Enhancing monoclonal antibody diversity by integrating bulk sorting and machine learning

Area of Science:

• Immunology
• Biotechnology
• Bioinformatics

Background:

• Therapeutic monoclonal antibody (mAb) engineering aims to improve affinity and activity.
• Conventional single-cell sorting for mAb discovery is costly and limits analysis.
• Identifying potent neutralizing antibodies requires diverse human mAb libraries, especially for rapidly mutating viruses like SARS-CoV-2.

Purpose of the Study:

• To develop a cost-effective and rapid method for generating diverse human mAb libraries.
• To overcome limitations of single-cell sorting in antibody discovery.
• To explore the potential of synthetic chimeric antibody (SynCA) technology for therapeutic antibody development.

Main Methods:

• Developed synthetic chimeric antibody (SynCA) technology integrating bulk sorting of antigen-specific B cells and machine learning.
• Cloned antibody variable regions from a single cDNA extracted from approximately 5000 B cells.
• Compared SynCA method with single-cell sorting using convalescent sera from COVID-19 patients.

Main Results:

• SynCA method significantly enhanced B cell receptor repertoire diversity in heavy and light chain genes.
• Random pairing of heavy and light chain genes reconstituted diverse mAbs in vitro.
• Nucleotide sequence information from antibody gene regions (D _H and J _L ) was found to predict antibody reconstitution.

Conclusions:

• SynCA technology offers a cost-effective and rapid alternative for generating diverse mAb libraries.
• This method facilitates the discovery of therapeutic, diagnostic, and research mAbs.
• The findings provide new insights into antibody reconstitution prediction based on nucleotide sequence information.