Gold nanoparticles (GNPs) coated with small-molecule ligands are versatile materials for biological applications, such as drug delivery and biosensing, because their physicochemical properties and corresponding interactions with biological materials can be tailored by selecting ligands from a large available design space. Unfortunately, a central challenge inhibiting GNP design is that subtle differences in GNP composition (i.e., ligand selection and core size) can trigger large changes in macroscopic behavior that are difficult to predict a priori. In this talk, I will discuss my group’s efforts to combine molecular simulations and data-centric techniques to characterize and predict interactions at the nano-bio interface. In the first part of my talk, I will discuss how systematic variations to the properties of ligands protecting small (<10 nm in diameter) GNPs impact interactions with model cell membranes. Using atomistic and coarse-grained simulations, we show that the free energy of membrane adsorption depends on the hydrophobicity of charged ligand end groups in agreement with experimental measurements. Building upon this work, we have parameterized quantitative structure-activity relationship models to predict cell uptake based on high-throughput simulations. In the second part of my talk, I will discuss our efforts to predict hydrophobicity as the key surface property relevant to both bilayer interactions and interactions with biomacromolecules. We have developed machine-learning models to predict the hydration free energies at ligand-functionalized interfaces with spatially varying chemical properties. This work highlights our approach to derive chemically specific design guidelines for GNPs with tailored nano-bio interactions.