SPROUT is a new computer program for constrained structure generation
that is designed to generate molecules for a range of applications in
molecular recognition. It uses artificial intelligence techniques to m
oderate the combinatorial explosion that is inherent in structure gene
ration. The program is presented here for the design of enzyme inhibit
ors. Structure generation is divided into two phases: (i) primary stru
cture generation to produce molecular graphs to fit the steric constra
ints; and (ii) secondary structure generation which is the process of
introducing appropriate functionality to the graphs to produce molecul
es that satisfy the secondary constraints, e.g., electrostatics and hy
drophobicity. Primary structure generation has been tested on two enzy
me receptor sites; the p-amidino-phenyl-pyruvate binding site of tryps
in and the acetyl pepstatin binding site of HIV-1 protease. The progra
m successfully generates structures that resemble known substrates and
, more importantly, the predictive power of the program has been demon
strated by its ability to suggest novel structures.