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 Video

Updated: May 16, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Hybrid Feature Selection-Based Machine Learning and Deep Learning Framework for Biomarker Prediction From RNA-seq

Srilekha Anumulapuri1,2, Jhansi Venkata Nagamani Josyula1,2, Agiesh Kumar Balakrishna Pillai3

  • 1Department of Applied Biology & Centre for Information Technology, CSIR-Indian Institute of Chemical Technology, Hyderabad, India.

Evolutionary Bioinformatics Online
|May 15, 2026
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

Interferon Inducible Guanylate Binding Protein 5 (GBP5) and Its Association With Oxidative Stress Markers in Regulating Dengue Severity: A Clinical and In Vitro Evaluation.

Journal of medical virology·2026
Same author

Green synthesis of silver nanoparticles using Padina tetrastromatica against malaria and deciphering the mechanism through machine learning-driven metabolomics and network pharmacology.

Molecular omics·2026
Same author

Exploring potential gene signatures in dengue through machine learning and deep learning approaches.

Virus genes·2025
Same author

Mycosynthesised iron oxide nanoparticles using <i>Apiospora aurea</i>: Mitigating somatic and germline toxicity for safer biomedical applications.

Journal of biomaterials applications·2025
Same author

Guanylate binding proteins (GBPs) as novel therapeutic targets against single-stranded RNA viruses.

Molecular biology reports·2025
Same author

Revealing COVID-19 breakthrough infection rates among vaccinated individuals at a tertiary care centre in South India.

Iranian journal of microbiology·2025

Identifying transcriptomic signatures can help distinguish severe dengue from dengue fever. Machine learning models, particularly Transformer-CNN, show promise for early risk stratification in dengue virus infection.

Area of Science:

  • * Transcriptomics and bioinformatics analysis
  • * Computational biology and machine learning applications in infectious diseases

Background:

  • * Severe dengue (SD) is a life-threatening progression of dengue virus infection.
  • * Early identification of patients at risk for SD is a clinical challenge.
  • * Understanding transcriptomic changes may enable timely therapeutic interventions.

Purpose of the Study:

  • * To identify transcriptomic signatures differentiating severe dengue (SD) from dengue fever (DF).
  • * To develop and evaluate machine learning models for classifying SD and DF.
  • * To uncover biological pathways associated with dengue severity.

Main Methods:

  • * RNA-sequencing data from 103 samples (62 SD, 41 DF) were analyzed.
  • * Differential gene expression analysis and functional enrichment were performed.
Keywords:
artificial neural networksferroptosislogistic regressionrandom forestsevere denguesupport vector machinetransformer

Related Experiment Videos

Last Updated: May 16, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

  • * Hybrid machine learning and deep learning models (including Transformer-CNN) were applied for classification.

    • Main Results:

    • * 55 significantly dysregulated genes were identified between SD and DF.
    • * Enriched pathways include metal ion homeostasis, platelet signaling, and ferroptosis.
    • * Transformer-CNN model achieved high performance (AUC=0.85, balanced accuracy=0.89), highlighting key genes like ILDR2 and TCP1.

    Conclusions:

    • * RNA-seq integrated with AI modeling identified transcriptomic signatures for dengue severity.
    • * Candidate genes and pathways provide a foundation for further research.
    • * Experimental validation and larger sample sizes are needed for clinical risk stratification.