DeepMBS: Prediction of Protein Metal Binding-Site Using Deep Learning Networks

Abstract

The tertiary structure of a protein indicates what vital function that protein fulfills in the cell. Prediction of the metal binding comformation of a protein from its sequence is a crucial step in predicting its tertiary structure. In this study, a computational method was developed for predicting the binding of Histidine and Cysteine to metals. We propose a deep convolutional neural network architecture, DeepMBS, to predict protein metal binding sites. To our knowledge, this study is the first realization of deep learning idea for the problem of predicting metal binding site. The method allows automatic extraction of complex interactions between important features using only sequence information by utilizing PAM120 scoring matrix. Features were extracted from protein sequences obtained from the Protein Data Bank and deep convolutional neural network was applied to these features. According to experimental results on a benchmark dataset, metal binding states can be predicted with 82% recall and 79% precision. These results show that a better performance can be achived with deep learning approach compared with previous studies on the same dataset.