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

You might also read

Related Articles

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

Sort by
Same author

How not to be seen: predicting unseen enzyme functions using contrastive learning.

Bioinformatics (Oxford, England)·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

How Not to be Seen: Predicting Unseen Enzyme Functions using Contrastive Learning.

bioRxiv : the preprint server for biology·2026
Same author

A PLUM Job: Peptide modeLs for Understanding and engineering antiMicrobial therapeutics.

bioRxiv : the preprint server for biology·2026
Same author

Advances in Protein Function Prediction from the Fifth CAFA Challenge.

bioRxiv : the preprint server for biology·2026
Same author

LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models.

ArXiv·2026

Related Experiment Video

Updated: Jan 9, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.4K

Identifying antimicrobial peptides using word embedding with deep recurrent neural networks.

Md-Nafiz Hamid1,2, Iddo Friedberg1,2

  • 1Interdepartmental program in Bioinformatics and Computational Biology.

Bioinformatics (Oxford, England)
|November 13, 2018
PubMed
Summary

Researchers developed a novel method using word embeddings to discover new bacteriocins, which are antimicrobial peptides, to combat antibiotic resistance. This approach bypasses traditional sequence similarity searches, identifying six potential new bacteriocins.

More Related Videos

Production and Visualization of Bacterial Spheroplasts and Protoplasts to Characterize Antimicrobial Peptide Localization
10:13

Production and Visualization of Bacterial Spheroplasts and Protoplasts to Characterize Antimicrobial Peptide Localization

Published on: August 11, 2018

12.6K
Antimicrobial Peptides Produced by Selective Pressure Incorporation of Non-canonical Amino Acids
11:56

Antimicrobial Peptides Produced by Selective Pressure Incorporation of Non-canonical Amino Acids

Published on: May 4, 2018

13.0K

Related Experiment Videos

Last Updated: Jan 9, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.4K
Production and Visualization of Bacterial Spheroplasts and Protoplasts to Characterize Antimicrobial Peptide Localization
10:13

Production and Visualization of Bacterial Spheroplasts and Protoplasts to Characterize Antimicrobial Peptide Localization

Published on: August 11, 2018

12.6K
Antimicrobial Peptides Produced by Selective Pressure Incorporation of Non-canonical Amino Acids
11:56

Antimicrobial Peptides Produced by Selective Pressure Incorporation of Non-canonical Amino Acids

Published on: May 4, 2018

13.0K

Area of Science:

  • Microbiology and Bioinformatics
  • Drug Discovery and Antimicrobial Peptides

Background:

  • Antibiotic resistance is a critical global health challenge requiring new antimicrobial agents.
  • Bacteriocins, antimicrobial peptides produced by bacteria, show promise but are difficult to discover using traditional genomic methods due to sequence variability.

Purpose of the Study:

  • To develop a novel computational method for identifying bacteriocins without relying on sequence similarity.
  • To explore the potential of word embeddings in representing protein sequences for antimicrobial peptide discovery.

Main Methods:

  • Utilized protein sequence word embeddings that capture amino acid order.
  • Applied these embeddings to predict novel bacteriocins from protein sequences, bypassing sequence similarity searches.
  • Focused on bacteriocin identification within the Lactobacillus genus.

Main Results:

  • Successfully predicted six previously unknown putative bacteriocins in Lactobacillus with high probability.
  • Demonstrated the efficacy of word embeddings in identifying bacteriocins, overcoming limitations of sequence similarity.

Conclusions:

  • Word embeddings preserving sequence order offer a powerful approach for peptide and protein classification, particularly for discovering novel antimicrobial peptides like bacteriocins.
  • This method provides a valuable tool for expanding the repertoire of antimicrobials to address the antibiotic resistance crisis.