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

CRISPR and crRNAs02:53

CRISPR and crRNAs

Bacteria and archaea are susceptible to viral infections just like eukaryotes; therefore, they have developed a unique adaptive immune system to protect themselves. Clustered regularly interspaced short palindromic repeats and CRISPR-associated proteins (CRISPR-Cas) are present in more than 45% of known bacteria and 90% of known archaea.
The CRISPR-Cas system stores a copy of foreign DNA in the host genome and uses it to identify the foreign DNA upon reinfection. CRISPR-Cas has three different...
CRISPR01:59

CRISPR

Genome editing technologies allow scientists to modify an organism’s DNA via the addition, removal, or rearrangement of genetic material at specific genomic locations. These types of techniques could potentially be used to cure genetic disorders such as hemophilia and sickle cell anemia. One popular and widely used DNA-editing research tool that could lead to safe and effective cures for genetic disorders is the CRISPR-Cas9 system. CRISPR-Cas9 stands for Clustered Regularly Interspaced Short...
CRISPR01:59

CRISPR

Genome editing technologies allow scientists to modify an organism’s DNA via the addition, removal, or rearrangement of genetic material at specific genomic locations. These types of techniques could potentially be used to cure genetic disorders such as hemophilia and sickle cell anemia. One popular and widely used DNA-editing research tool that could lead to safe and effective cures for genetic disorders is the CRISPR-Cas9 system. CRISPR-Cas9 stands for Clustered Regularly Interspaced Short...
CRISPR/Cas9 Genome Editing01:28

CRISPR/Cas9 Genome Editing

The CRISPR-Cas system serves as a bacterial defense mechanism against invading genetic elements such as viruses and plasmids, forming the foundation for its adaptation as a powerful genome-editing tool. Originally discovered in prokaryotes, this system has been repurposed to revolutionize genetic engineering across a wide range of organisms, including plants, animals, and humans. The core component, Cas9, is an endonuclease derived from Streptococcus pyogenes, capable of introducing...

You might also read

Related Articles

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

Sort by
Same author

CasGen: A Regularized Generative Model for CRISPR Cas Protein Design with Classification and Margin-Based Optimization.

bioRxiv : the preprint server for biology·2025
Same author

Identification of Family-Specific Features in Cas9 and Cas12 Proteins: A Machine Learning Approach Using Complete Protein Feature Spectrum.

Journal of chemical information and modeling·2024
Same author

Genetic engineering of the green alga Chlorella zofingiensis: a modified norflurazon-resistant phytoene desaturase gene as a dominant selectable marker.

Applied microbiology and biotechnology·2014
Same author

Successful one-stage extraction of an intracardiac and intravenous leiomyoma through the right atrium under transesophageal ultrasound monitoring.

Canadian journal of anaesthesia = Journal canadien d'anesthesie·2014
Same author

A particle swarm optimization variant with an inner variable learning strategy.

TheScientificWorldJournal·2014
Same author

Integrative Analysis of Cancer Diagnosis Studies with Composite Penalization.

Scandinavian journal of statistics, theory and applications·2014
Same journal

A Multi-Modal Framework for Phage-Host Interaction Prediction Using Multi-View Contrastive Learning.

IEEE transactions on computational biology and bioinformatics·2026
Same journal

Decoding Gene-Disease Associations with Computational Methods: A Survey.

IEEE transactions on computational biology and bioinformatics·2026
Same journal

A Competitive Coevolution-based Cancer Driver Pathway Identification Algorithm for Maximizing Coverage, Mutual Exclusivity, and Subnet Importance.

IEEE transactions on computational biology and bioinformatics·2026
Same journal

Prediction of GO Terms Based on Partitioning PPI Networks into Highly Connected Components.

IEEE transactions on computational biology and bioinformatics·2026
Same journal

Modeling and Tracking of Heterogeneous Cell Populations via Open Multi-Agent Systems.

IEEE transactions on computational biology and bioinformatics·2026
Same journal

Parameter Efficient Deep Learning Models for Multi-Target Binding Affinity and hERG Cardiotoxicity Prediction.

IEEE transactions on computational biology and bioinformatics·2026
See all related articles

Related Experiment Video

Updated: May 16, 2026

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks
07:02

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

Published on: May 17, 2020

Robust CRISPR-Cas Protein Identification using Max-Margin Regularized Transformer Models.

Bharani Nammi, Sita Sirisha Madugula, Vindi M Jayasinghe-Arachchige

    IEEE Transactions on Computational Biology and Bioinformatics
    |May 14, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Deep learning models, including a novel Latent Space Regularized Max-Margin Transformer (LSRMT), accurately classify CRISPR-Cas proteins. The LSRMT model shows superior performance, advancing genome editing research.

    More Related Videos

    Precise Phage Mutagenesis with NgTET-Assisted CRISPR-Cas Systems
    10:52

    Precise Phage Mutagenesis with NgTET-Assisted CRISPR-Cas Systems

    Published on: October 14, 2025

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    Related Experiment Videos

    Last Updated: May 16, 2026

    TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks
    07:02

    TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

    Published on: May 17, 2020

    Precise Phage Mutagenesis with NgTET-Assisted CRISPR-Cas Systems
    10:52

    Precise Phage Mutagenesis with NgTET-Assisted CRISPR-Cas Systems

    Published on: October 14, 2025

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    Area of Science:

    • Bioinformatics and Computational Biology
    • Molecular Biology and Genomics
    • Artificial Intelligence in Life Sciences

    Background:

    • The CRISPR-Cas system revolutionized genome editing but faces challenges in protein size, delivery, and specificity.
    • Understanding CRISPR-Cas proteins is crucial for developing improved genome editing tools and novel Cas proteins.
    • Current limitations necessitate advanced computational approaches for classifying and characterizing Cas proteins.

    Purpose of the Study:

    • To develop and evaluate deep learning models for classifying CRISPR-Cas proteins and their subfamilies (Cas9, Cas12).
    • To differentiate between Cas and non-Cas proteins using advanced machine learning techniques.
    • To enhance the robustness and generalization capabilities of protein classification models.

    Main Methods:

    • Development of two deep learning models: a transformer encoder trained from scratch and a fine-tuned ProtBert model.
    • Introduction of a novel margin-based loss function (Max-Margin) to improve latent space representation in the transformer model.
    • Extensive classification tasks including Cas9 vs. non-Cas, Cas12 vs. non-Cas, Cas9 vs. Cas12, and multi-class classification.

    Main Results:

    • The Fine-Tuned ProtBert-based (FTPB) model achieved high accuracies (up to 99.06%).
    • The Latent Space Regularized Max-Margin Transformer (LSRMT) model demonstrated superior performance, reaching up to 99.81% accuracy.
    • The LSRMT model outperformed a state-of-the-art large protein model, even with a smaller training dataset, highlighting its efficiency and generalization.

    Conclusions:

    • Deep learning, particularly the LSRMT model with Max-Margin regularization, is highly effective for classifying CRISPR-Cas proteins.
    • The LSRMT model's proficiency in identifying discriminative features of Cas proteins advances understanding of their structures.
    • This work represents a significant step towards the design and discovery of novel Cas proteins for improved genome editing applications.