·2021
Same author

Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning.

IEEE transactions on neural networks and learning systems·2021

Deterministic algorithms like Hill-climbing (HC) offer improved protein structure prediction. These methods optimize scoring functions more effectively than traditional stochastic techniques, leading to better new fold prediction accuracy.

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Protein structure prediction

Background:

  • Accurate protein new fold prediction remains a significant challenge in structural bioinformatics.
  • Current methods often struggle with the vast conformational space of protein sequences.
  • Fragment assembly approaches typically rely on stochastic optimization techniques.

Purpose of the Study:

  • To investigate the efficacy of deterministic algorithms for optimizing scoring functions in protein structure prediction.
  • To introduce and evaluate the Greedy and Hill-climbing (HC) algorithms for new fold prediction.
  • To compare the performance of these deterministic methods against traditional stochastic approaches.

Main Methods:

  • Application of Greedy and Hill-climbing (HC) algorithms to optimize scoring functions for protein structure prediction.

Related Experiment Videos

  • HC algorithm incorporates a mechanism to escape local minima.
  • Experimental validation using a dataset of 276 diverse proteins.

    • Main Results:

    • The Hill-climbing (HC) algorithm demonstrated consistent superior performance compared to Simulated Annealing.
    • HC optimization resulted in lower root mean squared deviation (RMSD) between predicted and native protein structures.
    • Deterministic algorithms show promise for enhancing new fold prediction accuracy.

    Conclusions:

    • Deterministic optimization, particularly the HC algorithm, provides a more effective approach for protein new fold prediction.
    • The HC algorithm's ability to overcome local minima is crucial for its improved performance.
    • These findings suggest a potential shift towards deterministic methods in computational protein structure prediction.