OPTIMALLY-CONNECTED HIDDEN MARKOV MODELS FOR PREDICTING MHC-BINDING PEPTIDES

Hidden Markov models (HMMs) are one of various methods that have been applied to prediction of major histo-compatibility complex (MHC) binding peptide. In terms of model topology, a fully-connected HMM (fcHMM) has the greatest potential to predict binders, at the cost of intensive computation. While a profile HMM (pHMM) performs dramatically fewer computations, it potentially merges overlapping patterns into one which results in some patterns being missed. In a profile HMM a state corresponds to a position on a peptide while in an fcHMM a state has no specific biological meaning. This work proposes optimally-connected HMMs (ocHMMs), which do not merge overlapping patterns and yet, by performing topological reductions, a model's connectivity is greatly reduced from an fcHMM. The parameters of ocHMMs are initialized using a novel amino acid grouping approach called "multiple property grouping." Each group represents a state in an ocHMM. The proposed ocHMMs are compared to a pHMM implementation using HMMER, based on performance tests on two MHC alleles HLA (Human Leukocyte Antigen)-A*0201 and HLA-B*3501. The results show that the heuristic approaches can be adjusted to make an ocHMM achieve higher predictive accuracy than HMMER. Hence, such obtained ocHMMs are worthy of trial for predicting MHC-binding peptides.

HOW SIMPLE CAN THE PROTEINS BE: FROM THE PREDICTION OF THE CLASSES OF PROTEIN STRUCTURES

The validity of complexity simplifications for proteins with different structural features may be different. In this paper, the simplification for proteins is studied using the ratios of successful prediction of structural class under a presumed amino-acid-grouping scheme with a composition-coupled method. It is found that for the α-class proteins, a two-letter alphabet may cover the degree of freedom to characterize the complexity of the class; for the β-class proteins, a 7-letter alphabet might indicate the minimal number of residue types to reconstruct the class feature of the natural proteins; for the α + β-class proteins and the α/β-class proteins, the redundancy of the compositions is weak and the simplification leads to a great loss of the information related to the corresponding structural classes.