The hidden Markov model
Five structural parts were defined in membrane proteins: membrane helix (h), inside and outside helix tail (i and o), inside and outside loop (I and O). Two connected tails form a short loop associated with the membrane, while the tail-loop-tail sequence forms a long loop in the cytosol or in the extra-cytosol. Topology is determined by partitioning amino acid sequence in a way that product of the relative frequencies of amino acids in these structural parts along the sequence should be maximal. This task can be solved by the hidden Markov model (HMM), in which biological constraints can be taken into account by the architecture of HMM. The structural parts correspond to the five states used by the model.