Molecular dynamics (MD) simulations are computationally expensive, a limiting factor when simulating biomolecular systems. Adaptive sampling approaches can accelerate the exploration of conformational space by running repeated short MD simulations from well-chosen starting points. Existing approaches to adaptive sampling have been optimized to either guide sampling in a desired direction or explore well-formed convex spaces. Here, we describe a novel adaptive sampling algorithm that leverages a k-nearest neighbour (k-NN) graph of the sampled conformational space to preferentially launch explorations from boundary states. We term this approach k-Nearest Neighbor Adaptive Sampling (kNN-AS) and show it has state-of-the-art performance on simple and complex artificial energy functions and generalizes well on a protein test case. Implementation of kNN-AS is light, simple and better suited to complex real-world applications where the dimension and shape of the energy landscape is unknown.
