K_net: Lysine Malonylation Sites Identification With Neural Network

Jin Sun, Yi Cao, Dong Wang, Wenzheng Bao, Yuehui Chen

Abstract: Lysine Malonylation (Kmal) is a newly discovered protein post-translational modifications (PTMs) type, which plays an important role in many biological processes. Therefore, identifying and understanding Kmal sites is very critical in the studies of biology and diseases. The typical methods are time-wasting and expensive. Nowadays, many researchers have proposed machine learning (ML) methods to deal with PTMs’s identification issue. Especially, some deep learning (DL) methods are also utilized in this field. In this work, we proposed K_net, which employed Convolutional Neural Network to identify the potential sites. Meanwhile, we proposed a new verification method Split to Equal Validation (SEV), which can well solve the impact of sample imbalance on prediction results. More Specifically, Acc, Sn, Sp, MCC and AUC values were adopted to evaluate the prediction performance of predictors. In total, CNN_Kmal achieved the better performance than other methods.