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 Concept Videos

Defense Against Bacterial Pathogens01:31

Defense Against Bacterial Pathogens

1.5K
The human immune system is a complex network of cells, tissues, and organs that work together to defend the body against bacterial infections. It consists of various immune cells, each playing a specific role in the defense mechanism.
Phagocytes
Phagocytes are the frontline soldiers of the immune system. They include neutrophils and macrophages. Neutrophils are the most abundant type of white blood cell and are quickly mobilized to the site of infection. Macrophages are larger cells that patrol...
1.5K
Modern Molecular Taxonomy01:29

Modern Molecular Taxonomy

159
Advancements in molecular biology have revolutionized the identification and characterization of bacteria, with multiple methods leveraging DNA sequencing for enhanced precision. As sequencing technologies improve and costs decline, these approaches are increasingly used in clinical, environmental, and evolutionary studies.Multilocus Sequence Typing (MLST) examines several housekeeping genes, essential chromosomal genes encoding cellular functions, to distinguish strains. Approximately...
159
Methods of Classification and Identification01:28

Methods of Classification and Identification

241
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
241

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Systems biology-based drug repurposing for neuroinflammation treatment in activated human microglia.

Scientific reports·2026
Same author

From gene correlations to cell clusters: COTAN improved scRNA-seq analysis.

NAR genomics and bioinformatics·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

Artificial intelligence-based characterization of multi-organ ultrasound congestion across the heart failure Spectrum.

European heart journal. Imaging methods and practice·2026
Same author

The elusive genomic signature of tadpole shrimps' ancient morphology.

Biology letters·2026
Same author

Alpha&ESMhFolds: An Updated Web Server for the Comparison, Evaluation, and Annotation of Human AlphaFold2 and ESMFold Models.

Journal of molecular biology·2026

Related Experiment Video

Updated: Sep 19, 2025

Use of an Influenza Antigen Microarray to Measure the Breadth of Serum Antibodies Across Virus Subtypes
08:52

Use of an Influenza Antigen Microarray to Measure the Breadth of Serum Antibodies Across Virus Subtypes

Published on: July 26, 2019

8.2K

A descriptor-free machine learning framework to improve antigen discovery for bacterial pathogens.

Marco Podda1, Castrense Savojardo2, Pier Luigi Martelli2

  • 1Department of Computer Science, University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, Italy.

Plos One
|June 5, 2025
PubMed
Summary

This study introduces protein sequence embeddings (PSEs) for bacterial vaccine target identification. The new PSE-based method outperforms traditional descriptor-based approaches, reducing the need for pre-clinical tests by up to 83%.

More Related Videos

Detection and Enrichment of Rare Antigen-specific B Cells for Analysis of Phenotype and Function
09:25

Detection and Enrichment of Rare Antigen-specific B Cells for Analysis of Phenotype and Function

Published on: February 16, 2017

12.4K
Automated, High-Throughput Detection of Bacterial Adherence to Host Cells
07:21

Automated, High-Throughput Detection of Bacterial Adherence to Host Cells

Published on: September 17, 2021

3.6K

Related Experiment Videos

Last Updated: Sep 19, 2025

Use of an Influenza Antigen Microarray to Measure the Breadth of Serum Antibodies Across Virus Subtypes
08:52

Use of an Influenza Antigen Microarray to Measure the Breadth of Serum Antibodies Across Virus Subtypes

Published on: July 26, 2019

8.2K
Detection and Enrichment of Rare Antigen-specific B Cells for Analysis of Phenotype and Function
09:25

Detection and Enrichment of Rare Antigen-specific B Cells for Analysis of Phenotype and Function

Published on: February 16, 2017

12.4K
Automated, High-Throughput Detection of Bacterial Adherence to Host Cells
07:21

Automated, High-Throughput Detection of Bacterial Adherence to Host Cells

Published on: September 17, 2021

3.6K

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Vaccine Development

Background:

  • Identifying bacterial protective antigens (PAs) for vaccine development is challenging due to the impracticality of large-scale in-vivo testing.
  • Reverse Vaccinology (RV) computationally screens proteomes, but traditional machine learning (ML) methods rely on potentially biased and complex descriptor-based protein representations.
  • Protein Sequence Embeddings (PSEs), derived from deep learning models, offer a data-driven, streamlined alternative for feature extraction in ML.

Purpose of the Study:

  • To introduce and evaluate Protein Sequence Embeddings (PSEs) as a descriptor-free feature representation for Machine Learning (ML) in Reverse Vaccinology (RV).
  • To compare the performance of PSE-based ML pipelines against traditional descriptor-based pipelines for identifying bacterial protective antigens (PAs).
  • To assess the utility of the PSE-based pipeline in ranking novel proteomes for pre-clinical vaccine candidate selection.

Main Methods:

  • Utilized Protein Sequence Embeddings (PSEs) generated by the FAIR ESM-2 protein language model as input for ML classifiers.
  • Developed and compared PSE-based and descriptor-based ML pipelines for PA classification across 10 bacterial species.
  • Evaluated pipeline performance using Area Under the Receiver Operating Characteristics curve (AUROC) and benchmark datasets (iBPA).

Main Results:

  • The PSE-based pipeline outperformed the descriptor-based pipeline in 9 out of 10 bacterial species, achieving a mean AUROC of 0.875 vs. 0.855.
  • The PSE approach showed superior performance on the iBPA benchmark (0.86 AUROC) compared to existing literature methods.
  • Ranking unseen proteomes using the PSE pipeline reduced the number of necessary pre-clinical tests for PA identification by an average of 83%.

Conclusions:

  • PSEs provide a robust and efficient descriptor-free method for ML-driven bacterial protective antigen identification within the Reverse Vaccinology framework.
  • The PSE-based pipeline significantly enhances the accuracy and efficiency of selecting vaccine candidates, streamlining the pre-clinical testing process.
  • This approach offers a powerful tool for accelerating vaccine development by prioritizing the most promising protective antigens.