Precise Prediction of Calpain Cleavage Sites and Their Aberrance Caused by Mutations in Cancer.

Ze-Xian Liu,Kai Yu,Zekun Liu,Han Cheng,Yimeng Du,Qingfeng Zhang,Shihua Li,Jingsi Dong,Linhong Zhao

doi:10.3389/fgene.2019.00715

Abstract

As a widespread post-translational modification of proteins, calpain-mediated cleavage regulates a broad range of cellular processes, including proliferation, differentiation, cytoskeletal reorganization, and apoptosis. The identification of proteins that undergo calpain cleavage in a site-specific manner is the necessary foundation for understanding the exact molecular mechanisms and regulatory roles of calpain-mediated cleavage. In contrast with time-consuming and labor-intensive experimental methods, computational approaches for detecting calpain cleavage sites have attracted wide attention due to their efficiency and convenience. In this study, we established a novel computational tool named DeepCalpain (http://deepcalpain.cancerbio.info/) for predicting the potential calpain cleavage sites by adopting deep neural network and the particle swarm optimization algorithm. Through critical evaluation and comparison, DeepCalpain exhibited superior performance against other existing tools. Meanwhile, we found that protein interactions could enrich the calpain-substrate regulatory relationship. Since calpain-mediated cleavage was critical for cancer development and progression, we comprehensively analyzed the calpain cleavage associated mutations across 11 cancers with the help of DeepCalpain, which demonstrated that the calpain-mediated cleavage events were affected by mutations and heavily implicated in the regulation of cancer cells. These prediction and analysis results might provide helpful information to reveal the regulatory mechanism of calpain cleavage in biological pathways and different cancer types, which might open new avenues for the diagnosis and treatment of cancers.

Highlights

With a nucleophilic cysteine at the catalytically active site, calpains are an important evolutionarily well-conserved family of Ca2+-dependent cysteine proteases (Croall and Ersfeld, 2007; Ono and Sorimachi, 2012)
For the preparation of training dataset, the known calpain cleavage sites were taken as the positive dataset, while all other non-cleavable sites in the same proteins were regarded as the negative dataset
We developed DeepCalpain software for the prediction of calpain cleavage sites based on multi-network deep learning and particle swarm optimization (PSO) algorithm

Summary

Introduction

With a nucleophilic cysteine at the catalytically active site, calpains (calcium-activated nonlysosomal proteases) are an important evolutionarily well-conserved family of Ca2+-dependent cysteine proteases (Croall and Ersfeld, 2007; Ono and Sorimachi, 2012). Calpains play a pivotal role in a wide range of cellular and physiological processes, such as the regulation of embryogenesis, differentiation, signal transduction, apoptosis, and necrosis as well as remodeling of cytoskeletal attachments in the process of cell migration and cell cycle progression (Schoenwaelder et al, 1997; Squier et al, 1999; Glading et al, 2002; Franco and Huttenlocher, 2005; Tan et al, 2006; Croall and Ersfeld, 2007). Current experimental approaches for the identification of calpain cleavage sites mainly include Edman N-terminal sequencing, mass spectrometry, and a peptide library approach; a large number of calpain cleavage proteins and sites have been experimentally verified. The application of current experimental techniques has increased the number of experimentally identified calpain substrates with cleavage sites, there are numerous substrates and cleavage sites that remain to be discovered. The computational approaches developed to accurately predict calpain substrates and cleavage sites may complement and guide the experimental studies to promote the discovery of putative cleavage sites

Methods

Results

Conclusion