Search

Network intrusion detection plays a crucial role in ensuring network security by distinguishing malicious attacks from normal network traffic. However, imbalanced data affects the performance of intrusion detection system. This paper utilizes few-shot learning to solve the data imbalance problem caused by insufficient samples in network intrusion detection, and proposes a few-shot intrusion detection method based on prototypical capsule network with the attention mechanism. Our method is mainly divided into two parts, a temporal-spatial feature fusion method using capsules for feature extraction and a prototypical network classification method with attention and vote mechanisms. The experimental results demonstrate that our proposed model outperforms state-of-the-art methods on imbalanced datasets. [ABSTRACT FROM AUTHOR]

N -glycosylation has been revealed to be tightly associated with cancer metastasis. As a key transferase that catalyzes the formation of β1,4 N -acetylglucosamine (β1,4GlcNAc) branches on the mannose core of N -glycans, N -acetylglucosaminyltransferase IVa (GnT-IVa) has been reported to be involved in hepatocellular carcinoma (HCC) metastasis by forming N -glycans; however, the underlying mechanisms are largely unknown. In the current study, we found that GnT-IVa was upregulated in HCC tissues and positively correlated with worse outcomes in HCC patients. We found that GnT-IVa could promote tumor growth in mice; notably, this effect was attenuated after mutating the enzymatic site (D445A) of GnT-IVa, suggesting that GnT-IVa regulated HCC progression by forming β1,4GlcNAc branches. To mechanistically investigate the role of GnT-IVa in HCC, we conducted GSEA and GO functional analysis as well as in vitro experiments. The results showed that GnT-IVa could enhance HCC cell migration, invasion and adhesion ability and increase β1,4GlcNAc branch glycans on integrin β1 (ITGB1), a tumor-associated glycoprotein that is closely involved in cell motility by interacting with vimentin. Interruption of β1,4GlcNAc branch glycan modification on ITGB1 could suppress the interaction of ITGB1 with vimentin and inhibit cell motility. These results revealed that GnT-IVa could promote HCC cell motility by affecting the biological functions of ITGB1 through N -glycosylation. In summary, our results revealed that GnT-IVa is highly expressed in HCC and can form β1,4GlcNAc branches on ITGB1, which are essential for interactions with vimentin to promote HCC cell motility. These findings not only proposed a novel mechanism for GnT-IVa in HCC progression but also revealed the significance of N -glycosylation on ITGB1 during the process, which may provide a novel target for future HCC therapy. • GnT-IVa enhances cell motility and correlates with poor outcomes of HCC. • GnT-IVa increases β1,4GlcNAc branches on ITGB1 to promote cell motility of HCC. • β1,4GlcNAc branches on ITGB1 affect interactions with vimentin in HCC. [ABSTRACT FROM AUTHOR]