Protein Interresidue Contact Prediction Based on Deep Learning and Massive Features from Multi-sequence Alignment

Abstract

Predicting the corresponding 3D structure from the protein’s sequence is one of the most challenging tasks in computational biology, and a confident interresdiue contact map serves as the main driver towards ab initio protein structure prediction. Benefiting from the ever-increasing sequence databases, residue contact prediction has been revolutionized recently by the introduction of direct coupling analysis and deep learning techniques. However, existing deep learning contact prediction methods often rely on a number of external programs and are therefore computationally expensive. Here, we introduce a novel contact prediction method based on fully convolutional neural networks and extensively extracted evolutionary features from multi-sequence alignment. The results show that our deep learning model based on a highly optimized feature extraction mechanism is very effective in interresidue contact prediction.