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 secondary structure prediction using nearest-neighbor methods

T M Yi1, E S Lander

  • 1Whitehead Institute for Biomedical Research, Cambridge, MA.

Journal of Molecular Biology
|August 20, 1993
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

Rare germline variants in ATM are associated with chronic lymphocytic leukemia.

Leukemia·2017
Same author

Whole-genome sequencing reveals activation-induced cytidine deaminase signatures during indolent chronic lymphocytic leukaemia evolution.

Nature communications·2015
Same author

SNP genotyping defines complex gene-flow boundaries among African malaria vector mosquitoes.

Science (New York, N.Y.)·2010
Same author

Genome sequence, comparative analysis, and population genetics of the domestic horse.

Science (New York, N.Y.)·2009
Same author

cDNA sequences for transcription factors and signaling proteins of the hemichordate Saccoglossus kowalevskii: efficacy of the expressed sequence tag (EST) approach for evolutionary and developmental studies of a new organism.

The Biological bulletin·2008
Same author

Distinct physiological states of Plasmodium falciparum in malaria-infected patients.

Nature·2007
Same journal

UPF3A and UPF3B shape the transcriptome cooperatively yet oppose cell function.

Journal of molecular biology·2026
Same journal

Antibody-secreting cells integrate efficient NMD with non‑canonical UPR signaling to maintain proteostasis and support massive immunoglobulin synthesis.

Journal of molecular biology·2026
Same journal

Small molecule stabilization of diverse amyloidogenic immunoglobulin light chains revealed by hydrogen-deuterium exchange mass spectrometry.

Journal of molecular biology·2026
Same journal

UPF1 at Work: Structural and Mechanistic Insights Into a Master Regulator of Nonsense-Mediated mRNA Decay.

Journal of molecular biology·2026
Same journal

Structural basis for the pro-amyloidogenic action and ligand binding of a novel W72R variant of human apolipoprotein A-I.

Journal of molecular biology·2026
Same journal

Cryo-EM Structure of the C. elegans Septin Tetramer Reveals a Revised Architecture and Conserved Positional Orthology.

Journal of molecular biology·2026
See all related articles

Nearest-neighbor classifiers improve protein secondary structure prediction accuracy. A novel approach provides probability estimates, increasing information content and enabling confident predictions for substantial protein segments.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Structural Biology

Background:

  • Accurate prediction of protein secondary structure is crucial for understanding protein function and design.
  • Traditional nearest-neighbor methods rely on fixed similarity metrics, potentially limiting prediction accuracy.

Purpose of the Study:

  • To enhance protein secondary structure prediction using an improved nearest-neighbor classification approach.
  • To develop a method for estimating prediction confidence and improving biological utility.

Main Methods:

  • Employed a novel similarity metric based on local structural environments for nearest-neighbor classification.
  • Modified the nearest-neighbor algorithm by introducing an 'effective radius' for exemplars.
  • Developed a nearest-neighbor estimator generating probability distributions over secondary structure states (helix, strand, coil).

Related Experiment Videos

Main Results:

  • Achieved a peak prediction accuracy of 68% for protein secondary structure.
  • Probability estimates provided 58% more information compared to traditional one-state predictions.
  • High accuracy (86%) was achieved for the top 28% of predictions, and 81% for the top 43%.

Conclusions:

  • The refined nearest-neighbor approach significantly improves protein secondary structure prediction.
  • Probability-based predictions enhance biological utility by providing confidence levels.
  • A substantial portion of protein secondary structure can be predicted with high accuracy, despite overall limitations.