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

Adaptive diffusion kernel learning from biological networks for protein function prediction.

Liang Sun1, Shuiwang Ji, Jieping Ye

  • 1Center for Evolutionary Functional Genomics, The Biodesign Institute, Arizona State University, Tempe, AZ, USA. sun.liang@asu.edu

BMC Bioinformatics
|March 28, 2008
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

Author Correction: UKB-MDRMF: a multi-disease risk and multimorbidity framework based on UK biobank data.

Nature communications·2026
Same author

MyESL: A Software for Evolutionary Sparse Learning in Molecular Phylogenetics and Genomics.

Molecular biology and evolution·2025
Same author

Rhizosphere microbial diversity and functional roles in tea cultivars: insights from high-throughput sequencing and functional isolates.

Plant signaling & behavior·2025
Same author

LLaFS++: Few-Shot Image Segmentation With Large Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

CATI: A medical context-enhanced framework for diagnosis code assignment in the UK Biobank study.

Artificial intelligence in medicine·2025
Same author

UKB-MDRMF: a multi-disease risk and multimorbidity framework based on UK biobank data.

Nature communications·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

Optimizing diffusion kernels for protein function prediction improves performance. A new method efficiently learns optimal kernels, outperforming individual kernels and handling multiple functions simultaneously.

Area of Science:

  • Bioinformatics
  • Machine Learning
  • Computational Biology

Background:

  • Machine learning is increasingly used for biological network analysis and protein function prediction.
  • Kernel methods, particularly diffusion kernels, are well-suited for graph-based biological data.
  • Selecting an optimal kernel function is crucial for effective kernel methods.

Purpose of the Study:

  • To develop an efficient method for learning an optimal diffusion kernel for protein function prediction.
  • To address limitations of existing Support Vector Machine (SVM)-based approaches, especially for Kullback-Leibler (KL) divergence.
  • To extend the method for simultaneous prediction of multiple protein functions (multi-task learning).

Main Methods:

  • Formulating the KL divergence-based kernel learning problem as an efficient optimization problem by exploiting diffusion kernel structure.

Related Experiment Videos

  • Developing algorithms for both single-task and multi-task protein function prediction.
  • Evaluating the proposed algorithms on benchmark datasets.

    • Main Results:

    • A linearly combined diffusion kernel significantly outperforms individual candidate kernels.
    • The proposed KL divergence-based kernel learning is efficient and effective.
    • Multi-task learning algorithms show competitive performance and computational efficiency for large numbers of tasks.

    Conclusions:

    • Linear combinations of diffusion kernels enhance protein function prediction accuracy.
    • Multi-task learning approaches are advantageous for predicting numerous protein functions, offering a balance of performance and computational cost.