Agrochemical products are typically formulations of numerous substances that each contribute to the overall toxicity profile of that product. Even though a proportion of these ingredients may have already been tested for their hazard characterisation in previous uses, the novel formulation must be assessed for its classification and labelling according to international guidelines such as the UN Globally Harmonized System of Classification and Labelling of Chemicals (GHS) requirements. This requires in vivo studies often resulting in pain, discomfort and death to animals. There has been some progress in the development and use of in silico approaches for specific acute endpoints on single chemicals and mixtures, but these have a number of limitations which restrict their use. This Challenge aims to develop innovative, integrated in silico approaches to better predict the GHS classification category for acute oral, skin and eye irritation in the development of agrochemical formulations without using animals or generating new in vitro data.
Here, a multidisciplinary team led by Professor Jon Timmis from SimOmics Ltd and the University of York propose to develop a web-based tool that reuses existing toxicological data to predict GHS classifications of novel formulations without the need for further in vivo studies. Their proposal includes the creation of a database of previously generated toxicological data across a range of substances and formulations. Machine learning will extract relationships between substances in the database, and will be used to predict a GHS classification for novel formulations. The team will generate a reasoned argument containing relevant evidence that will detail how a classification was derived and they will identify new (ideally in vitro) studies, where classifications cannot be made due to lack of data.
Full details about this CRACK IT Challenge can be found on the CRACK IT website.
Contractor(s)Professor Jonathan Timmis