A Linear Regression Predictor for Identifying N(6)-Methyladenosine Sites Using Frequent Gapped K-mer Pattern

N6-methyladenosine (m(6)A) is one of the most common and abundant modifications in RNA, which is related to many biological processes in humans. Abnormal RNA modifications are often associated with a series of diseases, including tumors, neurogenic diseases, and embryonic retardation. Therefore, identifying m(6)A sites is of paramount importance in the post-genomic age. Although many lab-based methods have been proposed to annotate m(6)A sites, they are time consuming and cost ineffective. In view of the drawbacks of the intrinsic methods in RNA sequence recognition, computational methods are suggested as a supplement to identify m(6)A sites. In this study, we develop a novel feature extraction algorithm based on the frequent gapped k-mer pattern (FGKP) and apply the linear regression to construct the prediction model. The new predictor is used to identify m(6)A sites in the Saccharomyces cerevisiae database. It has been shown by the 10-fold cross-validation that the performance is better than that of recent methods. Comparative results indicate that our model has great potential to become a useful and effective tool for genome analysis and gain more insights for locating m(6)A sites.