Imagine trying to guess if a new chemical is poisonous by comparing it to a photo album of known toxins; if the new chemical looks different, the guess fails. This project replaces that photo album with a digital 'fingerprint' based on the actual physics of the molecule. It uses AI to read these fingerprints, allowing us to predict safety without needing to run expensive and slow lab tests on animals or cells.
Current toxicity predictions rely on structural similarity, which fails for new chemicals and requires too many complex descriptors to be understandable. This leads to expensive lab failures and slow regulatory approvals.
A system of Electronic Signatures (ESigns) based on quantum mechanics and an AI tool to link these signatures to toxicity endpoints.
If you are a drug discovery biotech dealing with high failure rates in late-stage safety trials — this project developed Electronic Signatures (ESigns) that predict toxicity early in the pipeline. This reduces the reliance on costly and time-consuming experimental studies.
If you are a specialty chemical producer dealing with the need to assess novel compounds that don't fit existing safety models — this project developed a quantum-mechanical descriptor system that covers the whole chemical space. This allows for accurate risk assessment of underrepresented chemical classes.
If you are an environmental safety consultancy dealing with the slow pace of regulatory decision-making for pollutants — this project developed an AI system to link electronic signatures to toxicity endpoints. This provides a faster, cheaper way to assess environmental impact.
Based on available project data, it replaces expensive in vitro and in vivo experimental studies with in silico computer models, which are inherently faster and cheaper.
Yes, the project aims to cover the whole chemical space by abandoning predictions based on molecular structures in favor of quantum-mechanical descriptors.
Based on available project data, the project is in the execution phase (2024-2028), and specific licensing terms for the Electronic Signatures have not been disclosed.
It improves regulatory decision-making by providing more reliable and interpretable toxicity predictions early in the development pipeline.
The project period runs from 2024-02-01 to 2028-01-31, suggesting the technology is still being developed and validated.
The consortium is well-balanced for a translation project, consisting of 8 partners across 5 countries. With a 38% industry ratio (3 companies, including 3 SMEs), there is a clear bridge between the 4 universities and the research institute, ensuring that the quantum chemistry research is aligned with commercial toxicity testing needs.
Contact Istituto di Ricerche Farmacologiche Mario Negri in Italy
Contact us to explore licensing opportunities for ESign descriptors.
