Over the years, numerous studies have been performed in order to identify messenger RNAs (mRNAs) that are differentially expressed at different biological conditions for various diseases including cancer. In this regard, getting complete and noiseless data were always very challenging in previous technological set-up. While the inception of Next-Generation Sequencing (NGS) technology revolutionized the genome research, especially in the field of mRNA expression profile analysis. Here such data of breast cancer is used from The Cancer Genome Atlas (TCGA) to identify the cancer biomarkers. For this purpose, data have been preprocessed using statistical test and fold change concepts so that significant number of differentially expressed up and down regulated mRNAs can be recognized. Thereafter, wrapper based feature selection approach using Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) has been applied on such preprocessed dataset to identify the potential mRNAs as biomarkers. Identified top 10 biomarkers are COMP, LRRC15, CTHRC1, CILP2, FOXF1, FIGF, PRDM16, LMX1B, IRX5 and LEPREL1. The quantitative results of the proposed method have been demonstrated in comparison with other state-of-the-art methods. Finally, enrichment analysis and the KEGG pathway analysis have also been conducted for the selected mRNAs.