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

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

Dissecting and directing pathology foundation models.

bioRxiv : the preprint server for biology·2026

Same author

An AI-Based OCT System to Detect Diabetic Macular Edema: A Prospective Validation and Noninferiority Randomized Clinical Trial.

JAMA·2026

Same author

Highly Myopic Macular Hole Surgery by the Internal Limiting Membrane Flap with No Gas Tamponade Technique: A Prospective Interventional Case Series.

Ophthalmology. Retina·2026

Same author

Designing DNA With Tunable Regulatory Activity Using Discrete Diffusion.

bioRxiv : the preprint server for biology·2026

Same author

Marine-derived products as pharmaceutical treasure troves: a focus on recent research techniques and potential bioactive activities of marine peptides.

Chinese journal of natural medicines·2026

Same author

Genetic background shapes AI-predicted variant effects.

bioRxiv : the preprint server for biology·2026

Same journal

Algorithm-hardware co-design of neuromorphic networks with dual memory pathways.

Nature machine intelligence·2026

Same journal

Plagiarism in the Age of Generative Artificial Intelligence: The advent of generative artificial intelligence (GenAI) tools is challenging the scientific community's understanding of the meaning and significance of plagiarism. A new definition of research misconduct is needed that specifically addresses the use of GenAI writing tools.

Nature machine intelligence·2026

Same journal

Platonic representation of foundation machine learning interatomic potentials.

Nature machine intelligence·2026

Same journal

Immunotherapy drug target identification using machine learning and patient-derived tumour explant validation.

Nature machine intelligence·2026

Same journal

A generative artificial intelligence approach for peptide antibiotic optimization.

Nature machine intelligence·2026

Same journal

LLMs displaying less cognitive bias are not necessarily better decision makers.

Nature machine intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 26, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Evaluating deep learning for predicting epigenomic profiles.

Shushan Toneyan¹, Ziqi Tang¹, Peter K Koo¹

¹Simons Center for Quantitative Biology, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, USA.

Nature Machine Intelligence

|June 16, 2023

Summary

This summary is machine-generated.

Quantitative deep learning models for epigenomic profiles show improved generalizability and interpretability over traditional binary classification methods. This unified framework aids in evaluating new models for biological discovery and variant effect prediction.

More Related Videos

Pattern-based Search of Epigenomic Data Using GeNemo

Pattern-based Search of Epigenomic Data Using GeNemo

Published on: October 8, 2017

Automating ChIP-seq Experiments to Generate Epigenetic Profiles on 10,000 HeLa Cells

Automating ChIP-seq Experiments to Generate Epigenetic Profiles on 10,000 HeLa Cells

Published on: December 10, 2014

Related Experiment Videos

Last Updated: Jul 26, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Pattern-based Search of Epigenomic Data Using GeNemo

Pattern-based Search of Epigenomic Data Using GeNemo

Published on: October 8, 2017

Automating ChIP-seq Experiments to Generate Epigenetic Profiles on 10,000 HeLa Cells

Automating ChIP-seq Experiments to Generate Epigenetic Profiles on 10,000 HeLa Cells

Published on: December 10, 2014

Area of Science:

Genomics
Computational Biology
Machine Learning

Background:

Deep learning models accurately predict epigenomic profiles from DNA sequences.
Current methods often use binary classification based on peak callers, limiting functional activity assessment.
Emerging quantitative models directly predict experimental coverage values via regression.

Purpose of the Study:

To introduce a unified evaluation framework for assessing deep learning models predicting chromatin accessibility.
To compare the performance of binary and quantitative models.
To identify modeling choices impacting generalization and utility for downstream biological discovery.

Main Methods:

Developed a unified evaluation framework for deep learning models.
Compared various binary and quantitative models trained on chromatin accessibility data.
Introduced a robustness metric for model selection and variant effect prediction.

Main Results:

Quantitative models demonstrated superior generalizability compared to binary models.
Identified key modeling choices influencing performance.
The robustness metric improved variant effect predictions.

Conclusions:

Quantitative modeling of epigenomic profiles offers better generalizability and interpretability.
The unified framework facilitates fair assessment of novel models.
Enhanced model selection through a robustness metric aids biological discovery.