AUTHOR=Arras Paul , Yoo Han Byul , Pekar Lukas , Clarke Thomas , Friedrich Lukas , Schröter Christian , Schanz Jennifer , Tonillo Jason , Siegmund Vanessa , Doerner Achim , Krah Simon , Guarnera Enrico , Zielonka Stefan , Evers Andreas TITLE=AI/ML combined with next-generation sequencing of VHH immune repertoires enables the rapid identification of de novo humanized and sequence-optimized single domain antibodies: a prospective case study JOURNAL=Frontiers in Molecular Biosciences VOLUME=Volume 10 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2023.1249247 DOI=10.3389/fmolb.2023.1249247 ISSN=2296-889X ABSTRACT=In this study, we demonstrate the feasibility of yeast surface display (YSD) and next generation 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. 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 fluorescenceactivated cell sorting (FACS), 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. 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.