RHOJ as a novel mechanosensitive modulator of endothelial inflammation.

Physiological high shear stress (HSS), a frictional force generated by flowing blood, is essential for endothelial homeostasis under normal physiological conditions. HSS suppresses atherosclerosis by inhibiting endothelial inflammation. However, the molecular mechanisms underlying this process have not been fully elucidated. Here, we report that HSS downregulated the mRNA and protein levels of ras homolog family member J (RHOJ) in endothelial cells (ECs). Silencing endogenous RHOJ expression decreased the mRNA and protein levels of proinflammatory vascular cell adhesion molecule 1 (VCAM-1) and intercellular cell adhesion molecule 1 (ICAM-1) in ECs, leading to a reduction in monocyte adhesion to ECs. Conversely, the overexpression of RHOJ had the opposite effect. RNA-sequencing analysis uncovered several differentially expressed genes (such as yes-associated protein 1 (YAP1),heme oxygenase-1 (HO1), and monocyte chemoattractant protein-1 (MCP1)) and pathways (such as nuclear factor-kappa B (NF-κB), fluid shear stress and atherosclerosis, and cell adhesion pathways) as RHOJ targets. Additionally, HSS was observed to alleviate endothelial inflammation by inhibiting RHOJ expression. Finally, methylated RNA immunoprecipitation sequencing (MeRIP-seq) illustrated that fluid shear stress regulates RHOJ expression in an N6-methyladenosine (m6A)-dependent manner. Mechanistically, the RNA m6A writer, methyltransferase 3 (METTL3), and the RNA m6A readers, YTH N6-methyladenosine RNA-binding protein F 3 (YTHDF3) and YTH N6-methyladenosine RNA-binding protein C 1/2 (YTHDC1/2), are involved in this process. Taken together, our data demonstrate that HSS-induced downregulation of RHOJ contributes to endothelial homeostasis by suppressing endothelial inflammation and that RHOJ inhibition in ECs is a promising therapeutic strategy for endothelial dysfunction.

Deep Learning Model for Coronary Angiography.

The visual inspection of coronary artery stenosis is known to be significantly affected by variation, due to the presence of other tissues, camera movements, and uneven illumination. More accurate and intelligent coronary angiography diagnostic models are necessary for improving the above problems. In this study, 2980 medical images from 949 patients are collected and a novel deep learning-based coronary angiography (DLCAG) diagnose system is proposed. Firstly, we design a module of coronary classification. Then, we introduce RetinaNet to balance positive and negative samples and improve the recognition accuracy. Additionally, DLCAG adopts instance segmentation to segment the stenosis of vessels and depict the degree of the stenosis vessels. Our DLCAG is available at http://101.132.120.184:8077/ . When doctors use our system, all they need to do is login to the system, upload the coronary angiography videos. Then, a diagnose report is automatically generated.