TM-ZC: A Deep Learning-Based Predictor for the Z-Coordinate of Residues in α-Helical Transmembrane Proteins

Abstract

Z-coordinate is an important structural feature of $\alpha $ -helical transmembrane proteins ( $\alpha $ -TMPs), which is defined as the distance from a residue to the center of the biological membrane. Since the $\alpha $ -TMP structures from both experimental solved and computational predicted approaches still cannot cover the requirements in relevant research fields, z-coordinate prediction provides an opportunity to partly descript $\alpha $ -TMP structures based on their sequences, further contributes to function annotation and drug target discovery. For the purpose of improving the prediction accuracy and providing a convenient tool, we proposed a deep learning-based predictor (TM-ZC) for the z-coordinate of residues in $\alpha $ -TMPs. TM-ZC used the one-hot code and the PSSM as input features for a convolutional neural network (CNN) regression model. The experimental results demonstrated that TM-ZC was a powerful predictor, which is simple and fast, and achieved a considerable performance: the average error was 1.958, the percent of prediction error within 3A was 77.461%, and the correlation coefficient (CC) was 0.922. We further discussed the usefulness of TM-ZC predicted z-coordinate and found its high consistency with topology structure and the enhancement of the surface accessibility prediction.