The railway capacity optimization problem deals with the maximization of the number of trains running on a given network per unit time. In this study, we frame this problem as a typical asymmetrical Travelling Salesman Problem (ATSP), with the ATSP nodes representing the train arrival /departure events and the ATSP total cost representing the total time-interval of the schedule. The application problem is then optimized using the standard Ant Colony Optimization (ACO) algorithm. The simulation experiments validate the formulation of the railway capacity problem as an ATSP and the ACO algorithm produces optimal solutions superior to those produced by the domain experts.