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

DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier.

Maxat Kulmanov1, Mohammed Asif Khan1, Robert Hoehndorf1

  • 1Computer, Electrical and Mathematical Sciences & Engineering Division, Computational Bioscience Research Center, King Abdullah University of Science and Technology, Thuwal 23955-6900, Kingdom of Saudi Arabia.

Bioinformatics (Oxford, England)
|October 14, 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

Evaluating completeness, coherence, and consistency of genome-scale function annotations.

Briefings in bioinformatics·2026
Same author

INDIGENA: inductive prediction of disease-gene associations using phenotype ontologies.

Bioinformatics (Oxford, England)·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

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

ArXiv·2026
Same author

Sexual plasticity of Hippolyte inermis Leach (Crustacea, Decapoda): Gene expression of vitellogenin and insulin-like androgenic gland hormone.

Animal reproduction science·2026
Same author

LEP-AD: language embedding of proteins and attention to drugs predicts drug-target interactions.

Journal of cheminformatics·2026

This study introduces a novel deep learning method for predicting protein function from sequence data. The approach significantly improves accuracy over existing methods, particularly for cellular location prediction.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • High-throughput sequencing generates vast protein data, necessitating efficient functional characterization.
  • Experimental protein function determination is resource-intensive and limited in scope.
  • Computational methods are crucial for predicting protein functions across diverse organisms.

Purpose of the Study:

  • To develop a novel deep learning method for accurate protein function prediction from sequence.
  • To leverage protein-protein interaction networks and Gene Ontology (GO) structure for improved predictions.
  • To address the large-scale, multi-class, multi-label nature of protein function prediction.

Main Methods:

  • Employed deep learning to extract features from protein sequences.

Related Experiment Videos

  • Integrated a cross-species protein-protein interaction network into the model.
  • Utilized Gene Ontology (GO) class dependencies to construct the deep learning model.
  • Evaluated performance using Computational Assessment of Function Annotation (CAFA) standards.

    • Main Results:

    • Achieved significant improvements in protein function prediction accuracy compared to baseline methods like BLAST.
    • Demonstrated particular strength in predicting protein cellular locations.
    • The developed method effectively utilizes sequence and network information for function prediction.

    Conclusions:

    • The novel deep learning approach offers a powerful tool for large-scale protein function prediction.
    • This method advances the field of computational biology by improving prediction accuracy and efficiency.
    • The approach provides a valuable resource for understanding protein roles in biological systems.