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

Learning and alignment methods applied to protein structure prediction

J Gracy1, L Chiche, J Sallantin

  • 1Laboratoire d'Informatique, de Robotique et de Micro-électronique de Montpellier, France.

Biochimie
|January 1, 1993
PubMed
Summary

New algorithms predict protein structure by learning sequence-structure relationships. These methods optimize local fold propensity scores, improving protein structure prediction and alignment for weakly homologous proteins.

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

Extra-hepatic cholangiocarcinoma diagnosis: from classical pathological analysis to the emerging omics tests.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026
Same author

ASO Author's Reflections: Extrahepatic Cholangiocarcinoma as an Oncological Consistent Entity: Insights from Proteomic Profiling and Lack of Anatomical Impact.

Annals of surgical oncology·2025
Same author

Blurring the Anatomical Lines in Extrahepatic Cholangiocarcinoma: An Integrated Clinic-Oncological and Exploratory Proteomic Comparison of Perihilar and Distal Tumors.

Annals of surgical oncology·2025
Same author

[Between the normal and the pathological: The concept of pre-disease applied to systemic autoimmune rheumatic diseases].

La Revue de medecine interne·2024
Same author

Outcome and prognosis of isolated carotid vasculitis.

Journal of autoimmunity·2024
Same author

[Managing cancer immunotherapy toxicities: Challenges and rechallenges for (young) internists].

La Revue de medecine interne·2023

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Machine learning in protein science

Background:

  • Protein structure prediction is crucial for understanding biological function.
  • Existing methods often struggle with local fold prediction and alignment of weakly homologous proteins.

Purpose of the Study:

  • To develop novel algorithms for predicting local protein structure.
  • To enhance protein sequence-structure alignment using learned structural information.

Main Methods:

  • Developed two algorithms to optimize scores for polypeptide local fold propensity.
  • Algorithm 1: Generates secondary structure prediction rules from geometrical patterns.
  • Algorithm 2: Scores amino acid fit within local structural environments; uses dynamic programming for alignment.

Related Experiment Videos

Main Results:

  • Demonstrated system features on N-terminal domain of CD4 antigen.
  • Benchmarked usefulness of 3-D information in alignment using eight weakly homologous protein pairs.

Conclusions:

  • The developed learning techniques effectively extract structural knowledge from protein sequences.
  • The algorithms improve the accuracy of local fold prediction and protein alignment, particularly for challenging cases.