This study focuses on improving the multi-objective memetic algorithm for protein-protein interaction (PPI) network alignment, Optimizing Network Aligner - OptNetAlign, via integration with other existing network alignment methods such as SPINAL, NETAL and HubAlign. The output of this algorithm is an elite set of aligned networks all of which are optimal with respect to multiple user-defined criteria. However, OptNetAlign is an unsupervised genetic algorithm that initiates its search with completely random solutions and it requires substantial running times to generate an elite set of solutions that have high scores with respect to the given criteria. In order to improve running time, the search space of the algorithm can be narrowed down by focusing on remarkably qualified alignments and trying to optimize the most desired criteria on a more limited set of solutions. The method presented in this study improves OptNetAlign in a supervised fashion by utilizing the alignment results of different network alignment algorithms with varyingparameters that depend upon user preferences. Therefore, the user can prioritize certain objectives upon others and achieve better running time performance while optimizing the secondary objectives. (C) 2016 Elsevier Ltd. All rights reserved.