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

RNA-seq

RNA-seq

RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases.
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...

You might also read

Related Articles

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

Sort by

Same author

Genetic identification of Árpád Dynasty members from the ossuary of the Royal Basilica at Székesfehérvár.

iScience·2026

Same author

[Case report: VPS16 - a new cause of generalized dystonia].

Ideggyogyaszati szemle·2026

Same author

Ancient DNA evidence for the history of the Albanians.

Nature human behaviour·2026

Same author

Robust imputation-based method for eye, hair, and skin colour prediction from low-coverage ancient DNA.

Scientific reports·2026

Same author

Analysis of Transcript Expression and Core Promoter DNA Sequences of Brain, Adipose Tissues and Testis in Human and Fruit Fly.

International journal of molecular sciences·2025

Same author

Intellectual developmental disorder 56 associated with novel variants in the clathrin heavy chain encoding CLTC gene and brief review of the literature.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2025

Search research articles

Related Experiment Video

Updated: May 8, 2025

Detection of Copy Number Alterations Using Single Cell Sequencing

Detection of Copy Number Alterations Using Single Cell Sequencing

Published on: February 17, 2017

Optimizing sequence data analysis using convolution neural network for the prediction of CNV bait positions.

Zoltán Maróti¹, Peter Juma Ochieng^2,3,4, József Dombi^5,6

¹Albert Szent-Györgyi Health Centre, University of Szeged, Korányi fasor 14-15, Szeged, H-6725, Csongrád-Csanád, Hungary. maroti.zoltan@med.u-szeged.hu.

BMC Bioinformatics

|December 24, 2024

Summary

This study introduces a novel 1D convolution neural network (CNN) model to predict capture bait positions for improved copy number variation (CNV) analysis. This method enhances GC bias normalization in next-generation sequencing (NGS) data, boosting CNV detection accuracy.

Keywords:

Copy number variation Machine learning Oligo capture baits Targeted capture

More Related Videos

Informatic Analysis of Sequence Data from Batch Yeast 2-Hybrid Screens

Informatic Analysis of Sequence Data from Batch Yeast 2-Hybrid Screens

Published on: June 28, 2018

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Related Experiment Videos

Last Updated: May 8, 2025

Detection of Copy Number Alterations Using Single Cell Sequencing

Detection of Copy Number Alterations Using Single Cell Sequencing

Published on: February 17, 2017

Informatic Analysis of Sequence Data from Batch Yeast 2-Hybrid Screens

Informatic Analysis of Sequence Data from Batch Yeast 2-Hybrid Screens

Published on: June 28, 2018

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Area of Science:

Genomics
Bioinformatics
Computational Biology

Background:

Accurate copy number variation (CNV) detection from targeted capture next-generation sequencing (NGS) data requires effective normalization of read coverage profiles.
GC bias presents a significant challenge, impacting the sensitivity and specificity of CNV detection.
Limited information on exact oligo capture bait designs hinders precise normalization.

Purpose of the Study:

To develop a novel approach using a 1D convolution neural network (CNN) to predict capture bait positions in whole-exome sequencing (WES) kits.
To enable precise normalization of GC bias by accurately identifying bait coordinates.
To improve the overall normalization of CNV data.

Main Methods:

Utilized a 1D CNN model to predict the positions of capture baits.
Evaluated optimal hyperparameters, model architecture, and complexity for bait prediction.
Investigated the importance of spatiality and combined input data (experimental coverage, on-target information, sequence data).

Main Results:

CNN models demonstrated superior performance in predicting bait positions compared to Dense NN.
Batch normalization was identified as crucial for stable CNN model training.
The CNN models achieved high overlap (>90%) with true bait positions, especially when using combined input data.

Conclusions:

CNN-based approaches can optimize coverage data analysis for improved CNV normalization.
Accurate bait position prediction facilitates better GC bias normalization and reduces systemic bias.
This method enhances the sensitivity and specificity of CNV detection in genomic studies.