Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warranted.

BACKGROUND: SARS-CoV-2-neutralizing antibodies (nABs) showed great promise in the early phases of the COVID-19 pandemic. The emergence of resistant strains, however, quickly rendered the majority of clinically approved nABs ineffective. This underscored the imperative to develop nAB cocktails targeting non-overlapping epitopes. METHODS: Undertaking a nAB discovery program, we employed a classical workflow, while integrating artificial intelligence (AI)-based prediction to select non-competing nABs very early in the pipeline. We identified and in vivo validated (in female Syrian hamsters) two highly potent nABs. FINDINGS: Despite the promising results, in depth cryo-EM structural analysis demonstrated that the AI-based prediction employed with the intention to ensure non-overlapping epitopes was inaccurate. The two nABs in fact bound to the same receptor-binding epitope in a remarkably similar manner. INTERPRETATION: Our findings indicate that, even in the Alphafold era, AI-based predictions of paratope-epitope interactions are rough and experimental validation of epitopes remains an essential cornerstone of a successful nAB lead selection. FUNDING: Full list of funders is provided at the end of the manuscript.

An affinity-enhanced, broadly neutralizing heavy chain-only antibody protects against SARS-CoV-2 infection in animal models.

Broadly neutralizing antibodies are an important treatment for individuals with coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Antibody-based therapeutics are also essential for pandemic preparedness against future Sarbecovirus outbreaks. Camelid-derived single domain antibodies (VHHs) exhibit potent antimicrobial activity and are being developed as SARS-CoV-2­neutralizing antibody-like therapeutics. Here, we identified VHHs that neutralize both SARS-CoV-1 and SARS-CoV-2, including now circulating variants. We observed that the VHHs bound to a highly conserved epitope in the receptor binding domain of the viral spike protein that is difficult to access for human antibodies. Structure-guided molecular modeling, combined with rapid yeast-based prototyping, resulted in an affinity enhanced VHH-human immunoglobulin G1 Fc fusion molecule with subnanomolar neutralizing activity. This VHH-Fc fusion protein, produced in and purified from cultured Chinese hamster ovary cells, controlled SARS-CoV-2 replication in prophylactic and therapeutic settings in mice expressing human angiotensin converting enzyme 2 and in hamsters infected with SARS-CoV-2. These data led to affinity-enhanced selection of the VHH, XVR011, a stable anti­COVID-19 biologic that is now being evaluated in the clinic.