iCar-PseCp: identify carbonylation sites in proteins by Monte Carlo sampling and incorporating sequence coupled effects into general PseAAC

Abstract

// Jianhua Jia 1, 2 , Zi Liu 3 , Xuan Xiao 1, 2 , Bingxiang Liu 1 , Kuo-Chen Chou 2, 4 1 Computer Department, Jing-De-Zhen Ceramic Institute, Jing-De-Zhen 333403 China 2 Gordon Life Science Institute, Boston, MA 02478, USA 3 School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China 4 Center of Excellence in Genomic Medicine Research (CEGMR), King Abdulaziz University, Jeddah 21589, Saudi Arabia Correspondence to: Jianhua Jia, email: jjia@gordonlifescience.org Xuan Xiao, email: xxiao@gordonlifescience.org Kuo-Chen Chou, email: kcchou@gordonlifescience.org Keywords: carbonylation, sequence-coupling model, PseAAC, Monte Carlo sampling, random forest algorithm Received: March 06, 2016 Accepted: April 09, 2016 Published: May 03, 2016 ABSTRACT Carbonylation is a posttranslational modification (PTM or PTLM), where a carbonyl group is added to lysine (K), proline (P), arginine (R), and threonine (T) residue of a protein molecule. Carbonylation plays an important role in orchestrating various biological processes but it is also associated with many diseases such as diabetes, chronic lung disease, Parkinson’s disease, Alzheimer’s disease, chronic renal failure, and sepsis. Therefore, from the angles of both basic research and drug development, we are facing a challenging problem: for an uncharacterized protein sequence containing many residues of K, P, R, or T, which ones can be carbonylated, and which ones cannot? To address this problem, we have developed a predictor called iCar-PseCp by incorporating the sequence-coupled information into the general pseudo amino acid composition, and balancing out skewed training dataset by Monte Carlo sampling to expand positive subset. Rigorous target cross-validations on a same set of carbonylation-known proteins indicated that the new predictor remarkably outperformed its existing counterparts. For the convenience of most experimental scientists, a user-friendly web-server for iCar-PseCp has been established at http://www.jci-bioinfo.cn/iCar-PseCp , by which users can easily obtain their desired results without the need to go through the complicated mathematical equations involved. It has not escaped our notice that the formulation and approach presented here can also be used to analyze many other problems in computational proteomics.