Adeno-associated virus (AAV) is one of the most extensively studied and utilized viral vectors in clinical gene transfer research. However, the serum instability and immunogenicity of AAV vectors significantly limit their application. Here, we endeavored to overcome these limitations by developing a straightforward approach for site-specific PEGylation of AAV via genetic code expansion. This technique includes incorporation of the azide moiety into the AAV capsid protein followed by orthogonal and stoichiometric conjugation of a variety of polyethylene glycols (PEGs) through click chemistry. Using this approach, only the chosen site(s) was consistently PEGylated under mild conditions, preventing nonselective conjugation. Upon a series of in vitro examinations, AAVs conjugated with 20-kD PEG at sites Q325+1, S452+1, and R585+1 showed a 1.7- to 2.4-fold stability improvement in pooled human serum and a nearly twofold reduction in antibody recognition. Subsequent animal research on Sprague Dawley rats displayed a promising 20% reduction in antibody inducement and a higher virus titer in the blood. Together, our data demonstrate successful protection of an AAV vector from antibody neutralization and blood clearance, thereby increasing the efficiency of therapeutic gene delivery.

Recently, detecting logical anomalies is becoming a more challenging task compared to detecting structural ones. Existing encoder–decoder based methods typically compress inputs into low-dimensional bottlenecks on the assumption that the compression process can effectively suppress the transmission of logical anomalies to the decoder. However, logical anomalies present a particular difficulty because, while their local features often resemble normal semantics, their global semantics deviate significantly from normal patterns. Thanks to the generalisation capabilities inherent in neural networks, these abnormal semantic features can propagate through low-dimensional bottlenecks. This ultimately allows the decoder to reconstruct anomalous images with misleading fidelity. To tackle the above challenge, we propose a novel normality prior guided multi-semantic fusion network for unsupervised anomaly detection. Instead of feeding the compressed bottlenecks to the decoder directly, we introduce the multi-semantic features of normal samples into the reconstruction process. To this end, we first extract abstract global semantics of normal cases by a pre-trained vision-language network, then the learnable semantic codebooks are constructed to store representative feature vectors of normal samples by vector quantisation. Finally, the above multi-semantic features are fused and employed as input to the decoder to guide the reconstruction of anomalies to approximate normality. Extensive experiments are conducted to validate the effectiveness of our proposed method, and it achieves the SOTA performance on the MVTec LOCO AD dataset with improvements of 5.7% in pixel-sPRO and 2.6% in image-AUROC. The source code is available at https://github.com/Xmh-L/NPGMF.

Unsupervised medical anomaly detection aims to identify abnormal images by training exclusively on normal samples, thereby enabling the detection of disease related irregularities without the need for large-scale labeled datasets. Current knowledge distillation-based methods typically detect anomalies by comparing feature discrepancies between teacher and student networks. However, because these methods employ an optimization strategy where the teacher and student architectures are highly similar, the student network's features tend to closely mirror those of the teacher, leading to an identity mapping issue. Moreover, the diversity of lesion types in retinal Optical Coherence Tomography (OCT) images further complicates anomaly detection. In this paper, we propose a novel hybrid dual-heterogeneous knowledge distillation network to overcome these challenges. Our approach consists of a teacher network with an encoder-only architecture and a student network that integrates an encoder with dual decoders. This heterogeneous design effectively mitigates the identity mapping problem, enhancing sensitivity to both structural and logical anomalies. Specifically, our Multi Feature Model leverages convolutional and depthwise convolutional blocks to extract and integrate local features for structural anomaly detection, while the Mamba UpNet employs self-supervised learning to capture long-range dependencies and global anomaly patterns. Extensive experiments on two retinal OCT anomaly detection datasets demonstrate that our method achieves state-of-the-art performance, effectively handling diverse anomaly types. The source code is available at https://github.com/Xmh L/HDHKD.