Abstract We propose an integrative modeling approach to synthesize data generated across labs of the Nanotechnology Health Implications Research (NHIR) consortium. Our goal is to leverage these diverse data toward developing principles for sustainable design and synthesis of engineered nanomaterials (ENM). Our approach advances this goal by (1) Creation of a flexible data structure that permits analysis across ENM attributes and assay results, (2) Sophisticated machine learning modeling of integrated data, and (3) Facilitating dissemination of results via Cancer Nanotechnology Laboratory (CaNanoLab). This proposal can advance overarching NHIR goals by allowing for the discovery of robust patterns in complex, integrated data that could not be gleaned from single data sources alone.