Clearly, protein folding trajectories consist of both spatial and temporal components. Each protein in a MD simulation is composed of a number of residues spatially located in the 3D space that move over time. Each frame (or snapshot) of the trajectory can be represented as a 2D contact map, which captures the pair-wise 3D distances between residues. We extract non-local bit-patterns from these contact maps. We then use an entropy-based clustering algorithm to cluster such bit-patterns into groups. These bit-patterns are further associated to form spatial object association patterns (SOAPs). By using SOAPs, we are able to effectively summarize and analyze folding trajectories produced by MD simulations. A major advantage of this representation is its appropriateness for cross-comparison across different simulations, as discussed in later sections.