Optibrium has announced the availability of a range of Quantitative Structure Activity Relationship (QSAR) models to help predict the toxicity of potential new compounds.
The company has generated a range of QSAR models, based on data made available by the US Environmental Protection Agency (EPA), as part of its Toxicity Evaluation Software Toolkit (TEST).
The toxicity prediction models were built with the Auto-Modeller module of Stardrop 5 and are available free of charge to all Stardrop users.
Whether compounds are intended as drugs, cosmetics, agrochemicals or for other industrial applications, it is important to understand their potential to cause toxic effects.
Understanding this can allow scientists to prioritise chemical structures for further research or identify the most appropriate downstream experiments to confirm their safety.
However, the ability to predict toxicities in compounds can be challenging.
Models have a high degree of uncertainty in the predictions they make due to the complexity and variety of chemical and biological mechanisms that lead to toxicities.
Stardrop is an interactive platform that guides scientists to make decisions on the design and selection of high-quality compounds with the aim of achieving an optimal balance of properties.
It provides a suitable environment for application of toxicity models to the selection of compounds.
Its probabilistic scoring algorithm allows predictive models of toxicity to be used, while explicitly taking into consideration the uncertainty of each prediction.
This ensures that uncertain predictions are not given undue weight, relative to other data, when prioritising compounds that are more likely to have an appropriate balance of properties.
As a result, compounds that are more likely to be toxic are efficiently identified, improving lead optimisation.
The Glowing Molecule feature within Stardrop offers a visualisation that highlights regions of a compound with a significant influence on a predicted property.
As a result, this provides a link between the predicted toxicity and the chemical mechanism and guides users in the redesign of compounds with improved safety.
Many of the toxicity prediction models developed with the use of Stardrop are particularly relevant to potential environmental pollutants.
This illustrates the usability of Stardrop not just for drug discovery applications, but for industrial, agrochemical or cosmetic applications.
The toxicity prediction models conform to the Organisation for Economic Co-operation and Development (OECD) principles for validation of QSAR models for regulatory purposes and have also been found to perform equivalently or better than the EPA TEST models on the same validation sets.
