Introduction: In this study, we demonstrate the feasibility of yeast surface display (YSD) and nextgeneration sequencing (NGS) in combination with artificial intelligence and machine learning methods (AI/ML) for the identification of de novo humanized single domain antibodies (sdAbs) with favorable early developability profiles. Methods: The display library was derived from a novel approach, in which VHH-based CDR3 regions obtained from a llama (Lama glama), immunized against NKp46, were grafted onto a humanized VHH backbone library that was diversified in CDR1 and CDR2. Following NGS analysis of sequence pools from two rounds of fluorescence-activated cell sorting we focused on four sequence clusters based on NGS frequency and enrichment analysis as well as in silico developability assessment. For each cluster, long short-term memory (LSTM) based deep generative models were trained and used for the in silico sampling of new sequences. Sequences were subjected to sequence- and structure-based in silico developability assessment to select a set of less than 10 sequences per cluster for production. Results: As demonstrated by binding kinetics and early developability assessment, this procedure represents a general strategy for the rapid and efficient design of potent and automatically humanized sdAb hits from screening selections with favorable early developability profiles.

BACKGROUND: Adoptive cell therapy with engineered T cells expressing chimeric antigen receptors (CARs) originated from antibodies is a promising strategy in cancer immunotherapy. Several unsuccessful trials, however, highlight the need for alternative conventional binding domains and the better combination of costimulatory endodomains for CAR construction to improve the effector functions of the engineered T cells. Camelid single-domain antibodies (VHHs), which are the smallest single domain antibodies, can endow great targeting ability to CAR-engineered T cells.
METHODS: We have developed a method to generate genetically engineered Jurkat T cells armed with a CAR comprising the anti-HER2 VHH as targeting moiety. From an immune camel library, five VHH clones were selected as a set of oligoclonal anti-HER2 VHHs that exhibited diverse binding abilities and joined them to CD28-CD3ζ and CD28-OX40-CD3ζ signaling endodomains. Jurkat T cells expression of VHH-CARs and cell functions were evaluated.
RESULTS: The oligoclonal engineered T cells showed higher proliferation, cytokine secretion and cytotoxicity than each individual VHH-CAR-engineered Jurkat T cells.
CONCLUSIONS: The combination of superior targeting ability of oligoclonal VHHs with the third generation CAR can substantially improve the function of engineered T cells.
CONCLUSIONS: Antigen-specific directed oligoclonal T cells are alternatively promising, but safer systems, to combat tumor cells.