In our continuing efforts towards the design of nonlinear (NLO) optical chromophore containing polypeptides we present an integrated computational approach, in which the design of biomolecular materials with defined secondary and tertiary structures is investigated by means of novel predictive tools, while the effects of the nonlinear optical chromophores are studied with molecular dynamics simulations. A neural network that was trained to predict the spatial proximity of Cα atoms that are less than a given threshold apart, is applied. The double-iterated Kalman filter (DIKF) technique is then employed with a constraints set that includes these pairwise atomic distances, and the distances and angles that define the structure as it is known from the protein's sequence. The results for test cases, particularly Crambin and genetically engineered Eglin-C, demonstrate that this integrated approach is useful for structure prediction at an intermediate resolution. Defined structural motifs of NLO chromophore containing polypeptides are investigated by using molecular dynamics techniques, particularly for the design of coil coiled amphiphatic biopolymers.