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

Principles of Pharmacogenetics: Types of Genetic Variants

Principles of Pharmacogenetics: Types of Genetic Variants

The human genome is over 99.9% identical between individuals, yet genetic differences exist at millions of bases. The human genome contains approximately 3 million variant positions per individual, many of which are heterozygous, contributing to genetic diversity and individual traits. Genetic variations include single-nucleotide polymorphisms (SNPs), insertions, deletions, and copy number variations (CNVs).SNPs, the most common variation, involve single-base changes in DNA. These can be...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multi-ancestry transcriptome-wide association studies uncover insights into breast cancer genetics and biology.

Nature communications·2026

Same author

Long-Term Outcomes of Patients With BRCA+ or PALB2+ Pancreatic Cancer Treated With Maintenance Rucaparib: A Secondary Analysis of a Nonrandomized Clinical Trial.

JAMA oncology·2026

Same author

Comparative analysis of distinct genomic landscapes in young-onset gBRCA1/2 breast cancer.

JCI insight·2026

Same author

The arrival of digital twins and in silico trials in drug development.

Nature medicine·2026

Same author

Utah's Prescription-Renewal Pilot Program - Autonomous AI Managing Patient Care.

The New England journal of medicine·2026

Same author

Inflammatory biomarkers have a prognostic role in patients with metastatic castration-resistant prostate cancer treated with Lutetium-177-PSMA-617.

Cancer·2026

Search research articles

Related Experiment Video

Updated: May 11, 2026

In Vivo Modeling of the Morbid Human Genome using Danio rerio

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

Phenotypic evaluation of deep learning models for classifying germline variant pathogenicity.

Ryan D Chow¹, Katherine L Nathanson^2,3, Ravi B Parikh^4,5,6,7

¹Department of Medicine, Hospital of the University of Pennsylvania, Philadelphia, PA, USA. chowr@pennmedicine.upenn.edu.

NPJ Precision Oncology

|October 19, 2024

Summary

Deep learning models show promise for predicting hereditary breast cancer risk from genetic variants. However, their clinical utility is limited for variants of uncertain significance, especially in genes like ATM and CHEK2.

More Related Videos

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Published on: January 16, 2019

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

Related Experiment Videos

Last Updated: May 11, 2026

In Vivo Modeling of the Morbid Human Genome using Danio rerio

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation

Published on: January 16, 2019

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

Area of Science:

Genomics
Bioinformatics
Computational Biology

Background:

Predicting the pathogenicity of genetic variants is crucial for diagnosing hereditary diseases.
Deep learning models offer advanced computational approaches for variant pathogenicity prediction.
Real-world clinical validation of these models, particularly for hereditary breast cancer, is essential.

Purpose of the Study:

To evaluate the performance of state-of-the-art deep learning pathogenicity prediction models.
To assess the association of model predictions with clinical phenotypes (breast cancer risk) in a large cohort.
To determine the clinical utility of these models for variants of uncertain significance in hereditary breast cancer genes.

Main Methods:

Application of deep learning pathogenicity prediction models.
Analysis of missense variants in key hereditary breast cancer genes (BRCA1, BRCA2, PALB2, ATM, CHEK2).
Utilizing UK Biobank participant data linking genetic variants to breast cancer risk.

Main Results:

Model predictions for missense variants in BRCA1, BRCA2, and PALB2 were associated with breast cancer risk.
No significant association was found for ATM and CHEK2 variants.
Deep learning models demonstrated limited clinical utility when applied to variants of uncertain significance.

Conclusions:

Deep learning models show potential for predicting breast cancer risk associated with certain genetic variants.
The clinical utility of these models is currently restricted, particularly for variants of uncertain significance.
Further refinement and validation are needed for broader clinical application in hereditary cancer genetics.