Targeting CLK4 inhibits the metastasis and progression of breast cancer by inactivating TGF-ß pathway.

Triple-negative breast cancer (TNBC) represents the most aggressive subtype of breast cancer that is highly resistant to current therapeutic options. According to the public databases Oncomine and KM plotter, the CLK4 expression is correlated with poor patient survival in TNBC, especially in mesenchymal-like TNBC (MES-TNBC) that has strong metastatic potential. Therefore, we investigated the potential involvement of CLK4 in the metastasis and progression of MES-TNBC. In the MES-TNBC cell lines, the CLK4 expression was elevated. Notably, the RNAi-mediated silencing of CLK4 reduced the expression of multiple epithelial-mesenchymal transition (EMT) genes that mediate metastasis. Furthermore, CLK4 silencing reduced both the invasive behaviors of the cultured cells and tumor metastasis in the mouse xenograft model. It is also noteworthy that CLK4 silencing repressed the invasive and cancer stem cell (CSC) properties that are induced by the TGF-ß signaling. Importantly, the pharmacological inhibition of CLK4 potently repressed the invasion and proliferation of MES-TNBC cell lines and patient-derived cells, which demonstrates its clinical applicability. Collectively, our results suggest that CLK4 plays a crucial role in invasion and proliferation of MES-TNBC, especially in the processes that are induced by TGF-ß. Also, this study characterizes CLK4 as a novel therapeutic target in breast cancer.

Standard for the Quantification of a Sterilization Effect Using an Artificial Intelligence Disinfection Robot.

Recent outbreaks and the worldwide spread of COVID-19 have challenged mankind with unprecedented difficulties. The introduction of autonomous disinfection robots appears to be indispensable as consistent sterilization is in desperate demand under limited manpower. In this study, we developed an autonomous navigation robot capable of recognizing objects and locations with a high probability of contamination and capable of providing quantified sterilization effects. In order to quantify the 99.9% sterilization effect of various bacterial strains, as representative contaminants with robots operated under different modules, the operating parameters of the moving speed, distance between the sample and the robot, and the radiation angle were determined. We anticipate that the sterilization effect data we obtained with our disinfection robot, to the best of our knowledge, for the first time, will serve as a type of stepping stone, leading to practical applications at various sites requiring disinfection.

Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild.

We propose a method designed to push the frontiers of unconstrained face recognition in the wild with an emphasis on extreme out-of-plane pose variations. Existing methods either expect a single model to learn pose invariance by training on massive amounts of data or else normalize images by aligning faces to a single frontal pose. Contrary to these, our method is designed to explicitly tackle pose variations. Our proposed Pose-Aware Models (PAM) process a face image using several pose-specific, deep convolutional neural networks (CNN). 3D rendering is used to synthesize multiple face poses from input images to both train these models and to provide additional robustness to pose variations at test time. Our paper presents an extensive analysis of the IARPA Janus Benchmark A (IJB-A), evaluating the effects that landmark detection accuracy, CNN layer selection, and pose model selection all have on the performance of the recognition pipeline. It further provides comparative evaluations on IJB-A and the PIPA dataset. These tests show that our approach outperforms existing methods, even surprisingly matching the accuracy of methods that were specifically fine-tuned to the target dataset. Parts of this work previously appeared in [1] and [2].

Facial Landmark Detection with Tweaked Convolutional Neural Networks.

This paper concerns the problem of facial landmark detection. We provide a unique new analysis of the features produced at intermediate layers of a convolutional neural network (CNN) trained to regress facial landmark coordinates. This analysis shows that while being processed by the CNN, face images can be partitioned in an unsupervised manner into subsets containing faces in similar poses (i.e., 3D views) and facial properties (e.g., presence or absence of eye-wear). Based on this finding, we describe a novel CNN architecture, specialized to regress the facial landmark coordinates of faces in specific poses and appearances. To address the shortage of training data, particularly in extreme profile poses, we additionally present data augmentation techniques designed to provide sufficient training examples for each of these specialized sub-networks. The proposed Tweaked CNN (TCNN) architecture is shown to outperform existing landmark detection methods in an extensive battery of tests on the AFW, ALFW, and 300W benchmarks. Finally, to promote reproducibility of our results, we make code and trained models publicly available through our project webpage.