Prediction of stock price movement is regarded as a challenging task of financial time series prediction. Due to the complexity and massive financial market data, the research of deep learning approaches for predicting the future price is very difficult. This study attempted to develop a novel framework, named 13f-LSTM, where the AutoRegressive Integrated Moving Average (ARIMA), for the first time, as one of the technical features, Fourier transforms for trend analysis and Long-Short Term Memory (LSTM), including its variants, to forecast the future’s closing prices. Thirteen historical and technical features of stock were selected as inputs of the proposed 13f-LSTM model. Three typical stock market indices in the real world and their corresponding closing prices in 30 trading days are chosen to examine the performance and predictive accuracy of it. The experimental results show that the 13f-LSTM model outperforms other proposed models in both profitability performance and predictive accuracy.

Lupus nephritis (LN) is a common and serious clinical manifestation of systemic lupus erythematosus (SLE). However, the pathogenesis of LN is not fully understood. The currently available treatments do not cure the disease and appear to have a variety of side effects in the long term. The purpose of this study was to search for key molecules involved in the immune response during the development of LN through bioinformatics techniques to provide a reference for LN-specific targeted therapy. The GSE112943 dataset was downloaded from the Gene Expression Omnibus (GEO) database, and 20 of the samples were selected for analysis. In, total 2330 differentially expressed genes were screened. These differentially expressed genes were intersected with a list of immune genes obtained from the IMMPORT immune database to obtain a total of 128 differentially expressed immune-related genes. Enrichment analysis showed that most of these genes were enriched in the interferon (IFN) signaling pathway. Gene set enrichment analysis (GSEA) revealed that the overall expression information of the sample was also significantly enriched in the interferon signaling pathway. Further analysis of the core gene cluster showed that nine genes, GBP2, VCAM1, ADAR, IFITM1, BST2, MX2, IRF5, OAS1 and TRIM22, were involved in the interferon signaling pathway. According to our analysis, the guanylate binding protein 2 (GBP2), interferon regulatory factor 5 (IRF5) and 2'-5'-oligoadenylate synthetase 1 (OAS1) genes are involved in three interferon signaling pathways. At present, we do not know whether GBP2 is associated with LN. Therefore, this study focuses on the relationship between GBP2 and LN pathogenesis. We speculate that GBP2 may play a role in the pathogenesis of LN as a member of the interferon signaling pathway. Further immunohistochemical results showed that the expression of GBP2 was increased in the renal tissues of LN patients compared with the control group, confirming this conjecture. In conclusion, according to our study, GBP2 is a member of the interferon signaling pathway that may have implications for the pathogenesis of LN and serves as a potential biomarker for LN.

Lupus nephritis (LN) is a common and serious clinical manifestation of systemic lupus erythematosus. However, the pathogenesis of LN is not fully understood. The currently available treatments do not cure the disease and appear to have a variety of side effects in the long term. The purpose of this study was to search for key molecules involved in the LN immune response through bioinformatics techniques to provide a reference for LN-specific targeted therapy. The GSE112943 dataset was downloaded from the Gene Expression Omnibus database, and 20 of the samples were selected for analysis. In total, 2330 differentially expressed genes were screened. These genes were intersected with a list of immune genes obtained from the IMMPORT immune database to obtain 128 differentially expressed immune-related genes. Enrichment analysis showed that most of these genes were enriched in the interferon signalling pathway. Gene set enrichment analysis revealed that the sample was significantly enriched for expression of the interferon signalling pathway. Further analysis of the core gene cluster showed that nine genes, GBP2, VCAM1, ADAR, IFITM1, BST2, MX2, IRF5, OAS1 and TRIM22, were involved in the interferon signalling pathway. According to our analysis, the guanylate binding protein 2 (GBP2), interferon regulatory factor 5 and 2′-5′-oligoadenylate synthetase 1 (OAS1) genes are involved in three interferon signalling pathways. At present, we do not know whether GBP2 is associated with LN. Therefore, this study focused on the relationship between GBP2 and LN pathogenesis. We speculate that GBP2 may play a role in the pathogenesis of LN as a member of the interferon signalling pathway. Further immunohistochemical results showed that the expression of GBP2 was increased in the renal tissues of LN patients compared with the control group, confirming this conjecture. In conclusion, GBP2 is a member of the interferon signalling pathway that may have implications for the pathogenesis of LN and serves as a potential biomarker for LN. Supplementary Information The online version contains supplementary material available at 10.1186/s12865-022-00520-5.

No abstract

A new cryosection milling imaging system with high spatial resolution is developed to screen small laboratory animals such as mice and rats. The system hardware consists of cutting device, Image Capture and Photography device, refrigerated storage and parallel data processing system. By this system high spatial resolution (no less than 20 μm) small laboratory animal atlas can be achieved. After image registration, image segmentation and 3D reconstruction, a small laboratory animal can be visualized. This paper, taking an adult SD (Sprague-Dawley) rat as an example, describes an experimental process of cryoection milling imaging, in which SD Rat atlas was obtained(the voxels size is 20 μm × 20 μm × 20 μm, cryosection images were captured in 4,600×2,580×24-bit BMP format, 9475 pages, 314.68G). By this system 3D microstructure of small laboratory animal can be obtained accurately. Cryoection milling imaging system offers a new efficient method for small laboratory animal study.