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

High-precision high-coverage functional inference from integrated data sources.

Bolan Linghu1, Evan S Snitkin, Dustin T Holloway

  • 1Bioinformatics Graduate Program, Boston University, Boston, MA, 02215, USA. blinghu@bu.edu

BMC Bioinformatics
|February 27, 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

Defining the <i>Candidozyma auris</i> pan-genome and essentiality.

bioRxiv : the preprint server for biology·2026
Same author

Resolving competing evolutionary histories in joint ancestral state reconstruction.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Genomic inference of sites of transmission during regional spread of bla<sub>NDM</sub> Klebsiella pneumoniae in Michigan.

Nature communications·2026
Same author

Vaginal microbiota of adolescents and their mothers: A preliminary study of vertical transmission and persistence.

Frontiers in microbiomes·2026
Same author

Antibiotic-resistance plasmid amplified among MRSA cases in an urban jail and its connected communities.

Nature communications·2025
Same author

A Novel Technique to Characterize <i>Klebsiella pneumoniae</i> Populations Indicates that Mono-Colonization is Associated with Risk of Infection.

bioRxiv : the preprint server for biology·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

We developed a two-step machine learning framework to improve protein function annotation. Integrating data into a functional linkage network (FLN) and applying a maximum weight rule significantly boosts annotation precision and coverage.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Integrating diverse data sources enhances protein function knowledge.
  • Machine learning methods construct weighted functional linkage networks (FLNs).
  • Current FLNs offer high coverage but low precision in functional annotation.

Purpose of the Study:

  • Propose a two-step framework for precise protein functional annotation.
  • Develop a method to optimize functional annotation using FLNs.
  • Enhance the reliability and range of protein function knowledge.

Main Methods:

  • Construct a high-coverage, reliable FLN using machine learning techniques.
  • Develop and apply a decision rule to the FLN for optimized annotation.

Related Experiment Videos

  • Evaluate four machine learning methods: Linear SVM, Linear Discriminant Analysis, Naïve Bayes, and Neural Network.

    • Main Results:

    • Four machine learning methods successfully created reliable, high-coverage FLNs.
    • The maximum edge weight decision rule yielded the most precise annotations (approx. 70% at full coverage).
    • The framework demonstrated robustness and applicability to less-studied organisms, with a scoring scheme for prediction precision.

    Conclusions:

    • A general two-step framework for protein function annotation was established.
    • High-coverage, high-precision annotations are achievable through data integration into FLNs.
    • Applying a maximum weight decision rule is key to optimizing functional annotation accuracy.