There are many proteins that share the same fold but have no clear sequence
similarity To predict the structure of these proteins, so called "protein
fold recognition methods" have been developed. During the last few years, i
mprovements of protein fold recognition methods have been achieved through
the use of predicted secondary structures (Rice and Eisenberg, J Mol Biol 1
997;267:1026-1038), as well as by using multiple sequence alignments in the
form of hidden Markov models (HMM) (Karplus et al,, Proteins Suppl 1997;1:
134-139),To test the performance of different fold recognition methods, we
have developed a rigorous benchmark where representatives for all proteins
of known structure are matched against each other. Using this benchmark, we
have compared the performance of automatically-created hidden Markov model
s with standard-sequence-search methods. Further, we combine the use of pre
dicted secondary structures and multiple sequence alignments into a combine
d method that performs better than methods that do not use this combination
of information. Using only single sequences, the correct fold of a protein
was detected for 10% of the test cases in our benchmark. Including multipl
e sequence information increased this number to 16%, and when predicted sec
ondary structure information was included as well, the fold was correctly i
dentified in 20% of the cases. Moreover, if the correct secondary structure
was used, 27% Of the proteins could be correctly matched to a fold, For co
mparison, blast2, fasta, and ssearch identifies the fold correctly in 13-17
% of the cases. Thus, standard pairwise sequence search methods perform alm
ost as web as hidden Markov models in our benchmark. This is probably becau
se the automatically-created multiple sequence alignments used in this stud
y do not contain enough diversity and because the current generation of hid
den Markov models do not perform very well when built from a few sequences.
Proteins 1999;36:68-76. (C) 1999 Wiley-Liss, Inc.