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

A neural-network-based method for predicting protein stability changes upon single point mutations.

Emidio Capriotti1, Piero Fariselli, Rita Casadio

  • 1Laboratory of Biocomputing, CIRB/Department of Biology, University of Bologna, Bologna, Italy.

Bioinformatics (Oxford, England)
|July 21, 2004
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

Survival prediction from neural parametrization of diffusive processes.

Physical review. E·2026
Same author

Computational Resources for Molecular Biology 2026.

Journal of molecular biology·2026
Same author

Update of the MSKCC nomogram for metastatic progression and its role in active surveillance: the Italian TPCP cohort.

Frontiers in oncology·2026
Same author

Environmental Personal Exposure Clusters to Investigate Multiple Sclerosis and Amyotrophic Lateral Sclerosis Progression.

Studies in health technology and informatics·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

A machine learning-derived cardiovascular risk score in people with HIV: the ML-ICONA score.

American journal of preventive cardiology·2026
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

A new neural network method accurately predicts protein stability changes from mutations, classifying over 80% correctly. This advance aids protein design by improving stability predictions and complementing existing methods.

Area of Science:

  • Biochemistry
  • Computational Biology
  • Bioinformatics

Background:

  • Predicting protein stability changes upon mutation is crucial for protein design.
  • Existing methods lack direct statistical evaluation and comparison.
  • The ProTherm database provides thermodynamic data for protein stability changes.

Purpose of the Study:

  • To develop a neural-network-based method for predicting protein thermodynamic stability changes upon mutation.
  • To evaluate the prediction performance against existing methods.
  • To enhance protein design strategies.

Main Methods:

  • Utilized a neural network approach for predicting stability changes.
  • Trained and tested the model on a dataset of 1615 mutations from the ProTherm database.

Related Experiment Videos

  • Integrated the neural network predictor with energy-based methods.

    • Main Results:

    • The neural network predictor achieved over 80% accuracy in classifying mutations.
    • Outperformed other available web-based methods on the same dataset.
    • Coupling with energy-based methods increased prediction accuracy to 90%.

    Conclusions:

    • The developed neural network method is effective for predicting protein stability changes.
    • The method shows potential for improving protein design strategies.
    • It can enhance the performance of existing prediction tools.