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

Cancers Originate from Somatic Mutations in a Single Cell

Cancers Originate from Somatic Mutations in a Single Cell

Cancer arises from mutations in the critical genes that allow healthy cells to escape cell cycle regulation and acquire the ability to proliferate indefinitely. Though originating from a single mutation event in one of the originator cells, cancer progresses when the mutant cell lines continue to gain more and more mutations, and finally, become malignant. For example, chronic myelogenous leukemia (CML) develops initially as a non-lethal increase in white blood cells, which progressively...

You might also read

Related Articles

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

Sort by

Same author

Improving hit discovery by integrating activity cliff sensitivity into active learning.

Bioinformatics (Oxford, England)·2026

Same author

Data-Driven Discovery of Quaternary Ammonium Interlayers for Efficient and Thermally Stable Perovskite Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

Comprehensive discovery of m<sup>6</sup>A sites in the human transcriptome at single-molecule resolution.

Nature communications·2025

Same author

Unbiased microRNA-Disease Association Prediction Using ICD-11 Codes and Negative Sampling.

Pharmacology research & perspectives·2025

Same author

Transcriptome Transformer: improving patient survival prediction via multitask learning of transcriptomic and clinical features.

Briefings in bioinformatics·2025

Same author

Human cytomegalovirus long non-coding RNA counteracts nuclear cGAS to facilitate immune evasion.

Nature microbiology·2025

Search research articles

Related Experiment Video

Updated: Jul 20, 2025

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Published on: October 18, 2013

AIVariant: a deep learning-based somatic variant detector for highly contaminated tumor samples.

Hyeonseong Jeon^1,2, Junhak Ahn^2,3, Byunggook Na⁴

¹Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, 08826, Republic of Korea.

Experimental & Molecular Medicine

|July 31, 2023

Summary

Detecting somatic DNA variants in low-purity or low-depth tumor samples is difficult. AIVariant, a deep learning model trained on extensive real data, significantly improves variant detection accuracy, especially in challenging low-resource scenarios.

More Related Videos

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jul 20, 2025

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Published on: October 18, 2013

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Genomics
Bioinformatics
Cancer Research

Background:

Accurate detection of somatic DNA variants is crucial for cancer diagnosis and treatment.
Low tumor purity and sequencing depth in samples present significant challenges for variant identification.
Existing methods struggle to reliably detect variants in these difficult sample types.

Purpose of the Study:

To develop an advanced deep learning model for improved somatic DNA variant detection.
To address the limitations of current methods in low tumor purity and sequencing depth scenarios.
To create a robust model trained on a comprehensive dataset of actual positive and negative variants.

Main Methods:

Construction of an extended dataset including actual positive variants across diverse tumor purities and sequencing depths.
Inclusion of actual negative variants specifically derived from sequencer-specific errors.
Development and training of a deep learning model, AIVariant, on this curated dataset.

Main Results:

The AIVariant model demonstrated superior performance compared to existing methods.
Performance was particularly enhanced under conditions of low tumor purity and low sequencing depth.
The model effectively distinguishes true variants from sequencing errors.

Conclusions:

AIVariant offers a significant advancement in somatic DNA variant detection, especially for challenging samples.
The model's performance highlights the effectiveness of deep learning with comprehensive datasets.
This approach has the potential to improve diagnostic accuracy and guide personalized cancer therapies.