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

Next-generation Sequencing03:00

Next-generation Sequencing

86.2K
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....
86.2K
RNA-seq03:21

RNA-seq

9.7K
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...
9.7K
Sanger Sequencing01:57

Sanger Sequencing

751.3K
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...
751.3K

You might also read

Related Articles

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

Sort by
Same author

Fertility Alteration Characteristics and Cytological Mechanisms of Pollen Abortion in Thermo-Photo-Sensitive Genic Male Sterile Wheat K64S.

Plants (Basel, Switzerland)·2026
Same author

Dermal fibroblasts attenuate osteoarthritis by restoring synovial fibroblast homeostasis.

Journal of orthopaedic translation·2026
Same author

Optical metasurfaces for general vision processing on the edge.

Nature·2026
Same author

Beyond the virus: rethinking nasopharyngeal carcinoma through the gut microbiome.

Gut·2026
Same author

Leveraging natural climatic advantages for large‑scale wheat doubled haploid production via wheat × maize: a protocol optimization study.

BMC plant biology·2026
Same author

MADCrowner: Margin Aware Dental Crown design with template deformation and refinement.

Medical image analysis·2026

Related Experiment Video

Updated: May 13, 2025

Rare Event Detection Using Error-corrected DNA and RNA Sequencing
10:36

Rare Event Detection Using Error-corrected DNA and RNA Sequencing

Published on: August 3, 2018

11.9K

Transformer-based deep learning for accurate detection of multiple base modifications using single molecule real-time

Xi Hu1,2,3, Yuwei Shi1,2,3, Suk Hang Cheng1,2,3

  • 1Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.

Communications Biology
|April 14, 2025
PubMed
Summary
This summary is machine-generated.

A new hybrid AI model, HK model 2, significantly improves detection of DNA base modifications like 5-methylcytosine using single molecule sequencing. This versatile tool enhances liquid biopsy applications for diseases like cancer.

More Related Videos

Visual Detection of Multiple Nucleic Acids in a Capillary Array
08:56

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

7.2K
Author Spotlight: Advancements in DNA Nanosensors – Addressing Sensitivity and Selectivity Challenges in Molecular Detection
07:16

Author Spotlight: Advancements in DNA Nanosensors – Addressing Sensitivity and Selectivity Challenges in Molecular Detection

Published on: February 9, 2024

826

Related Experiment Videos

Last Updated: May 13, 2025

Rare Event Detection Using Error-corrected DNA and RNA Sequencing
10:36

Rare Event Detection Using Error-corrected DNA and RNA Sequencing

Published on: August 3, 2018

11.9K
Visual Detection of Multiple Nucleic Acids in a Capillary Array
08:56

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

7.2K
Author Spotlight: Advancements in DNA Nanosensors – Addressing Sensitivity and Selectivity Challenges in Molecular Detection
07:16

Author Spotlight: Advancements in DNA Nanosensors – Addressing Sensitivity and Selectivity Challenges in Molecular Detection

Published on: February 9, 2024

826

Area of Science:

  • Computational Biology
  • Genomics
  • Artificial Intelligence in Medicine

Background:

  • Previous work introduced the holistic kinetic model (HK model 1), a convolutional neural network (CNN) for 5-methylcytosine (5mC) detection via single molecule real-time (SMRT) sequencing.
  • The need for more accurate and versatile methods for detecting epigenetic modifications in DNA is critical for advancing diagnostics and understanding biological processes.

Purpose of the Study:

  • To develop an improved AI model (HK model 2) by integrating CNNs with transformer layers for enhanced DNA base modification detection.
  • To evaluate the performance of HK model 2 in detecting 5-methylcytosine (5mC), 5-hydroxymethylcytosine (5hmC), and N6-methyladenine (6mA) using SMRT sequencing.
  • To assess the utility of HK model 2 in clinical applications, specifically for detecting hepatocellular carcinoma (HCC) via cell-free DNA (cfDNA) analysis.

Main Methods:

  • Construction of a hybrid deep learning model (HK model 2) combining convolutional neural network (CNN) and transformer architectures.
  • Performance evaluation using SMRT sequencing data, focusing on the area under the receiver operating characteristic curve (AUC) for base modification detection.
  • Application of HK model 2 to analyze 5mC patterns in cfDNA for hepatocellular carcinoma detection and 6mA patterns for cfDNA end analysis.

Main Results:

  • HK model 2 achieved a significantly improved AUC of 0.99 for 5mC detection, compared to 0.91 for the previous HK model 1.
  • The model successfully detected other base modifications, including 5-hydroxymethylcytosine (5hmC) and N6-methyladenine (6mA).
  • Analysis of cfDNA revealed an AUC of 0.97 for detecting hepatocellular carcinoma patients using 5mC patterns. 6mA detection facilitated analysis of cfDNA ends and chromatin structures.

Conclusions:

  • HK model 2 represents a substantial advancement in AI-driven DNA base modification detection using SMRT sequencing.
  • The model's versatility extends its application to various epigenetic analyses and liquid biopsy diagnostics, including cancer detection.
  • HK model 2 enhances the utility of SMRT sequencing for diverse genomic and epigenomic research, as well as clinical applications.