Background: For genome sequencing projects to achieve their full impac
t on biology and medicine, each protein sequence must be identified wi
th its three-dimensional structure. Fold assignment methods (also call
ed profile and threading methods) attempt to assign sequences to known
protein folds by computing the compatibility of sequence to fold. Res
ults: We have extended profile methods for the detection of protein fo
lds having structural similarity but low sequence similarity to sequen
ce probes. Our extension combines sequence substitution tables with st
ructural properties to form a combined profile. The structural propert
ies used in this study include distances between residues, exposed are
as, areas buried by polar atoms, and properties of the original three-
dimensional profile method. We compared the performance of these combi
ned profiles with different sequence matrices and with the original th
ree-dimensional profile method. To determine the optimal gap penalties
and weights used with these profiles, we employed a genetic algorithm
. The performance of these combined profiles was tested by cross valid
ation using independent test and training sets. Conclusions: These stu
dies show that the combined profiles perform better than profiles base
d on either structural or sequence information alone. (C) Current Biol
ogy Ltd.