RACK1 promotes the occurrence and progression of cervical carcinoma.

BACKGROUND: RACK1 has been identified as a multifunctional cytosolic protein, and plays a pivotal role in multiple biological responses involved in several kinds of tumors, while its effect in cervical cancer has not been well elucidated yet. The study aimed to investigate the role of RACK1 in cervical cancer occurrence and progression. METHODS: The expression of RACK1 in cervical specimens was measured by immunohistochemical staining and Western blot assay. Transgenic mice were used to detect the role of RACK1 in modulating tumorigenesis in vivo. Cervical carcinoma cell lines were used to explore the underlying mechanisms of RACK1 on the behaviors of tumor cells in vitro. RESULTS: We found that RACK1 expression was upregulated in cancer tissues compared with adjacent tissues, and its expression was gradually increased from cervictis, and cervical intraepithelial neoplasis (CIN) to carcinoma. Genetic overexpression of RACK1 facilitated tumor formation and growth in nude mice. Mechanism studies disclosed that RACK1 over-expression prolonged the G0 /G1 phase by up-regulating the expression of cyclinD1, down-regulating p21 and p27 probably by modulating the phosphorylation of AKT. CONCLUSIONS: Taken together, we concluded that RACK1 stimulates tumorigenesis and progression of cervical cancer via modulating the proliferation of tumor cells, implying that targeting RACK1 may serve as a promising method for cervical cancer therapy.

A GAN-based anomaly detector using multi-feature fusion and selection.

In numerous applications, abnormal samples are hard to collect, limiting the use of well-established supervised learning methods. GAN-based models which trained in an unsupervised and single feature set manner have been proposed by simultaneously considering the reconstruction error and the latent space deviation between normal samples and abnormal samples. However, the ability to capture the input distribution of each feature set is limited. Hence, we propose an unsupervised and multi-feature model, Wave-GANomaly, trained only on normal samples to learn the distribution of these normal samples. The model predicts whether a given sample is normal or not by its deviation from the distribution of normal samples. Wave-GANomaly fuses and selects from the wave-based features extracted by the WaveBlock module and the convolution-based features. The WaveBlock has proven to efficiently improve the performance on image classification, object detection, and segmentation tasks. As a result, Wave-GANomaly achieves the best average area under the curve (AUC) on the Canadian Institute for Advanced Research (CIFAR)-10 dataset (94.3%) and on the Modified National Institute of Standards and Technology (MNIST) dataset (91.0%) when compared to existing state-of-the-art anomaly detectors such as GANomaly, Skip-GANomaly, and the skip-attention generative adversarial network (SAGAN). We further verify our method by the self-curated real-world dataset, the result show that our method is better than GANomaly which only use single feature set for training the model.