Understanding and recognizing genetic sequences is one step towards the treatment of the genetic disorders. Cancer, which is a major leading genetic disorder and responsible for around 13% of all deaths world-wide. Since the discovery of DNA, there has been a growing interest in genetic sequence recognition and gene expression analysis, inspired by its promising potential to cure a broad range of genetic disorders. Conventional biopsy examinations are highly invasive since tissue samples are required to be extracted from patients. Blood-based biomarkers have given optimism about the future cancer management. There have indeed been a number of studies to identify novel miRNA-based cancer biomarkers. However, the existing diagnosis techniques using miRNA suffer from low diagnosis accuracy, sensitivity, and specificity. The low diagnosis accuracy and sensitivity of the existing techniques stems from the fact that there is extremely low miRNA count in body fluids. In this paper, we employed three marker selection algorithms to select relevant miRNAs that are directly responsible for cancer classification. Among the three methods, gain ratio (GR) results are quite encouraging. Despite much noise contaminated in the datasets, the predictive framework able to identify miRNA markers responsible for classification of cancer. 