Machine learning-based antibody screening method and device

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a machine learning-based antibody screening method, which comprises the following steps: collecting topological structure information of an antigen and an antibody and knowledge graph information of the interaction of the antigen and the antibody, and constructing a sample set based on the topological structure information and the knowledge graph information; training a network model in a directed transmission mode by using a sample set containing topological structure information and knowledge graph information, and constructing an antibody prediction model capable of sensing the molecular structure and knowledge graph characteristics; and inputting the amino acid sequence and topological structure information of a to-be-predicted target antigen into the antibody prediction model in response to an instruction of screening the target antibody for the target antigen, so as to obtain amino acid sequence information of the target antibody with neutralizing activity on the target antigen. The method can learn and excavate the topological structure of the antigen and the antibody and the knowledge map characteristics of the interaction of the antigen and the antibody, and can be used as the prediction discovery of the neutralizing antibody, so that the screening effect of the antibody is improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an antibody screening method, device, computer equipment and computer storage medium based on machine learning. Background technique [0002] Monoclonal antibodies are very important biological products in virus therapy, cancer treatment, disease monitoring, and experimental research, and are in huge demand. In the screening process of traditional monoclonal antibodies, it is necessary to continuously inject antigens into immunized animals, take effector B lymphocytes from the spleen of mice, screen hybridoma cells in HAT culture medium, and then screen out hybridoma cell populations that can produce antibodies against a certain antibody. A specific hybridoma cell with a predetermined antigenic determinant is cultured from one cell to form a cell population and the secreted antibody is collected. Even if the monoclonal antibody obtained in this way, most p...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a machine learning-based antibody screening method, device, computer equipment and computer storage medium, the main purpose of which is to solve the problem that the antibody library constructed based on deep learning in the prior art can only target antibody sequence information or The coding gene sequence of the antibody is processed, and it is impossible to learn and mine the antigen, the topology structure of the antibody, and the knowledge map features of the antigen-antibody interaction, resulting in the problem of unsatisfactory antibody screening effect

Images