Abstract: The present invention provides methods for the prediction of in vivo cell-specific toxicity of a compound that combines high-throughput imaging of cultured cells, quantitative phenotypic profiling, and machine learning methods. More particularly, the invention provides a method for the prediction of in vivo renal proximal tubular-, bronchial-epithelial-, and alveolar-cell-specific toxicities of a soluble or particulate compound that comprises contacting cultured human kidney and pulmonary cells with the compound at a range of concentrations, then labeling the cells with DNA, ?H2AX and actin markers and obtaining textural features, spatial correlation features, ratios of the markers, intensity features, cell count and morphology, estimating dose response curves and performing automatic classification of the compound using a random-forest algorithm.

Abstract: There is provided a method of screening for toxicity of a compound. The method comprises contacting a test compound with a test population of cells in which nuclear factor (NF)-?B has not been activated prior to the contacting; determining nuclear localization levels of NF-?B in the test population subsequent to the contacting; and comparing nuclear localization levels of NF-?B of a control population that has not been contacted with the test compound. An increase in nuclear localization levels of NF-?B as of the test population relative to the control population is indicative that the test compound injures the cells and/or induces a pro-inflammatory response and thus is toxic to the cell type used in the method.