Dynamic and Static Representation Learning Network for Recommendation.

Existing review-based recommendation methods learn a latent representation of user and item from user-generated reviews by a static strategy, which are unable to capture the dynamic evolution of users' interests and the dynamic attraction of items. Here, we propose a dynamic and static representation learning network (DSRLN) to improve the rating prediction accuracy by exploring fine-grained representations of users and items. Specifically, we built DSRLN with a dynamic representation extractor to model the dynamic evolution of users' interests by exploring the inner relations of an interaction sequence, and with a static representation extractor to model the users' intrinsic preferences by learning the semantic coherence and feature strength information from reviews. To identify the different influences of dynamic and static features for different users, a personalized adaptive fusion module was designed using a weighted attention mechanism. Extensive experiments on five real-world datasets from Amazon demonstrated the superiority of the proposed model, and the additional ablation studies verified the effectiveness of the components designed in the DSRLN model.

microRNA-206 Suppresses Cholangiocarcinoma Cell Growth and Invasion by Targeting Jumonji AT-Rich Interactive Domain 2.

BACKGROUND: The current study set out to elucidate the specific role of microRNA (miR)-206 in cholangiocarcinoma (CCA) cell biological activities by negatively modulating jumonji AT-rich interactive domain 2 (JARID2). METHODS: Firstly, human intrahepatic biliary epithelial cells and CCA cell lines were selected via the analysis of miR-206 and JARID2 expression patterns in CCA by qRT-PCR. Next, the target relation between miR-206 and JARID2 was predicted by Targetscan and validated using dual-luciferase reporter gene assay and RNA immunoprecipitation (RIP) assay. Subsequently, CCK-8 method, colony formation assay, scratch test, Transwell assay, and western blot analysis were performed to evaluate cancer cell development after the overexpression of miR-206 and/or JARID2, with levels of invasion-related proteins assessed. In addition, xenograft transplantation was also employed to confirm the role of miR-206 in vivo. Lastly, Ki-67 expression pattern was also quantified with immunohistochemistry. RESULTS: It was found that miR-206 was poorly expressed and JARID2 was highly expressed in CCA cell lines. Also, miR-206 overexpression brought about a suppressive effect on cancer cell proliferation, migration, and invasion. Furthermore, miR-206 was observed to target JARID2. Meanwhile, JARID2 overexpression promoted cell growth, while simultaneous overexpression of miR-206 and JARID2 impeded malignant cancer progression, indicating that miR-206 overexpression inhibited cell progression via targeting JARID2. Finally, in vivo experimentation illustrated that miR-206 overexpression suppressed tumor growth and weight, and inhibited the expressions of JARID2 N-cadherin, vimentin, and Ki-67. CONCLUSION: Altogether, our findings clarified that miR-206 inhibited CCA malignancy by negatively regulating JARID2.

LncRNA ANCR Promotes Invasion and Migration of Gastric Cancer by Regulating FoxO1 Expression to Inhibit Macrophage M1 Polarization.

BACKGROUND: Long non-coding RNAs (LncRNAs) are closely related to the occurrence of cancer, but its mechanism in gastric cancer (GC) is still largely unclear. AIMS: This study aimed to reveal the underlying mechanism of LncRNA ANCR in GC. METHODS: The expression of LncRNA ANCR was detected by qRT-PCR. ELISA was used to identify THP-1 cells into macrophage M1 type polarization. After macrophages overexpressing LncRNA ANCR were co-cultured with GC cell HGC-27, the invasion and metastasis of GC were analyzed by Transwell assay. The targeted regulation of FoxO1 by LncRNA ANCR was analyzed by RNA pull-down, RNA immunoprecipitation (RIP), and Western blot. The BALB/c nude mouse model of GC was established to analyze the effect of LncRNA ANCR on tumor growth. RESULTS: LncRNA ANCR was highly expressed in GC. The overexpression of LncRNA ANCR in macrophages reduced the concentrations of M1 macrophage polarized marker molecules IL-1ß and IL-6 in the supernatant of cells, and inhibited the polarization of macrophages to M1, while the knockdown of LncRNA ANCR produced the opposite effect. The co-culture of macrophages overexpressing LncRNA ANCR with GC cells promoted the invasion and migration of cells. LncRNA ANCR targeted FoxO1 and inhibited the expression of FoxO1 in THP-1 cells by promoting FoxO1 ubiquitination degradation. In addition, the overexpression of LncRNA ANCR promoted tumor growth in a BALB/c nude mouse model of GC, while the knockdown of LncRNA ANCR produced the opposite effect. CONCLUSIONS: Based on these results, the overexpression of LncRNA ANCR promoted the invasion and metastasis of GC cells via down-regulating FoxO1 to inhibit macrophage polarization to M1.

Associating pancreaticostomy and biliary-irrigation for staged pancreaticoduodenectomy approach to pancreatic intraductal papillary mucinous neoplasm with recurrent cholangitis and severe jaundice: A case report.

PATIENT CONCERNS: A 63-year-old man was hospitalized with history of abdominal pain since more than 1 year, and that of fever with chills since 2 weeks. DIAGNOSES: Based on the laboratory investigations and radiologic findings, a preliminary diagnosis of pancreatic intraductal papillary mucinous neoplasm (IPMN) with recurrent cholangitis and severe jaundice was made. INTERVENTIONS: An initial attempt at endoscopic and image-guided drainage proved unsuccessful. Due to cholangitis, liver dysfunction, and hypoalbuminemia, the patient was deemed to be medically unfit for radical surgery. Therefore we considered a novel strategy of associating pancreaticostomy and biliary-irrigation for staged pancreaticoduodenectomy (APBSP). In the first stage, biliary tract double irrigation (endoscopic nasobiliary drainage and T-tube) in combination with pancreaticostomy was performed, which alleviated the symptoms and helped improve the general condition of the patient. In the second stage, radical pancreaticoduodenectomy was performed. OUTCOMES: Over a follow-up period of 23 months, no recurrence occurred. LESSONS: In this report, we present a previously unreported treatment strategy for pancreatic IPMN with recurrent cholangitis and jaundice. The innovative treatment approach may help advance the understanding and management of this condition.