Genetic clustering with Bee Colony Optimization for flexible protein-ligand docking

Abstract

In this paper Flexible Protein Ligand Docking is carried out using Genetic Clustering with Bee Colony Optimization. The molecular docking problem is to find a good position and orientation for docking and a small molecule ligand to a large receptor molecule. It is originated as an optimization problem consists of optimization method and the clustering technique. Clustering is a data mining task which groups the data on the basis of similarities among the data. A Genetic clustering algorithm combine a Genetic Algorithm (GA) with the K-medians clustering algorithm. GA is one of the evolutionary algorithms inspired by biological evolution and utilized in the field of clustering. K-median clustering is a variation of K-means clustering where instead of calculating the mean for each cluster to determine its centroid, one instead calculates the median. Genetic Clustering is combined with Bee Colony Optimization (BCO) algorithm to solve Molecular docking problem. BCO is a new Swarm Intelligent algorithm that was first introduced by Karaboga. It is based on the Fuzzy Clustering with Artificial Bee Colony Optimization algorithm proposed by Dervis Karaboga and Celal Ozturk. In this work, we propose a new algorithm called Genetic clustering Bee Colony Optimization (GCBCO). The performance of GCBCO is tested in 10 docking instances from the PDB bind core set and compared the performance with PSO and ACO algorithms. The result shows that the GCBCO could find ligand poses with best energy levels than the existing search algorithms.