EBP-A: a prediction method of protein backbone torsion angle based on convolutional neural network

Abstract

Protein backbone torsion angles prediction from sequence is an important sub-problem in protein structure prediction. The prediction of protein backbone torsion angle can help to achieve an accurate prediction of protein structure and its function determination. Therefore, there are many methods for the prediction of protein backbone torsion angle. However, most existing methods are profile-based, and most proteins(more than 90%) have none or very few homologous sequences for generating evolutionary information. In addition, with the development of protein sequencing technology, the number of sequences in the protein sequence library continues to grow rapidly. To this end, this paper proposes a new embeddings-based prediction method, which takes the embedding feature of amino acid sequences as input, and designs a suitable network structure, to prediction protein backbone torsion angles. The experimental results on the Test2018 and Test2016 test datasets show that our method has higher prediction accuracy than existing prediction methods.