We submitted nine predictions to CASP2 using our fold recognition prog
ram ProFIT. Two of these structures were still unsolved by the end of
the experiment, six had a recognizable fold, and one fold was new, Fou
r predictions of the six recognizable folds were correct, Two models w
ere excellent in terms of alignment quality (T0031, T0004): in one the
alignment was partially correct (T0014), and one fold was correctly i
dentified (T0038), We discuss improvements of the program and analyze
the prediction results. (C) 1998 Wiley-Liss, Inc.