A user-friendly online platform for predicting chemical and nanomaterial safety and properties

What is it about?

Developing new drugs and advanced materials requires understanding their properties and potential risks, but traditional experimental testing is often slow, expensive, and complex. In this work, we present the Enalos Cloud Platform, an online system that allows researchers to predict chemical and nanomaterial properties using advanced computational models—without needing programming skills.  The platform integrates a wide range of tools and models from cheminformatics, nanoinformatics, and materials science into a single, easy-to-use interface. Users can perform tasks such as predicting toxicity, simulating material properties, screening drug candidates, and analyzing nanoparticle behavior—all within a few steps.  Importantly, the platform provides not only predictions but also information about their reliability (applicability domain), ensuring transparency and trust in the results. It includes over 50 web-based tools developed through multiple EU-funded projects and is freely accessible without login requirements.  The platform also supports advanced concepts such as Integrated Approaches to Testing and Assessment (IATA), allowing users to combine different models and data sources to evaluate materials without the need for laboratory experiments.

Featured Image

Photo by Omar:. Lopez-Rincon on Unsplash

Photo by Omar:. Lopez-Rincon on Unsplash

Why is it important?

Although many powerful computational models exist for predicting chemical and material properties, they are often difficult to use and not widely accessible to non-experts. This work is important because it bridges the gap between advanced modeling and practical usability. By providing a user-friendly, web-based environment, the Enalos Cloud Platform makes cutting-edge predictive tools available to a much broader audience, including experimental scientists and regulators. The platform supports faster and more efficient research by enabling virtual screening and early risk assessment, reducing the need for costly and time-consuming experiments.  It also promotes safe-and-sustainable-by-design (SSbD) development by allowing researchers to evaluate materials before they are synthesized, helping identify safer and more effective candidates early in the design process.  Additionally, the transparency, documentation, and validation of the models align with regulatory requirements, supporting their potential use in decision-making and policy contexts.

Perspectives