Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Learning regulatory programs that accurately predict differential expression with MEDUSA.

Anshul Kundaje¹, Steve Lianoglou, Xuejing Li

¹Department of Computer Science, Center for Computational Learning Systems, Columbia University, New York, NY 10065, USA.

Annals of the New York Academy of Sciences

|October 16, 2007

Summary

This summary is machine-generated.

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

BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics.

bioRxiv : the preprint server for biology·2026

Same author

Recurrent intra-tumour heterogeneity is a hallmark of metastatic prostate cancer.

Nature communications·2026

Same author

Author Correction: Ontogeny and transcriptional regulation of Thetis cells.

Nature·2026

Same author

Decoding common and rare noncoding variant effects across cellular and developmental contexts.

Nature genetics·2026

Same author

Chemically induced skin tumors arise from long-lived stem cells of the upper hair follicle.

Science (New York, N.Y.)·2026

Same author

On the subtleties of cluster construction when defining crystalline nuclei in atomistic simulations.

The Journal of chemical physics·2026

Same journal

Multiomics Profiling During Autoimmune Demyelination Highlights a Complex Regulatory Role for Ataxin-1 in B Cells.

Annals of the New York Academy of Sciences·2026

Same journal

Global Trends in Light Pollution and Their Relationship With Socioeconomic Factors.

Annals of the New York Academy of Sciences·2026

Same journal

Wired for Corruption: Inter-Brain Synchrony Encodes Bribery-Related Value Information and Predicts Bribery Agreement.

Annals of the New York Academy of Sciences·2026

Same journal

LM-YOLO: A Lightweight Multi-Scale Enhanced Model for Forest Smoke Detection Using Unmanned Aerial Vehicles.

Annals of the New York Academy of Sciences·2026

Same journal

Polyrhythm Perception and Production: A Scoping Review.

Annals of the New York Academy of Sciences·2026

Same journal

DARTS-CNN-BiLSTM: Intelligent Fault Diagnosis for Computer Numerical Control Machine Tool Feed System.

Annals of the New York Academy of Sciences·2026

See all related articles

MEDUSA, a machine learning algorithm, infers gene regulatory networks by integrating diverse genomic data. It accurately predicts gene expression changes, offering a validated approach for understanding transcriptional regulation.

Area of Science:

Computational biology
Bioinformatics
Systems biology

Background:

Inferring gene regulatory networks is crucial for understanding cellular mechanisms.
Existing methods often rely on clustering or correlation, which may not capture complex regulatory logic.

Purpose of the Study:

To introduce MEDUSA, a novel machine learning approach for inferring gene regulatory networks.
To predict target gene differential expression by integrating promoter sequences, mRNA expression, and transcription factor occupancy data.

Main Methods:

MEDUSA utilizes a boosting algorithm to predict gene expression, mitigating overfitting in high-dimensional data.
It identifies condition-specific regulators and regulatory motifs, modeling biological mechanisms of transcriptional regulation.

Related Experiment Videos

The approach integrates promoter sequence, mRNA expression, and transcription factor occupancy data.

Main Results:

MEDUSA achieves high prediction accuracy on unseen experimental data.
The algorithm successfully identifies key regulators and motifs in biological processes like DNA damage and hypoxia.
It provides a statistically sound method for validating reverse-engineered gene regulatory networks.

Conclusions:

MEDUSA offers a robust and validated method for inferring gene regulatory networks.
The predictive accuracy serves as a concrete measure for network validation, essential in the absence of a gold standard.
This approach facilitates hypothesis generation and network building in computational biology.