Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
| Hi-index | 0.00 |
This article describes a variable string length genetic algorithm for de novo ligand design. The input to the algorithm is the active site dimensions which guides the ligand construction. A library of forty one fragments is used to construct the ligands by evaluating the combinations of these fragments. Bond stretching, angle bending, torsional terms, van der Waals and electrostatic interaction energy with distance dependent dielectric constant contribute are used to evaluate the internal energy of the ligand and the interaction energy of the ligand receptor complex. Domain specific genetic operators are used to evolve the solutions to obtain better ligands. Experimental results for HIV-1 Protease and Thrombin are provided which underline the superiority of the proposed scheme over three existing approaches.