Residue distance prediction from the sequence is critical for many biological applications such as protein structure reconstruction, protein–protein interaction prediction, and protein design. However, prediction of fine-grained distances between residues with long sequence separations still remains challenging. In this study, we propose DuetDis, a method based on duet feature sets and deep residual network with squeeze-and-excitation (SE), for protein inter-residue distance prediction. DuetDis embraces the ability to learn and fuse features directly or indirectly extracted from the whole-genome/metagenomic databases and, therefore, minimize the information loss through ensembling models trained on different feature sets. We evaluate DuetDis and 11 widely used peer methods on a large-scale test set (610 proteins chains). The experimental results suggest that 1) prediction results from different feature sets show obvious differences; 2) ensembling different feature sets can improve the prediction performance; 3) high-quality multiple sequence alignment (MSA) used for both training and testing can greatly improve the prediction performance; and 4) DuetDis is more accurate than peer methods for the overall prediction, more reliable in terms of model prediction score, and more robust against shallow multiple sequence alignment (MSA).

/pdf/inter-residue-distance-prediction-from-duet-deep-learning-1yz11uat.pdf

Inter-Residue Distance Prediction From Duet Deep Learning Models

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.

Yanjie Wei

Papers

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