VEGA HUB
VEGA HUB provides in silico predictive models for chemical hazard evaluation, focusing on genotoxicity prediction for the in vitro micronucleus assay.
Key Features:
- In Silico Genotoxicity Prediction: Implements computational models that predict outcomes of the in vitro micronucleus assay for genotoxicity assessment.
- Statistical and Knowledge-Based Models: Includes both statistical approaches and knowledge-based frameworks, with models built from fragments extracted via SARpy.
- SARpy-Derived Structural Alerts: Utilizes fragments extracted with SARpy and incorporates over 100 structural alerts representing genotoxic and non-genotoxic activities.
- High Predictive Performance: The SARpy-derived model is reported to exhibit high accuracy and a low false negative rate for initial chemical screening.
- Integration with VEGA Platform Tools: Models are integrated within the VEGA platform and associated modules ToxRead, ToxWeight, ToxDelta, and JANUS.
Scientific Applications:
- Regulatory Genotoxicity Assessment: Supports prediction of micronucleus assay outcomes for regulatory decision-making in sectors such as cosmetics and food.
- Chemical Prioritization and Screening: Enables prioritization of large chemical libraries for follow-up testing based on predicted genotoxic potential.
- Alternatives to Experimental Testing: Provides in silico predictions to reduce reliance on laboratory micronucleus assays during early screening phases.
Methodology:
Extraction and analysis of structural alerts using SARpy, development of statistical and knowledge-based models, and incorporation of over 100 structural alerts to predict in vitro micronucleus assay outcomes.
Topics
Details
- Added:
- 1/14/2020
- Last Updated:
- 1/2/2021
Operations
Publications
Baderna D, Gadaleta D, Lostaglio E, Selvestrel G, Raitano G, Golbamaki A, Lombardo A, Benfenati E. New in silico models to predict in vitro micronucleus induction as marker of genotoxicity. Journal of Hazardous Materials. 2020;385:121638. doi:10.1016/j.jhazmat.2019.121638. PMID:31757721.
PMID: 31757721