Protein sequence design method of fixed skeleton based on graph network mask node classification

Abstract

A protein sequence design method of a fixed skeleton based on graph network mask node classification comprises the following steps: in an offline stage, training a graph neural network by constructing a protein nearest neighbor graph of a sample as a training set; in the online stage, the nearest graph of the protein structure of the deleted sequence is processed through the trained graph neural network, the category probability of the deleted amino acid is obtained, and then the category probability is sampled to obtain the predicted deleted amino acid sequence. According to the method, more structural constraints are added, distance and relative angle features and dihedral angle features of each amino acid are added to connected amino acid pairs in a protein map, and then a neighbor map is established, so that a more efficient map network based on a Transform multiple attention mechanism is realized, and the optimal amino acid mask proportion is explored.

Description

technical field [0001] The invention relates to a technology in the field of bioengineering, in particular to a method for designing protein sequences with fixed skeletons based on graph network mask node classification. Background technique [0002] Protein design is an important method to study the relationship between protein sequence and protein structure. It designs novel proteins by designing amino acid sequences with specific structures. At present, the technology of protein design using deep learning generally divides protein design into two steps. First, the protein skeleton is generated according to the required function, and then the protein design of the fixed skeleton is carried out, and a specific and stable three-dimensional structure is strived for. [0003] ProteinSolver (https: / / github.com / ostrokach / proteinsolver) belongs to a fixed-skeleton protein design method, which models protein design as a constraint satisfaction problem (CSP), specifically using the...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of insufficient structural feature constraints of the existing ProteinSolver and insufficient efficiency of the network model, the present invention proposes a fixed-skeleton protein sequence design method based on graph network mask node classification, which adds more structural constraints, and in the protein graph The distance and relative angle features and the dihedral angle features of each amino acid are added to the connected amino acid pairs, and then the neighbor graph is established to realize a more efficient graph network based on Transformer's multi-head attention mechanism and explore the optimal amino acid mask ratio.

Images