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

DeepUMQA: ultrafast shape recognition-based protein model quality assessment using deep learning.

Sai-Sai Guo1, Jun Liu1, Xiao-Gen Zhou1

  • 1College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China.

Bioinformatics (Oxford, England)
|February 8, 2022
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

ProSiteHunter: A Unified Framework for Sequence-Based Prediction of Protein-Nucleic Acid and Protein-Protein Binding Sites.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

When cryo-EM modeling meets structure prediction.

Nature structural & molecular biology·2026
Same author

High-accuracy protein complex structure modeling based on sequence-derived structure complementarity.

Nature communications·2025
Same author

MultiSAAl: Sequence-Informed Antibody-Antigen Interaction Prediction Using Multiscale Deep Learning.

Journal of chemical information and modeling·2025
Same author

Highlights of Model Quality Assessment in CASP16.

Proteins·2025
Same author

Beyond static structures: protein dynamic conformations modeling in the post-AlphaFold era.

Briefings in bioinformatics·2025
Same journal

Cross-Domain Transfer Learning from Peptides to Metabolites Using a Multi-Property Fine-Tuned LLM.

Bioinformatics (Oxford, England)·2026
Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026
Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026
Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
See all related articles

DeepUMQA enhances protein model quality assessment using Ultrafast Shape Recognition (USR) features with deep learning. This method improves residue-level topological information, boosting prediction accuracy for protein structure models.

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning

Background:

  • Protein model quality assessment is crucial for accurate protein structure prediction.
  • Existing methods using voxelization features may not fully capture residue-level topological information.
  • Improved residue-level topological characterization is needed for enhanced model quality assessment.

Purpose of the Study:

  • To develop a novel deep learning method, DeepUMQA, for residue-level single-model quality assessment.
  • To incorporate Ultrafast Shape Recognition (USR) features to better represent residue topology.
  • To improve the accuracy of protein model quality assessment by combining USR with existing features.

Main Methods:

  • Developed DeepUMQA, a deep residual neural network-based method.

Related Experiment Videos

  • Integrated residue-level USR features, capturing topological relationships.
  • Combined USR features with 1D, 2D, and voxelization features for quality assessment.

    • Main Results:

    • DeepUMQA significantly improved model assessment accuracy on CASP13, CASP14, and CAMEO datasets.
    • USR features effectively supplemented voxelization features, providing comprehensive structural information.
    • DeepUMQA demonstrated top-tier performance compared to state-of-the-art single-model quality assessment methods.

    Conclusions:

    • DeepUMQA offers a robust approach for residue-level protein model quality assessment.
    • The integration of USR features enhances the characterization of local residue topology.
    • DeepUMQA represents a significant advancement in the field of protein structure prediction quality assessment.