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

A Template-Based Protein Structure Reconstruction Method Using Deep Autoencoder Learning.

Haiou Li1,2, Qiang Lyu1, Jianlin Cheng2

  • 1Department of Computer Science and Technology, Soochow University, Suzhou, 215006, China.

Journal of Proteomics & Bioinformatics
|October 31, 2017
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

A unified multimodal model for generalizable zero-shot and supervised protein function prediction.

Bioinformatics (Oxford, England)·2026
Same author

CryoFSL: an annotation-efficient, few-shot learning framework for robust protein particle picking in cryo-electron microscopy micrographs.

Briefings in bioinformatics·2026
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Decoupling the role of pad materials in brake wear particulate emissions using the UN GTR-24 test method toward non-exhaust PM management.

Journal of hazardous materials·2026
Same author

Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction.

NAR genomics and bioinformatics·2026
Same author

LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models.

ArXiv·2026
Same journal

Large Scale Screening and Quantitative Analysis of Site-Specific N-Glycopeptides from Human Serum in Early Alzheimer's Disease Using LC-HCD-PRM-MS.

Journal of proteomics & bioinformatics·2023
Same journal

High Fat Diet-Induced Changes in Hepatic Protein Abundance in Mice.

Journal of proteomics & bioinformatics·2021
Same journal

Quantitative Proteomics Using Formalin-fixed, Paraffin-embedded Biopsy Tissues in Inflammatory Disease.

Journal of proteomics & bioinformatics·2020
Same journal

The Quiescent Metabolic Phenotype of Glioma Stem Cells.

Journal of proteomics & bioinformatics·2020
Same journal

Interactive Web Tool for Standardizing Proteomics Workflow for Liquid Chromatography-Mass Spectrometry Data.

Journal of proteomics & bioinformatics·2020
Same journal

Standardizing Proteomics Workflow for Liquid Chromatography-Mass Spectrometry: Technical and Statistical Considerations.

Journal of proteomics & bioinformatics·2020
See all related articles

We developed a novel deep learning method for protein structure reconstruction. This approach uses a stacked denoising autoencoder to improve protein structure prediction accuracy, showing promising results.

Area of Science:

  • Computational Biology
  • Biomedical Research
  • Structural Biology

Background:

  • Protein structure prediction is crucial for understanding protein function, design, and drug discovery.
  • Accurate protein structure modeling remains a significant challenge in computational biology.

Purpose of the Study:

  • To develop a novel deep learning approach for protein structure reconstruction.
  • To apply a stacked denoising autoencoder for enhancing template-based protein structure prediction.

Main Methods:

  • Utilized a PSI-BLAST search to identify homologous template proteins.
  • Employed 3DRobot to generate initial protein structure decoy models from templates.
  • Trained a stacked denoising autoencoder on these decoys to create a deep learning model for target protein reconstruction.
Keywords:
Deep autoencoderDeep learningProtein structure predictionTemplate-based modeling

Related Experiment Videos

Main Results:

  • The deep autoencoder model was successfully trained on generated decoys.
  • The model reconstructed final structural models for target sequences.
  • Achieved a GDT-TS score greater than 0.7 for proteins with highly similar templates.

Conclusions:

  • The developed deep learning approach shows significant promise for protein structure reconstruction.
  • Stacked denoising autoencoders offer a viable method for improving protein structure prediction accuracy.
  • This work contributes to advancing computational biology and its applications in biomedical research.