Elucidation of the Correlation between Heme Distortion and Tertiary Structure of the Heme-Binding Pocket Using a Convolutional Neural Network

Abstract

Heme proteins serve diverse and pivotal biological functions. Therefore, clarifying the mechanisms of these diverse functions of heme is a crucial scientific topic. Distortion of heme porphyrin is one of the key factors regulating the chemical properties of heme. Here, we constructed convolutional neural network models for predicting heme distortion from the tertiary structure of the heme-binding pocket to examine their correlation. For saddling, ruffling, doming, and waving distortions, the experimental structure and predicted values were closely correlated. Furthermore, we assessed the correlation between the cavity shape and molecular structure of heme and demonstrated that hemes in protein pockets with similar structures exhibit near-identical structures, indicating the regulation of heme distortion through the protein environment. These findings indicate that the tertiary structure of the heme-binding pocket is one of the factors regulating the distortion of heme porphyrin, thereby controlling the chemical properties of heme relevant to the protein function; this implies a structure–function correlation in heme proteins.

Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network

“…The input voxels were prepared for each atom (C, N, O, and S) and used as an input with four channels. For the detailed procedures for determining the inclusion region and voxelization, please refer to our previous study [28].…”

“…We did not separate the test and cross-validation datasets because of limited data. The detailed procedure of the cross-validation has been described in our previous study [28].…”

“…To compare the cavity shapes of various proteins, the region to be analyzed was limited to the vicinity of the heme molecule: the center and radius of the inclusion sphere (parameters for POVME) were set to the coordinates of the heme iron atom and 8.5 Å, respectively. The detailed procedure for preparing the input protein coordinates has been described in our previous work [28].…”

“…Let I be a set of samples of cavity shapes in a protein group. To estimate the dispersion of cavity shapes, the mean distance from the barycenter for cavity vector vi was calculated for each protein group following the same procedure as our previous work [28] as follows:…”

“…From a simulation study for two oxygen carrier proteins, hemoglobin and myoglobin, it was suggested that the host protein environment affects heme distortion and controls heme's chemical properties relevant to the protein function [26]. As a first step in elucidating such regulation of heme distortion, we elucidated the correlations between the heme distortion and protein environment around heme, including proximal and distal amino acids using a machine learning method [27] and a convolutional neural network (CNN) [28]. Furthermore, our group has successfully constructed a predictor of protein function with heme distortion and axial ligand(s) as input (in preparation).…”