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

Predicting deleterious nsSNPs: an analysis of sequence and structural attributes.

Richard J Dobson1, Patricia B Munroe, Mark J Caulfield

  • 1Clinical Pharmacology, The William Harvey Research Institute, Bart's and the London School of Medicine and Dentistry, Queen Mary University of London, Charterhouse Square, London EC1M 6BQ, UK. r.j.dobson@qmul.ac.uk

BMC Bioinformatics
|April 25, 2006
PubMed
Summary

Machine learning improves non-synonymous protein coding single nucleotide polymorphism (nsSNP) function prediction. Balancing datasets and using sequence conservation significantly enhances accuracy, with predictions available for all Ensembl nsSNPs.

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

Imaging-Derived Sarcopenic Obesity and Cardiovascular Outcomes: Insights Into Heart Failure Risk and Muscle Biology.

Journal of the American College of Cardiology·2026
Same author

Survey to inform personalised prescribing in a British South Asian community: pharmacogenomics and traditional medicine use.

BMC medicine·2026
Same author

Shared proteomic landscape between arteriosclerosis and cardiovascular endpoints: a Mendelian randomization and observational study integrating AlphaFold3 for structural prediction.

Cardiovascular research·2026
Same author

Cardiovascular prescriber attitudes to pharmacogenomics: a survey by the ESC working group on cardiovascular pharmacotherapy.

The pharmacogenomics journal·2026
Same author

The future of pharmacogenomics in cardiovascular medicine.

Pharmacogenomics·2026
Same author

An epigenomic investigation of atrial fibrillation in a matched left and right atrial human cohort.

Clinical epigenetics·2026

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Vast numbers of single nucleotide polymorphisms (SNPs) are available in public databases.
  • Focus on non-synonymous protein coding SNPs (nsSNPs), which can be disease-associated or neutral.
  • Investigating nsSNP distribution using sequence and structural features.

Purpose of the Study:

  • Assess the predictive value of sequence and structural attributes for nsSNP function.
  • Evaluate machine learning methods for nsSNP function prediction.
  • Address dataset imbalance in machine learning for improved prediction accuracy.

Main Methods:

  • Utilized machine learning algorithms to predict nsSNP function.
  • Employed sequence and structural features for prediction.

Related Experiment Videos

  • Applied 100% undersampling of the majority class to balance datasets.

    • Main Results:

    • Dataset imbalance significantly impacts prediction success.
    • Balanced datasets with all attributes yield the best predictions.
    • Sequence conservation is the most crucial attribute; structural predictions also valuable.

    Conclusions:

    • Optimized nsSNP function prediction models using balanced datasets and comprehensive attributes.
    • Predictions for all Ensembl nsSNPs are accessible via DAS annotation.
    • Provided instructions for integrating Ensembl nsSNP predictions.