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

You might also read

Related Articles

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

Sort by
Same author

Non-invasive wood moisture sensing for arthropod infestation prevention using a circularly polarized high-isolation antenna system.

Scientific reports·2026
Same author

Meiotic pairing through barcode-like satellite DNA repeats.

Nature communications·2026
Same author

Early antifungal resistance prediction based on MALDI-TOF mass spectrometry and machine learning.

Scientific reports·2026
Same author

Prime editing of a pathogenic <i>Scn1a</i> allele ameliorates seizure phenotypes in a GEFS<sup>+</sup> mouse model.

Science translational medicine·2026
Same author

RNA-LNP-mediated in vivo prime editing corrects disease phenotypes in a mouse model of citrullinemia type I.

Science translational medicine·2026
Same author

Translational bioinformatics stalls at implementation.

Briefings in bioinformatics·2026

Related Experiment Video

Updated: Oct 23, 2025

Efficient PAM-Less Base Editing for Zebrafish Modeling of Human Genetic Disease with zSpRY-ABE8e
07:31

Efficient PAM-Less Base Editing for Zebrafish Modeling of Human Genetic Disease with zSpRY-ABE8e

Published on: February 17, 2023

1.3K

Predicting base editing outcomes with an attention-based deep learning algorithm trained on high-throughput target

Kim F Marquart1,2, Ahmed Allam3, Sharan Janjuha2

  • 1Institute of Molecular Health Sciences, ETH Zurich, Zurich, Switzerland.

Nature Communications
|August 26, 2021
PubMed
Summary
This summary is machine-generated.

Base editors are powerful genome editing tools, but their efficiency varies. This study introduces BE-DICT, a deep learning algorithm that accurately predicts base editing outcomes, enhancing their application in research and therapy.

More Related Videos

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
09:05

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

16
Functional Assessment of BRCA1 variants using CRISPR-Mediated Base Editors
09:22

Functional Assessment of BRCA1 variants using CRISPR-Mediated Base Editors

Published on: February 28, 2021

5.7K

Related Experiment Videos

Last Updated: Oct 23, 2025

Efficient PAM-Less Base Editing for Zebrafish Modeling of Human Genetic Disease with zSpRY-ABE8e
07:31

Efficient PAM-Less Base Editing for Zebrafish Modeling of Human Genetic Disease with zSpRY-ABE8e

Published on: February 17, 2023

1.3K
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
09:05

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

16
Functional Assessment of BRCA1 variants using CRISPR-Mediated Base Editors
09:22

Functional Assessment of BRCA1 variants using CRISPR-Mediated Base Editors

Published on: February 28, 2021

5.7K

Area of Science:

  • Molecular Biology
  • Genetics
  • Bioinformatics

Background:

  • Base editors are CRISPR-Cas based gene editing tools enabling precise DNA base transitions.
  • Current base editing technologies exhibit variable efficiencies across different genomic loci, limiting their therapeutic and research applications.

Purpose of the Study:

  • To develop a predictive model for base editing efficiency.
  • To enhance the accuracy and applicability of base editing technologies for genomic research and gene therapy.

Main Methods:

  • Extensive analysis of adenine- and cytosine base editors on a library of 28,294 lentivirally integrated genetic sequences.
  • Development of BE-DICT, an attention-based deep learning algorithm for predicting base editing outcomes.

Main Results:

  • BE-DICT achieves high accuracy in predicting base editing outcomes across diverse genomic loci.
  • The algorithm demonstrates versatility and can be trained on novel base editor variants.

Conclusions:

  • BE-DICT significantly improves the predictability of base editing, overcoming a major hurdle in the field.
  • This deep learning tool facilitates the broader application of base editing in fundamental research and the development of gene therapies.