Despite little progress in ab initio solutions to the problem of predi
cting a protein's tertiary structure, over the past four years or so t
he development of fold-recognition methods for tertiary structure pred
iction has been the source of some encouragement in this difficult fie
ld. Despite promising initial results, these methods are clearly not y
et fully mature and many groups are now working on different aspects o
f the methods involved in the hope of increasing the reliability and s
ensitivity of these tools.