Support Vector Machine-based Prediction for Oral Cancer Using Four SNPs in DNA Repair Genes

Abstract

Abstract—Oral cancer is the sixth most common cancer and a major health problem in the world. We aimed at DNA repair genes such as X-ray repair cross-complementing group (XRCC)1, 2, 3, and 4. Single nucleotide polymorphisms (SNPs) dataset with 238 samples of oral cancer and control patients were chosen for disease prediction. All prediction experiments were conducted using the support vector machine. The result showed the performances of the holdout cross validation is superior to 10-fold cross validation, and the best classification accuracy is 64.2%. Although only four SNPs were used in this analysis, our proposed methodology is still high-throughput for genome-wide SNPs. Once more SNPs were introduced to oral cancer prediction, the prediction rate will be further improved. Index Terms—oral cancer, X-ray repair cross-complementing group, single nucleotide polymorphisms, support vector machine I.