Storing and Using Qualitative and Quantitative Structure–Activity Relationships in the Era of Toxicological and Chemical Data Expansion
Emerging Big Data technologies and the growing amount of data in predictive toxicology (and in chemistry in general) require new solutions and methods for large-scale data and model storage, as well as for model representation and analysis. Knowledge extraction from big and diverse toxicology and chemistry data results in mathematical models that are used to organise and systematise data and structure patterns. Consequently, next to the developments in data organisation and analysis, the systematic representation and organisation of descriptive and predictive qualitative and quantitative structure–activity relationships, (Q)SARs, is equally important. Therefore, full attention from model developers is required to make the new knowledge derived from the data and models easily accessible and usable. This chapter considers issues related to the organisation of (Q)SAR models and gives an overview of the file and data formats used to organise predictive models as well as their storage solutions in the era of data expansion.