Cryptic allosteric sites—pockets in a folded protein that are invisible to conventional experiments but can alter enzymatic activity via allosteric communication with the active site—are a promising opportunity for facilitating drug design by greatly expanding the repertoire of available drug targets. Unfortunately, identifying these sites is difficult, typically requiring resource intensive screening of large libraries of small molecules. I will present recent advances in using Markov state models built from extensive computer simulations (totaling hundreds of microseconds of dynamics) to identify prospective cryptic sites from the equilibrium fluctuations of proteins like â-lactamase in the absence of any ligands. This approach reveals extensive conformational heterogeneity in folded proteins that could give rise to cryptic sites. Based on this observation, I hypothesized that cryptic sites should appear as high-energy (or low population) pockets adjacent to residues displaying correlated motions with the active site. I will show that these ingredients are sufficient to retrodict a known cryptic site in â-lactamase and, more importantly, predict the existence of a multitude of new sites. Finally, I will present the results of experimental tests supporting the existence of my new sites.