In this article, the possible subcellular location of a protein is predicted using multiobjective particle swarm optimization-based feature selection technique. In general form of pseudo-amino acid composition, the protein sequences are used for constructing protein features. Here, the different amino acids compositions are used to construct the feature sets. Therefore, the data are presented as sample of protein versus amino acid compositions as features. The proposed algorithm tries to maximize the feature relevance and minimize the feature redundancy simultaneously. After proposed algorithm is executed on the multiclass dataset, some features are selected. On this resultant feature subset, tenfold cross-validation is applied and corresponding accuracy, F score, entropy, representation entropy and average correlation are calculated. The performance of the proposed method is compared with that of its single objective versions, sequential forward search, sequential backward search, minimum redundancy maximum relevance with two schemes, CFS, CBFS, [Formula: see text], Fisher discriminant and a Cluster-based technique.