CIPPN: computational identification of protein pupylation sites by using neural network

// Wenzheng Bao 1, * , Zhu-Hong You 2, * and De-Shuang Huang 1 1 Institute of Machine Learning and Systems Biology, School of Electronics and Information Engineering, Tongji University, Shanghai, China 2 Xinjiang Technical Institutes of Physics and Chemistry, Chinese Academy of Science, Urumqi 830011, China * The first two authors should be regarded as joint First Authors Correspondence to: De-Shuang Huang, email: dshuang@tongji.edu.cn Keywords: disease; post translational modification; classification Received: July 14, 2017      Accepted: September 03, 2017      Published: November 06, 2017 ABSTRACT Recently, experiments revealed the pupylation to be a signal for the selective regulation of proteins in several serious human diseases. As one of the most significant post translational modification in the field of biology and disease, pupylation has the ability to playing the key role in the regulation various diseases’ biological processes. Meanwhile, effectively identification such type modification will be helpful for proteins to perform their biological functions and contribute to understanding the molecular mechanism, which is the foundation of drug design. The existing algorithms of identification such types of modified sites often have some defects, such as low accuracy and time-consuming. In this research, the pupylation sites’ identification model, CIPPN, demonstrates better performance than other existing approaches in this field. The proposed predictor achieves Acc value of 89.12 and Mcc value of 0.7949 in 10-fold cross-validation tests in the Pupdb Database ( http://cwtung.kmu.edu.tw/pupdb ). Significantly, such algorithm not only investigates the sequential, structural and evolutionary hallmarks around pupylation sites but also compares the differences of pupylation from the environmental, conservative and functional characterization of substrates. Therefore, the proposed feature description approach and algorithm results prove to be useful for further experimental investigation of such modification’s identification.