Registration Details
The NC3Rs NAMs Network and the British Toxicology Society Mechanistic & Discovery Toxicology Speciality Section are hosting a webinar exploring the opportunities and latest developments in the application of artificial intelligence (AI) in safety assessment. Three leading experts will discuss how AI and approaches such as machine learning can be used to improve toxicity prediction and reduce reliance on animal models.
Registration will close 24hrs before the scheduled start time of the webinar.
Programme
Chaired by Dr Nicholas Coltman (BTS Mechanistic and Discovery Toxicology Speciality Section Chair and Deputy Head of Safety Science at Apconix) and Dr Natalie Burden (NC3Rs Head of NAMs Strategy).
- The future of artificial intelligence in human safety assessment.
Dr Darren Green, DesignPlus Cheminformatics Consultants. - Machine learning for toxicity prediction using chemical structures: Pillars for success in the real world.
Dr Srijit Seal, Broad Institute of MIT and Harvard/University of Cambridge. - Overview of 2025 HESI Workshop: Building a roadmap for AI-enabled human and environmental health protection.
Dr Michelle Embry, HESI.
The webinar will be of interest to researchers, technology developers and industry and regulatory end-users.
About the NC3Rs NAMs Network
The NC3Rs NAMs Network brings together researchers, developers and industry and regulatory end-users together to accelerate the use of NAMs*. We encourage stakeholders from across the sector to join the Network to stay-up-date with opportunities and resources in the NAMs space. More information about the Network and how to join is available on our Network page.
We have funded a number of projects and supported the development of products to apply computational, AI- or machine learning-based approaches to toxicology and safety assessment:
- Project: Machine-learning aided multiscale modelling framework for toxicological endpoint predictions in the dog.
- Project: Predicting oral bioavailability and performance of new drugs using AI-PAT.
- Project: High fidelity computational approaches to predict whether a compound will impact cardiac ion channel function.
- Project: Using machine learning to predict tumourigenicity and improve the safety assessment of cell therapies.
- Product: A QSAR model to predict human respiratory infection.
- Product: An integrative platform to assess developmental reproductive toxicology.
- Product: In silico tools to predict skin and eye irritation and corrosivity.
* We use the term new approach methodologies (NAMs) specifically to refer to full and partial replacement approaches for assessing chemical or drug toxicity. Learn more on our page on NAMs terminology.