Related Experiment Video
Updated: Jan 7, 2026
11:10
High-throughput Assay to Phenotype Salmonella enterica Typhimurium Association, Invasion, and Replication in Macrophages
Published on: August 11, 2014
13.1K
SAR Modeling to Predict Ames Mutagenicity Across Different Salmonella typhimurium Strains
Alexander V Dmitriev1, Alexey A Lagunin1,2, Anastasia V Rudik1
1Department for Bioinformatics, Institute of Biomedical Chemistry, 119121 Moscow, Russia.
Pharmaceuticals (Basel, Switzerland)
|December 31, 2025
Summary
A new web application predicts mutagenic activity using Ames test models, accelerating drug development by screening chemical compounds. This tool enhances genetic toxicology assessments for researchers.
Area of Science:
- Genetic Toxicology
- Computational Chemistry
- Drug Discovery
Background:
- The Ames test is crucial for evaluating chemical mutagenicity and carcinogenicity.
- Experimental Ames testing is time-consuming and resource-intensive for large-scale screening.
- Predictive models are needed to expedite the assessment of chemical compounds.
Purpose of the Study:
- To develop a web application for predicting mutagenic activity in the Ames test.
- To provide a tool for rapid screening of chemical structures across multiple bacterial strains.
- To aid pharmaceutical development by assessing mutagenicity of drug candidates.
Main Methods:
- Developed the Ames Mutagenicity Predictor web application.
- Utilized structure-activity relationship (SAR) models from PASS (Prediction of Activity Spectra for Substances) v2024.
- Trained models on 3250 mutagenic and 4285 non-mutagenic compounds across 69 bacterial strains.
Main Results:
- Achieved an average Invariant Accuracy of Prediction (IAP) of 0.944 across 69 strain-specific models.
- Obtained an IAP of 0.962 for unspecified mutagenicity predictions.
- Validated predictive models demonstrating high accuracy.
Conclusions:
- Integrated validated models into a free, accessible web application.
- Enables users to input compound structures via chemical editor, SMILES, or name search.
- Provides detailed mutagenicity profiles for researchers, predicting Ames test results for individual strains.
