YabXnization platform: A monoclonal antibody heterologization server based on rational design and artificial intelligence-assisted computation

Abstract

The application of antibody therapeutics is promising in the field of immunotherapy. While, heterologization should be done in most cases before applying the therapeutic antibodies into bodies, e.g., humanization, caninization and felinization for human beings, canine and feline, respectively. Here we report YabXnization, the platform which realizes antibody heterologization on the basis of rational design and artificial intelligence (AI)-assisted computation. YabXnization provides two ways for heterologization: traditional CDR-grafting and backmutation-based rational design; and AI-assisted fusion computational design. Taking humanization as example, both of the two ways first find the proper template for heavy and light chains with CDR-grafting followed. For rational design, bioinformatics analysis-based backmutation is then conducted. For AI-assisted computational design, the backmutation and humanness evaluation are implemented through evolutionary computation framework with DeepForest-based humanness evaluation model and the distance to the previously found human template as objective functions. Finally, the top heterologized antibodies can be provided by YabXnization platform. We examined the platform with 18 antibodies to be heterologized, in which 10 for humanization, 6 for caninization and 2 for felinization, respectively. The heterologized antibodies were measured by indirect ELISA and BLI(Octet)/SPR(Biacore) binding affinity measurement methods. Test results show a 90% success rate with the binding affinity loss of heterologized antibodies within an order of magnitude compared to the corresponding chimeric antibodies. It even shows an increase in the binding affinity on some of the heterologized antibodies. The platform can be reached through .