Ant Colony Optimisation for Ligand Docking

In this work we propose a hybrid ant colony optimisation algorithm as an alternative search engine in the GOLD protein-ligand docking framework [4]. The approach treats the placement of a ligand molecule in the protein's binding site as a discrete assignment problem and a geometric point fitting procedure generates protein-ligand complex conformations from this representation. As in PLANTS [5,6], we combine this approach with a local search in the continuous search space of the objective function. Continuous solutions are finally reassigned to approximate solutions of the discrete assignment problem resulting in a high-performing optimisation approach. We discuss certain aspects of the hybridisation strategy including the integration of heuristic information into the search process and compare the performance to the genetic algorithm currently used in GOLD.