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

SNAP: predict effect of non-synonymous polymorphisms on function.

Yana Bromberg1, Burkhard Rost

  • 1Department of Biochemistry and Molecular Biophysics, Columbia University, 630 West 168th St., New York, NY 10032, USA. bromberg@rostlab.org

Nucleic Acids Research
|May 29, 2007
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

Whole metagenome sequencing: not deep enough for complete microbial function recovery.

Microbiome·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

Advances in Protein Function Prediction from the Fifth CAFA Challenge.

bioRxiv : the preprint server for biology·2026
Same author

Quantifying uncertainty in protein representations across models and tasks.

Nature methods·2026
Same author

Whole-genome prediction of bacterial pathogenic capacity on novel bacteria using protein language models with PathogenFinder2.

Bioinformatics (Oxford, England)·2026
Same author

Session Introduction: Biological molecular function: methods and benchmarks for finding function in biological dark matter.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026

Predicting the functional impact of genetic variations is crucial for understanding diseases. A new method, SNAP (screening for non-acceptable polymorphisms), accurately identifies non-neutral single nucleotide polymorphisms (SNPs) using sequence data.

Area of Science:

  • Genetics
  • Bioinformatics
  • Computational Biology

Background:

  • Single nucleotide polymorphisms (SNPs) are common genetic variations.
  • Non-synonymous SNPs can be functionally neutral or non-neutral, impacting protein function.
  • Identifying non-neutral SNPs is vital for disease research and understanding phenotypic fitness.

Purpose of the Study:

  • To introduce comprehensive datasets for evaluating SNP effect prediction methods.
  • To present SNAP (screening for non-acceptable polymorphisms), a novel neural network-based predictor for non-synonymous SNP functional effects.
  • To assess the performance of SNAP compared to existing methods.

Main Methods:

  • Developed SNAP, a neural network model utilizing sequence information, with optional functional and structural annotations.

Related Experiment Videos

  • Conducted a cross-validation test on over 80,000 mutants.
  • Evaluated prediction accuracy for both neutral and non-neutral substitutions.

    • Main Results:

    • SNAP achieved 80% accuracy in identifying non-neutral substitutions and 80% accuracy for neutral substitutions.
    • Demonstrated significant performance improvement over existing methods, particularly for challenging cases.
    • Introduced a reliable measure for prediction confidence, enabling focused analysis.

    Conclusions:

    • SNAP offers an improved approach for predicting the functional consequences of non-synonymous SNPs.
    • The reliability measure enhances the utility of SNP effect predictions for research applications.
    • SNAP provides a valuable tool for identifying disease-associated mutations and fitness-enhancing variations.