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

An improved method for identification of small non-coding RNAs in bacteria using support vector machine.

Ranjan Kumar Barman1, Anirban Mukhopadhyay2, Santasabuj Das1,3

  • 1Biomedical Informatics Centre, National Institute Of Cholera and Enteric Diseases, Kolkata, West Bengal, India.

Scientific Reports
|April 7, 2017
PubMed
Summary

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

Trends of severe human metapneumovirus infections in India.

BMC infectious diseases·2026
Same author

A Large Community Outbreak of Guillain-Barré Syndrome in Pune City, India, 2025.

The American journal of tropical medicine and hygiene·2026
Same author

From ecological foundations to nature-based solutions: A semantic-temporal scientometric analysis of urban expansion and green space research.

Journal of environmental management·2026
Same author

Third-generation cephalosporin-induced L-form transition in <i>Shigella sonnei</i> reveals a virulence-survival trade-off underlying persistent infection.

Microbiology spectrum·2026
Same author

Feline Assistance: Cats, unlike dogs and toddlers, help you only when it helps them.

Scientific American·2026
Same author

Polyphenols-rich Indian barberry berries extract alleviates inorganic arsenic exposure-induced cognitive impairments and associated gut microflora alterations.

Food research international (Ottawa, Ont.)·2026

This study introduces a computational method using support vector machines (SVM) to accurately predict bacterial small non-coding RNAs (sRNAs). The novel approach enhances the identification of these crucial functional RNAs in various bacterial species.

Area of Science:

  • Microbiology
  • Bioinformatics
  • Computational Biology

Background:

  • Bacterial small non-coding RNAs (sRNAs) are vital regulatory molecules involved in essential cellular processes.
  • Experimental identification of bacterial sRNAs is challenging and often incomplete, necessitating computational approaches.
  • Existing methods for sRNA detection require improvement in accuracy and scope.

Purpose of the Study:

  • To develop and validate a computational method for accurate prediction of bacterial sRNAs.
  • To leverage machine learning, specifically Support Vector Machines (SVM), for sRNA identification.
  • To assess the method's performance across different bacterial species.

Main Methods:

  • A Support Vector Machine (SVM) classifier was trained using sequence and structure features of experimentally validated sRNAs from Salmonella Typhimurium LT2.

Related Experiment Videos

  • Tri-nucleotide composition was identified as a key feature for SVM model optimization.
  • The developed SVM model was validated on datasets of experimentally detected sRNAs from E. coli and Salmonella Typhi.

    • Main Results:

    • The SVM model achieved high accuracy in predicting sRNAs, with 88.35% for Salmonella Typhimurium LT2.
    • Validation on E. coli K-12 and Salmonella Typhi Ty2 yielded accuracies of 81.25% and 88.82%, respectively.
    • A sliding window approach combined with the SVM model demonstrated high sensitivity in identifying sRNAs from complete bacterial genomes.

    Conclusions:

    • The proposed computational method significantly improves the identification of bacterial sRNAs.
    • The SVM-based approach offers a robust and accurate tool for bacterial sRNA discovery.
    • This method holds promise for advancing the study of bacterial regulatory networks and functions.