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

You might also read

Related Articles

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

Sort by

Same author

Structome-TM: complementing dataset assembly for structural phylogenetics by addressing size-based biases.

Bioinformatics advances·2026

Same author

SGGly: a web server for whole-protein, structure-guided analysis of candidate N-linked glycosylation sites.

Nucleic acids research·2026

Same author

A three generation family with VACTERL association is found to have a rare form of diamond-blackfan anaemia.

European journal of human genetics : EJHG·2026

Same author

Systematic evaluation of computational tools to predict the effects of mutations on protein-ligand binding affinity in the absence of experimental structures.

Briefings in bioinformatics·2026

Same author

Structome-AlignViewer: On Confidence Assessment in Structure-Aware Alignments.

Genome biology and evolution·2026

Same author

kinCSM-RTK: Machine Learning-Based Screening of Receptor Tyrosine Kinase Inhibitors in Drug Discovery.

Journal of chemical information and modeling·2025

Same journal

RETRACTED: Meligy et al. Therapeutic Potential of Mesenchymal Stem Cells Versus Omega n - 3 Polyunsaturated Fatty Acids on Gentamicin-Induced Cardiac Degeneration. <i>Pharmaceutics</i> 2022, <i>14</i>, 1322.

Pharmaceutics·2026

Same journal

Correction: Mohite et al. Bioactive Compound-Fortified Nanomedicine in the Modulation of Reactive Oxygen Species and Enhancement of the Wound Healing Process: A Review. <i>Pharmaceutics</i> 2025, <i>17</i>, 855.

Pharmaceutics·2026

Same journal

Metal Nanoparticle-Reinforced Hydrogels Applied in the Inhibition of Clinical Pathogens: Structural Features, Mechanisms, and Biomedical Prospects.

Pharmaceutics·2026

Same journal

Development and Evaluation of a Physiologically Based Pharmacokinetic Model for Cipepofol Across Diverse Clinical Populations.

Pharmaceutics·2026

Same journal

Artificial Intelligence in Nanopharmaceutical Development: From Predictive Design to Clinical Translation.

Pharmaceutics·2026

Same journal

Textilinin-1, a Snake Venom-Derived Kunitz-Type Protease Inhibitor, Accelerates Wound Healing Through Anti-Inflammatory, Antibacterial, and Pro-Regenerative Activities.

Pharmaceutics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 8, 2025

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Published on: February 10, 2023

CSM-Toxin: A Web-Server for Predicting Protein Toxicity.

Vladimir Morozov^1,2, Carlos H M Rodrigues^1,2, David B Ascher^1,2

¹School of Chemistry and Molecular Biosciences, University of Queensland, St Lucia, QLD 4072, Australia.

|February 25, 2023

Summary

This summary is machine-generated.

Scientists developed CSM-Toxin, a new tool predicting biologic drug toxicity from protein sequences. This computational method helps reduce failures in biologic drug development by identifying potential toxic properties early.

Keywords:

deep-learning protein toxicity sequence

More Related Videos

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

Published on: March 14, 2019

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Related Experiment Videos

Last Updated: Aug 8, 2025

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Published on: February 10, 2023

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

Published on: March 14, 2019

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Area of Science:

Biochemistry
Computational Biology
Drug Development

Background:

Biologics are a growing therapeutic class but can exhibit toxicity.
Early toxicity identification in small molecules reduced clinical trial failures.
Predictive tools for peptide and protein toxicity are currently lacking.

Purpose of the Study:

To develop a computational tool for predicting peptide and protein toxicity.
To address the need for robust predictive models in biologic drug development.

Main Methods:

Curated the largest dataset of experimental peptide and protein toxicity data.
Developed CSM-Toxin, an in-silico toxicity classifier using deep learning and natural language processing on primary protein sequences.
Treated protein residues as words and sequences as sentences to encode biological language.

Main Results:

CSM-Toxin accurately identified potentially toxic peptides and proteins.
Achieved a Matthews Correlation Coefficient (MCC) of up to 0.66 in cross-validation and blind tests.
Outperformed existing methods, demonstrating robust and generalizable performance.

Conclusions:

CSM-Toxin is a valuable tool for minimizing toxicity in the biologic development pipeline.
The model's performance highlights its potential to improve drug safety and reduce trial failures.
The CSM-Toxin method is accessible via a free webserver.