A method for the discovery, development and clinical application of multidimensional multiplex synthetic biomarker assays based on patterns of cellular response.
After stimulation or inhibition, a selected multiplicity of cell types are assayed for a multiplicity of cellular or molecular responses, and known machine learning techniques are used to synthesize the cellular responses into an optimized clinical biomarker. The computationally derived algorithm includes the relationships within and between the component steps so as to produce an optimized synthetic clinical biomarker. During discover of the assay one or more of the component steps are repeated iteratively until a final clinically optimized algorithm is produced.
Such a multidimensional multiplex cell response assay may provide improved diagnostic performance with respect to entities such as immune status, infection, and antibiotic and vaccine efficacy, among others.