Combined <i>In Vitro</i> and <i>In Silico</i> Workflow to Deliver Robust, Transparent, and Contextually Rigorous Models of Bioactivity

New approach methodologies (NAMs) are an increasing priority in the field of toxicology to fill data gaps and reduce time and resources in chemical safety assessment. We describe an NAMs workflow that integrates an <i>in vitro</i> high-throughput bioassay with an <i>in silico</i> computational model. In defining this workflow, we propose, as a crucial step of <i>in silico</i> development, the identification of explicit "purpose contexts": <i>a priori</i> definitions of the scope and intent of an <i>in silico</i> solution, which provide natural targets for the mechanistic interpretation, validation, and output design of the model. By inspecting data from an <i>in vitro</i> assay measuring the displacement of fluorescent probe 8-anilino-1-naphthalenesulfonic acid (ANSA) from the serum transport protein transthyretin (TTR) as a proxy for potential disruption of thyroxine (T4) binding, in collaboration with the experimenters, we developed three relevant purpose contexts for this <i>in silico</i> modeling effort: (1) examination and confirmation of the <i>in vitro</i> assay principle via orthogonal information, (2) immediate integration with the <i>in vitro</i> experimental cycle to reduce costs and enhance hit rates, and (3) ultimate replacement of the use of single-concentration screening as a prioritization strategy for bioactivity testing of bulk chemical libraries. From these purpose contexts, we derived the foundations of a robust and transparent quantitative structure-activity relationship (QSAR) model that is constructively fit for purpose, characterized by first-principles mechanistic analysis, strict data quality evaluation, contextually rigorous performance testing and, finally, delivery of a quantitative recommendation schedule to simultaneously improve <i>in vitro</i> hit rates and <i>in silico</i> model learning potential.