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

Local protein structure prediction using discriminative models.

Oliver Sander1, Ingolf Sommer, Thomas Lengauer

  • 1Max-Planck-Institute for Informatics, Department of Computational Biology and Applied Algorithmics, Stuhlsatzenhausweg 85, D-66123 Saarbrücken, Germany. osander@mpi-sb.mpg.de

BMC Bioinformatics
|January 13, 2006
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

Development and validation of a Relapsing Polychondritis disease-specific Quality of Life instrument (ERN ReCONNET RP-QoL).

Rheumatology (Oxford, England)·2026
Same author

Evaluating disease burden in German AAV patients using the AAV-PRO: associations with disease activity, physical function, depression, fatigue and quality of life.

Journal of patient-reported outcomes·2026
Same author

Identifying quality of life domains and facets affected in relapsing polychondritis: a qualitative analysis for the development of a disease-specific health-related quality of life instrument.

Orphanet journal of rare diseases·2026
Same author

Validation of the German version of the ANCA-associated vasculitis patient-reported outcome questionnaire.

Clinical and experimental rheumatology·2026
Same author

Association of G-Protein-Coupled Receptors autoantibodies with vasoregulation in Post-COVID.

PloS one·2026
Same author

Geno2pheno: recombination detection for HIV-1 and HEV subtypes.

NAR molecular medicine·2025
Same journal

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

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

This study introduces a novel method for predicting local protein structures. The approach enhances protein structure prediction accuracy by providing probability estimates for local structure candidates.

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Protein structure prediction

Background:

  • Recent advances in protein structure prediction leverage local structure information, significantly improving new fold and fold recognition methods.
  • Existing methods benefit from incorporating local structure predictions, enhancing accuracy in protein structure analysis.
  • A novel local structure prediction method was developed for integration into existing protein structure prediction pipelines.

Purpose of the Study:

  • To develop a method for predicting local protein structure probabilities based on sequence information.
  • To create a tool that can be integrated into both fold recognition and new fold prediction algorithms.
  • To improve the accuracy and efficiency of protein structure prediction.

Main Methods:

Related Experiment Videos

  • Clustering of recurrent local structures to define a set of representative local structures.
  • Training a discriminative model to predict local structure representatives using local sequence information.
  • Predicting probability estimates for local structure candidates for each sequence window.

Main Results:

  • Clustering yielded 27 structural representatives with an average RMSD quantization error of 1.19 Å for a fragment length of 7 residues.
  • The prediction model achieved an area under the ROC curve ranging from 0.68 to 0.88 for detecting the 27 local structure classes.
  • The method provides probability estimates for various local protein structures.

Conclusions:

  • The developed method effectively predicts probability estimates for local protein structure candidates.
  • These predictions offer valuable signals for diverse local structures.
  • Integration into fold recognition and new fold prediction methods can enhance alignment quality and overall prediction accuracy.