We present a protein fold recognition method that uses a comprehensive statistical interpretation of structural Hidden Markov Models (HMMs). The structure/fold recognition is done by summing the probabilities of all sequence-to-structure alignments Conventionally, Boltzmann statistics dictate that the optimal alignment can give an estimate of the lowest free energy of the sequence conformation imposed by the structural model. The alignment is optimized for a scoring function that is interpreted as a free energy of an amino acid in a structural environment. Near-optimal alignments are ignored, regardless of how likely they might be compared to the optimal alignment. Here we investigate an alternative view. A structure model can be seen as a statistical representation of an ensemble of similar structures. The optimal alignment is always the most probable, but sub-optimal alignments may have comparable probabilities. These sub-optimal alignments can be interpreted as optimal alignments to the “other” structures from the ensemble or optimal alignments under minor fluctuations in the scoring function. Summing probabilities for all alignments gives an estimate of sequence-model compatibility. We have built a set of structural HMMs for 188 protein structures, and have compared two methods for identifying the structure compatible with a sequence: by the optimal alignment probability and by the total probability. Fold recognition by total probability was 40% more accurate than fold recognition by the optimal alignment probability.