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: Mar 30, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.5K

Semi-supervised prediction of gene regulatory networks using machine learning algorithms.

Nihir Patel1, Jason T L Wang

  • 1Bioinformatics Program, New Jersey Institute of Technology, Newark, NJ 07102, USA.

Journal of Biosciences
|November 14, 2015
PubMed
Summary

Semi-supervised machine learning improves gene regulatory network (GRN) prediction accuracy by using unlabeled data. Transductive learning approaches demonstrated superior performance over inductive methods for predicting GRNs in E. coli and S. cerevisiae.

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

FlareDB: A Database of Significant Flares in Solar Cycles 24 and 25 with SDO/HMI and SDO/AIA Observations.

Scientific data·2026
Same author

Distinctive genomic features of hydroa vacciniforme lymphoproliferative disorder in Latin American patients: A multicenter multi-omics study.

Journal of the American Academy of Dermatology·2025
Same author

A process optimization and release modeling of coaxial electrospun aligned core-shell poly (ethylene oxide-poly(l-lactide-co-glycolide)) nanofibers encapsulating nerve growth factor.

Journal of applied polymer science·2025
Same author

Goliath clades and <i>in vivo</i> tracking of clonal dynamics show three phases of UV-induced skin carcinogenesis.

bioRxiv : the preprint server for biology·2025
Same author

<i>HRAS</i>-Mutant Cardiomyocyte Model of Multifocal Atrial Tachycardia.

Circulation. Arrhythmia and electrophysiology·2024
Same author

Operational prediction of solar flares using a transformer-based framework.

Scientific reports·2023

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • Predicting gene regulatory networks (GRNs) from gene expression data is crucial for understanding cellular mechanisms.
  • Existing unsupervised methods often suffer from low prediction accuracy due to insufficient labeled training data.
  • Supervised methods also face challenges with limited labeled data for complex biological systems.

Purpose of the Study:

  • To develop and evaluate semi-supervised learning methods for enhanced GRN prediction.
  • To leverage unlabeled gene expression data to improve the accuracy of GRN inference.
  • To compare the performance of inductive and transductive learning approaches using Support Vector Machines (SVM) and Random Forests (RF).

Main Methods:

  • Proposed semi-supervised learning frameworks utilizing both Support Vector Machines (SVM) and Random Forests (RF).

More Related Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

3.1K

Related Experiment Videos

Last Updated: Mar 30, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.5K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

3.1K
  • Investigated inductive and transductive learning strategies, incorporating iterative procedures to generate reliable negative training data from unlabeled datasets.
  • Applied and validated the developed methods on gene expression datasets from Escherichia coli and Saccharomyces cerevisiae.

    • Main Results:

    • The transductive learning approach consistently outperformed the inductive learning approach for both E. coli and S. cerevisiae datasets.
    • No significant performance difference was observed between SVM and RF algorithms within the semi-supervised frameworks.
    • The proposed semi-supervised methods achieved superior GRN prediction performance compared to existing supervised methods for both organisms.

    Conclusions:

    • Semi-supervised learning, particularly the transductive approach, offers a promising strategy for improving GRN prediction accuracy.
    • The developed methods effectively utilize unlabeled data, addressing a key limitation of traditional approaches.
    • These findings provide a more robust computational framework for dissecting gene regulatory mechanisms in biological systems.