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

Protein molecular function prediction by Bayesian phylogenomics.

Barbara E Engelhardt1, Michael I Jordan, Kathryn E Muratore

  • 1Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, California, United States of America. bee@cs.berkeley.edu

Plos Computational Biology
|October 12, 2005
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

predNMD: prediction of nonsense-mediated mRNA decay for improved clinical variant pathogenicity classification.

bioRxiv : the preprint server for biology·2026
Same author

Segmentation-free analysis of live-cell imaging data reveals how T cell modifications influence cancer cell aggregation dynamics.

Scientific reports·2026
Same author

Machine Learning-Guided Discovery of Bacterial-Selective Membrane-Active Compounds Reveals Mechanistic Bias in Antibiotic Training Datasets.

bioRxiv : the preprint server for biology·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

Differential Methylation by Early Life Adversity in the Future of Families Child Wellbeing Study.

bioRxiv : the preprint server for biology·2026
Same author

Advances in Protein Function Prediction from the Fifth CAFA Challenge.

bioRxiv : the preprint server for biology·2026
Same journal

Another 10 years of PLOS Computational Biology: A data-driven reflection on trends in genomics research.

PLoS computational biology·2026
Same journal

Mobility data resolution needed to inform predictive models of spatial epidemic spread from mobile phone data.

PLoS computational biology·2026
Same journal

DeepMethylation: A deep learning framework for tissue-specific DNA methylation prediction and functional variant annotation.

PLoS computational biology·2026
Same journal

Redefining and estimating the early-phase reproduction ratio for epidemic outbreaks in spatially structured populations.

PLoS computational biology·2026
Same journal

Optimized phenotype definitions boost GWAS power.

PLoS computational biology·2026
Same journal

Detection, communication, and individual identification with deep audio embeddings: A case study with North Atlantic right whales.

PLoS computational biology·2026
See all related articles

SIFTER, a new statistical model, accurately predicts protein molecular function using evolutionary relationships. It significantly outperforms existing methods, even with limited data, aiding in understanding protein families.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Unannotated protein sequences pose a challenge in understanding molecular functions.
  • Phylogenomic principles offer a framework for inferring protein function through evolutionary relationships.

Purpose of the Study:

  • To develop and validate SIFTER (Statistical Inference of Function Through Evolutionary Relationships), a novel statistical graphical model for predicting specific molecular functions of unannotated proteins.
  • To compare SIFTER's predictive accuracy against established methods like BLAST and Gene Ontology annotations.

Main Methods:

  • SIFTER utilizes a statistical graphical model based on phylogenomic principles.
  • It infers molecular function from reconciled phylogenies and existing function annotations, handling sparse or noisy data.

Related Experiment Videos

  • Predictions were validated across 100 Pfam families and specifically on adenosine deaminase and lactate/malate dehydrogenase families.

    • Main Results:

    • SIFTER demonstrated high accuracy (96%) in predicting molecular function for the adenosine deaminase family, significantly outperforming BLAST (75%), GeneQuiz (64%), GOtcha (89%), and Orthostrapper (11%).
    • The model showed consistent and specific predictions across diverse protein families.
    • Experimental characterization of *Plasmodium falciparum* adenosine deaminase confirmed SIFTER's prediction.

    Conclusions:

    • SIFTER effectively predicts protein molecular function by leveraging statistical models of function evolution.
    • The method offers a significant advancement in phylogenomic analysis, particularly for unannotated or sparsely annotated protein sequences.
    • SIFTER provides a powerful, accurate, and experimentally validated tool for molecular function inference.