Molecular docking is a simulation process where the binding of a small molecule is identified in the structure of a protein target. There are several different computational approaches to solve this problem. Here it is described recent developments in application of evolutionary algorithms to molecular docking simulations. Evolutionary algorithms are classified as a group of computational techniques based on the concepts of Darwin's theory of evolution that are designed to find the best possible solution to optimization problems. A successfully implementation of this algorithm can be found in the program MolDock. The main features of MolDock are reviewed here. We also describe application of MolDock to purine nucleoside phosphorylase, shikimate kinase and cyclin-dependent kinase 2.