Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Sanger Sequencing01:57

Sanger Sequencing

DNA sequencing is a fundamental technique that is routinely used in the biological sciences. This method can be applied to a range of questions at different scales - from the sequencing of a cloned DNA fragment or the study of a mutation in a gene up to whole-genome sequencing. However, despite the widespread use of sequencing today, it was not until 1977 that Fredrick Sanger and his collaborators developed the chain-termination method to decode DNA sequences. It relies on the separation of a...
Evolutionary Relationships through Genome Comparisons02:54

Evolutionary Relationships through Genome Comparisons

Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
RNA-seq03:21

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 microarray-based...
Next-generation Sequencing03:00

Next-generation Sequencing

The first human genome sequencing project cost $2.7 billion and was declared complete in 2003, after 15 years of international cooperation and collaboration between several research teams and funding agencies. Today, with the advent of next-generation sequencing technologies, the cost and time of sequencing a human genome have dropped over 100 fold.
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features.
DNA Microarrays02:34

DNA Microarrays

Microarrays are high-throughput and relatively inexpensive assays that can be automated to analyze large quantities of data at a time. They are used in genome-wide studies to compare gene or protein expression under two varied conditions, such as healthy and diseased states. Microarrays consist of glass or silica slides on which probe molecules are covalently attached through surface functionalization. Most commonly, the slides are prepared through the chemisorption of silanes to silica...
Nucleic Acid Structure01:25

Nucleic Acid Structure

The pentose sugar in DNA is deoxyribose, while in RNA the pentose sugar is ribose. The difference between the sugars is the presence of the hydroxyl group on the ribose's second carbon and a hydrogen on the deoxyribose's second carbon. The phosphate residue attaches to the hydroxyl group of the 5′ carbon of one sugar and the hydroxyl group of the 3′ carbon of the sugar of the next nucleotide, which forms  a 5′ to 3′ phosphodiester linkage.
DNA Structure
DNA has a double-helix structure. The...

You might also read

Related Articles

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

Sort by
Same author

Complete end-to-end learning from protein feature representation to protein interactome inference.

GigaScience·2025
Same author

A large language model framework for literature-based disease-gene association prediction.

Briefings in bioinformatics·2025
Same author

Discovery and prioritization of genetic determinants of kidney function in 297,355 individuals from Taiwan and Japan.

Nature communications·2024
Same author

Predicting splicing patterns from the transcription factor binding sites in the promoter with deep learning.

BMC genomics·2024
Same author

High-Performance Poly(3-hexyl thiophene)-Based Organic Photovoltaics with Side-Chain Engineering of Core Units of Small Molecule Acceptors.

ACS applied materials & interfaces·2023
Same author

A feature extraction free approach for protein interactome inference from co-elution data.

Briefings in bioinformatics·2023
Same journal

Literature-informed gene extraction and ranking for multimodal data fusion.

Briefings in bioinformatics·2026
Same journal

SA-MTP: a structure-aware framework for multifunctional therapeutic peptide annotation.

Briefings in bioinformatics·2026
Same journal

Genome assemblies and annotations are not static and need support for tracking their evolution.

Briefings in bioinformatics·2026
Same journal

A historical journey of metabolite-protein interaction discovery: from data harmonization to AI-driven prediction.

Briefings in bioinformatics·2026
Same journal

Bridging local-global transmembrane protein contexts with contrastive pretraining for alignment-free pathogenicity prediction.

Briefings in bioinformatics·2026
Same journal

Prediction of drug hypersensitivity by comprehensive modeling of HLA-peptidomes.

Briefings in bioinformatics·2026
See all related articles

Related Experiment Video

Updated: Jul 5, 2026

Pattern-based Search of Epigenomic Data Using GeNemo
06:38

Pattern-based Search of Epigenomic Data Using GeNemo

Published on: October 8, 2017

DNA-DETR: sequence representation matters in object detection for functional genomic elements.

Bing-Shiun Tsai1, Jin-Yung Wong1,2, Huai-Kuang Tsai1

  • 1Institute of Information Science, Academia Sinica, Academia Road, Section 2, Nankang, Taipei, 11529, Taiwan.

Briefings in Bioinformatics
|July 3, 2026
PubMed
Summary
This summary is machine-generated.

Object detection models struggle with genomic sequences due to poor data representation. Combining sequence representations significantly improves Non-B DNA detection accuracy, highlighting the importance of feature selection in genomic analysis.

Keywords:
DETRfunctional genomic elementsobject detectionsequence representationtransformer

More Related Videos

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay (EMSA) and DNA-affinity Precipitation Assay (DAPA)
11:35

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay (EMSA) and DNA-affinity Precipitation Assay (DAPA)

Published on: August 21, 2016

Robust 3D DNA FISH Using Directly Labeled Probes
12:16

Robust 3D DNA FISH Using Directly Labeled Probes

Published on: August 15, 2013

Related Experiment Videos

Last Updated: Jul 5, 2026

Pattern-based Search of Epigenomic Data Using GeNemo
06:38

Pattern-based Search of Epigenomic Data Using GeNemo

Published on: October 8, 2017

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay (EMSA) and DNA-affinity Precipitation Assay (DAPA)
11:35

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay (EMSA) and DNA-affinity Precipitation Assay (DAPA)

Published on: August 21, 2016

Robust 3D DNA FISH Using Directly Labeled Probes
12:16

Robust 3D DNA FISH Using Directly Labeled Probes

Published on: August 15, 2013

Area of Science:

  • Genomics
  • Bioinformatics
  • Machine Learning

Background:

  • Object detection models excel in image analysis but are underutilized in genomic sequence analysis.
  • Existing methods often fail to capture essential structural features of DNA elements like Non-B DNA.

Purpose of the Study:

  • To adapt the DETR (DEtection TRansformer) architecture for 1D genomic object detection, termed DNA-DETR.
  • To investigate the impact of different sequence representations on the performance of genomic object detection models.

Main Methods:

  • Implemented DNA-DETR, an adaptation of the DETR architecture for DNA sequences.
  • Evaluated various sequence representations: one-hot encoding, dot matrix, and combined approaches.
  • Assessed model performance in classifying and localizing genomic elements, focusing on Non-B DNA.

Main Results:

  • Direct application of object detection with standard representations yielded suboptimal results for Non-B DNA.
  • The choice of sequence representation significantly impacts detection accuracy and model generalization.
  • Combined representations consistently outperformed single representations, especially for complex DNA elements.

Conclusions:

  • A universal 'one-representation-fits-all' approach is not suitable for genomic sequence feature learning.
  • Thoughtful selection of sequence representation remains critical for designing effective deep learning models in genomics, even with end-to-end learning architectures.