%0 Journal Article %A Opiyo, Stephen O. %A Moriyama, Etsuko N. %D 2007 %T Protein Family Classification with Partial Least Squares %U https://acs.figshare.com/articles/journal_contribution/Protein_Family_Classification_with_Partial_Least_Squares/3029764 %R 10.1021/pr060534k.s001 %2 https://ndownloader.figshare.com/files/4732300 %K SquaresThe quality %K profile %K protein function predictions %K performance decrease %K Markov models %K protein classification methods %K protein families %K Protein Family Classification %K protein samples %X The quality of protein function predictions relies on appropriate training of protein classification methods. Performance of these methods can be affected when only a limited number of protein samples are available, which is often the case in divergent protein families. Whereas profile hidden Markov models and PSI-BLAST presented significant performance decrease in such cases, alignment-free partial least-squares classifiers performed consistently better even when used to identify short fragmented sequences. Keywords: partial least square • physico-chemical properties • amino acid composition • profile hidden Markov model • G-protein coupled receptors %I ACS Publications