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

Can correct protein models be identified?

Björn Wallner1, Arne Elofsson

  • 1Stockholm Bioinformatics Center, SCFAB, Stockholm University, SE-106 91 Stockholm, Sweden.

Protein Science : a Publication of the Protein Society
|April 30, 2003
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

Improving AlphaFold2 Performance in Virtual Screens Targeting GPCRs by Enhancing Binding-Site Conformational Sampling.

Journal of chemical information and modeling·2026
Same author

Mass spectrometry integrates protein design into structural biology method development.

QRB discovery·2026
Same author

Evaluating deep learning based structure prediction methods on antibody-antigen complexes.

Bioinformatics (Oxford, England)·2026
Same author

The N-Myc MB0-MBI region interacts specifically and dynamically with the N-lobe of Aurora kinase A.

Nature communications·2026
Same author

A deep learning framework for comprehensive prediction of human RNA G-quadruplex-binding proteins.

Bioinformatics (Oxford, England)·2026
Same author

Blind prediction of complex water and ion ensembles around RNA in CASP16.

bioRxiv : the preprint server for biology·2025
Same journal

Macromolecular crowding inhibits degradation of alpha-synuclein amyloid fibrils induced by cathepsins and MMP9.

Protein science : a publication of the Protein Society·2026
Same journal

Sequence-encoded differences in the conformational ensembles of CITED transcriptional activation domains impact coactivator binding.

Protein science : a publication of the Protein Society·2026
Same journal

The phospholipid biosynthesis enzyme PlsB contains three distinct domains for membrane association, lysophosphatidic acid synthesis, and dimerization.

Protein science : a publication of the Protein Society·2026
Same journal

Structural basis of ligand selectivity in FAD/NAD(P)H-dependent dehydrogenases: insights from trypanothione reductase and type II NADH dehydrogenase.

Protein science : a publication of the Protein Society·2026
Same journal

Achieving protease substrate-specific inhibition by mAb dual functional selections.

Protein science : a publication of the Protein Society·2026
Same journal

How important are quantum mechanical effects in controlling biological functions: Enzymes, electron transfer and bird navigation.

Protein science : a publication of the Protein Society·2026
See all related articles

We developed ProQ, a neural network method for protein model quality prediction. ProQ accurately identifies native and near-native protein structures, outperforming existing methods in detecting correct models.

Area of Science:

  • Computational Biology
  • Structural Biology
  • Bioinformatics

Background:

  • Accurate protein structure prediction is crucial for understanding biological function.
  • Existing methods struggle to differentiate correct models from incorrect ones, especially those with limited similarity to the native structure.

Purpose of the Study:

  • To develop and evaluate ProQ, a novel neural-network-based method for predicting protein model quality.
  • To assess ProQ's ability to identify native and near-native protein structures, including those with partial structural similarity.

Main Methods:

  • ProQ utilizes structural features like atom-atom contact frequency to predict model quality.
  • Quality is measured using LGscore and MaxSub metrics.
  • ProQ's performance is compared against existing methods on various test sets.

Related Experiment Videos

  • ProQ is integrated with the Pcons fold recognition predictor (Pmodeller).

    • Main Results:

    • ProQ demonstrates comparable or superior performance to existing measures in identifying native structures.
    • ProQ excels at detecting correct protein models, even those with limited similarity to the native structure.
    • Combining ProQ with Pmodeller (Pcons) enhances performance, particularly by removing high-scoring incorrect models.
    • Pmodeller shows higher specificity than Pcons alone, validated in CASP5 and LiveBench-6.

    Conclusions:

    • ProQ is an effective tool for protein model quality assessment, improving the identification of correct structures.
    • The integration of ProQ with Pmodeller offers a robust approach for fold recognition and model selection.
    • These advancements contribute to more reliable protein structure prediction pipelines.