Comparison between Spatial Statistics Model and Bidirectional Hidden Markov Model for Assignment of Protein Sequences

Comparison between Spatial Statistics Model and Bidirectional Hidden Markov Model for Assignment of Protein Sequences

Profile hidden Markov model (PHMM) is widely used in assigning protein sequences to protein families. In PHAIM, the homologous sequences are assigned to the protein families asing the information of the left side of a residue. In this paper, the information of both left and right sides of a residue in a profile are considered. For this purpose bidirectional profile hidden Markov model (BPHMM) is used. Also, we employ a new method based on spatial statistics on a rectangular lattice for considering the whole information of a site, i.e., left, right, top and bottom sides of residues. We then compare the performance of BPHMM and spatial method by applying them on the real ten top protein profiles from Pfan database. Results show that using the spatial model for sequence assignment increases the number of correctly assigned protein sequences to profiles compared to BPHMM.