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 to discriminate between ligand-bound and disulfide-bound cysteines.

Andrea Passerini1, Paolo Frasconi

  • 1Dipartimento di Sistemi e Informatica, Università a di Firenze, 50139 Firenze, Italy. passerini@dsi.unifi.it

Protein Engineering, Design & Selection : PEDS
|May 29, 2004
PubMed
Summary

This study introduces a machine learning approach to differentiate cysteines in proteins, improving accuracy over existing methods. The new technique accurately predicts cysteine roles in ligand binding versus disulfide bridge formation.

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

Towards a more reliable assessment of aortic diameters using a Bayesian Z-score.

Scientific reports·2026
Same author

Monitoring optical properties of atmospheric aerosols at dome C, East Antarctic Plateau, provides insights into radiative transfer estimates.

Scientific reports·2025
Same author

Automatic CTA analysis for blood vessels and aneurysm features extraction in EVAR planning.

Scientific reports·2025
Same author

Fostering effective hybrid human-LLM reasoning and decision making.

Frontiers in artificial intelligence·2025
Same author

Deep learning-based localization algorithms on fluorescence human brain 3D reconstruction: a comparative study using stereology as a reference.

Scientific reports·2024
Same author

Corrigendum to "Machine learning approach for prediction of outcomes in anticoagulated patients with atrial fibrillation" [International Journal of Cardiology 407 (2024) 132088].

International journal of cardiology·2024

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning in structural biology

Background:

  • Cysteine residues in proteins play critical roles in both ligand binding and structural integrity via disulfide bridges.
  • Distinguishing between these functional types of cysteines is essential for understanding protein function and drug design.
  • Current methods, such as PROSITE patterns, have limitations in accurately classifying cysteine roles.

Purpose of the Study:

  • To develop and evaluate a novel machine learning method for accurate discrimination between ligand-binding cysteines and disulfide-bonding cysteines.
  • To assess the performance of the proposed method against existing pattern-based approaches.

Main Methods:

  • Utilizing a machine learning framework employing support vector machines (SVMs) with a polynomial kernel.

Related Experiment Videos

  • Representing each cysteine instance using a window of multiple sequence alignment profiles.
  • Exploring two novel kernel functions derived from similarity matrices to enhance SVM performance.

    • Main Results:

    • The developed machine learning method achieved significantly higher accuracy in predicting cysteine binding type compared to PROSITE patterns.
    • The novel kernel functions demonstrated potential for further improving prediction accuracy.

    Conclusions:

    • Machine learning, particularly SVMs with alignment profiles, offers a powerful and accurate approach for classifying cysteine functions in proteins.
    • This method provides a valuable tool for structural biology and drug discovery, enabling better prediction of protein-ligand interactions and protein stability.