A novel approach to heteropolymer design is proposed. It is based on the cr
iterion by Kurosky and Deutsch, with which the probability of a target conf
ormation in a conformation space is maximized at low but finite temperature
. The key feature of the proposed approach is the use of soft spins (fuzzy
monomers) that leads to a design equation, which is an analog of the Boltzm
ann machine learning equation in the design problem. We implement an algori
thm based on the design equation for the generalized HP model on the 3 x 3
x 3 cubic lattice and check its performance.