Characterization of the Adeno-Associated Virus 1 and 6 Sialic Acid Binding Site

The adeno-associated viruses (AAVs), which are being developed as gene delivery vectors, display differential cell surface glycan binding and subsequent tissue tropisms. For AAV serotype 1 (AAV1), the first viral vector approved as a gene therapy treatment, and its closely related AAV6, sialic acid (SIA) serves as their primary cellular surface receptor. Toward characterizing the SIA binding site(s), the structure of the AAV1-SIA complex was determined by X-ray crystallography to 3.0 angstrom. Density consistent with SIA was observed in a pocket located at the base of capsid protrusions surrounding icosahedral 3-fold axes. Site-directed mutagenesis substitution of the amino acids forming this pocket with structurally equivalent residues from AAV2, a heparan sulfate binding serotype, followed by cell binding and transduction assays, further mapped the critical residues conferring SIA binding to AAV1 and AAV6. For both viruses five of the six binding pocket residues mutated (N447S, V473D, N500E, T502S, and W503A) abolished SIA binding, whereas S472R increased binding. All six mutations abolished or decreased transduction by at least 50% in AAV1. Surprisingly, the T502S substitution did not affect transduction efficiency of wildtype AAV6. Furthermore, three of the AAV1 SIA binding site mutants-S472R, V473D, and N500E-escaped recognition by the anti-AAV1 capsid antibody ADK1a. These observations demonstrate that common key capsid surface residues dictate both virus binding and entry processes, as well as antigenic reactivity. This study identifies an important functional capsid surface "hot spot" dictating receptor attachment, transduction efficiency, and antigenicity which could prove useful for vector engineering. IMPORTANCE The adeno-associated virus (AAV) vector gene delivery system has shown promise in several clinical trials and an AAV1-based vector has been approved as the first gene therapy treatment. However, limitations still exist with respect to transduction efficiency and the detrimental effects of preexisting host antibodies. This study aimed to identify key capsid regions which can be engineered to overcome these limitations. A sialic glycan receptor recognition pocket was identified in AAV1 and its closely related AAV6, using X-ray crystallography. The site was confirmed by mutagenesis followed by cell binding and transduction assays. Significantly, residues controlling gene expression efficiency, as well as antibody escape variants, were also identified. This study thus provides, at the amino acid level, information for rational structural engineering of AAV vectors with improved therapeutic efficacy.