No abstract

Motivation Protein-protein interaction (PPI), as a relative property, is determined by two binding proteins, which brings a great challenge to design an expert model with an unbiased learning architecture and a superior generalization performance. Additionally, few efforts have been made to allow PPI predictors to discriminate between relative properties and intrinsic properties. Results We present a sequence-based approach, DeepTrio, for PPI prediction using mask multiple parallel convolutional neural networks. Experimental evaluations show that DeepTrio achieves a better performance over several state-of-the-art methods in terms of various quality metrics. Besides, DeepTrio is extended to provide additional insights into the contribution of each input neuron to the prediction results. Availability We provide an online application at http://bis.zju.edu.cn/deeptrio. The DeepTrio models and training data are deposited at https://github.com/huxiaoti/deeptrio.git. Supplementary information Supplementary data are available at Bioinformatics online.

This paper proposes a UAV platform that autonomously detects, hunts, and takes down other small UAVs in GPS-denied environments. The platform detects, tracks, and follows another drone within its sensor range using a pre-trained machine learning model. We collect and generate a 58,647-image dataset and use it to train a Tiny YOLO detection algorithm. This algorithm combined with a simple visual-servoing approach was validated on a physical platform. Our platform was able to successfully track and follow a target drone at an estimated speed of 1.5 m/s. Performance was limited by the detection algorithm’s 77% accuracy in cluttered environments and the frame rate of eight frames per second along with the field of view of the camera.

No abstract

Background Osteoarthritis (OA) is one of the most common degenerative diseases worldwide. Many researchers are studying the pathogenesis of OA, however, it is still unclear. Methods Screening and validation of OA relevant hub genes are an important part of exploring their potential molecular mechanism. Therefore, this study aims to explore and verify the mechanisms of hub genes in the OA by bioinformatics, qPCR, fluorescence and propidium iodide staining. Results Microarray datasets GSE43923, GSE55457 and GSE12021 were collected in the Gene Expression Omnibus (GEO), including 45 samples, which divided into 23 osteoarthritis knee joint samples and 22 samples of normal knee joint. Thereafter, 265 differentiallyexpressedgenes (DEGs) were identified in all, which divided into 199 upregulated genes and 66 downregulated genes. The hub genes MAPK-14, PTPRC, PTPN12 were upregulated, while B9D1 was downregulated. In order to further confirm the expression of screening differential genes in human chondrocytes, the human chondrocytes were extracted from a joint replacement surgery and stained with toluidine blue for identification. Compared with normal chondrocytes, OA chondrocytes had high expression of COL I protein and low expression of COL II protein. The expression levels of MAPK-14, PTPRC and PTPN12 in OA chondrocytes were significantly higher than the expression levels of B9D1 in normal chondrocytes. Moreover, the inflammatory necrosis of OA chondrocytes was increased compared with the normal chondrocytes by propidium iodide staining. Conclusions The high expression of MAPK-14 works as a promoter of chondrocytes death and an important signal of the osteoarthritis process.

Background Recently, ClC-3 chloride channel expression has been noted to be high in some tumors. In chondrosarcoma, which is a malignant tumor with a high incidence in the bone, there has been no previous literature regarding ClC-3 chloride channel expression. Here we evaluated the expression of ClC-3 chloride channel in chondrosarcoma and explored its clinical significance. Material/Methods In this study, 75 chondrosarcoma and 5 normal cartilage tissues were collected. Thereafter, tissue microarray was performed. Immunohistochemistry was also used to observe the level of ClC-3 chloride channel expression between normal and chondrosarcoma tissues. Results Results showed that the expression of ClC-3 chloride channel in the normal chondrocyte was thinner, since it showed distinct differentiation among chondrosarcoma specimens. Interestingly, we noticed that the moderately-differentiated chondrosarcoma (MDC) and the poorly-differentiated chondrosarcoma (PDC) exhibited 94.44% of ClC-3 chloride channel. Besides, the subcellular localization of ClC-3 chloride channel was changed in association with malignant degree changes. The subcellular localization of ClC-3 chloride channel in the MDC and PDC tissue was localized in the cytoplasm and both nucleus and cytoplasm: 83.33% (5 out of 6 cases) and 91.66% (11 out of 12 cases) respectively. On the other hand, we noticed that patient age and gender could have a relation with ClC-3 chloride channel expression; 30- to 60-year-old males showed more expression. Conclusions These results demonstrated a high frequency of ClC-3 chloride channel overexpression and subcellular localization differences in MDC and PDC tissue, suggesting a specific role of ClC-3 chloride channel in the pathogenesis of chondrosarcoma.

Osteoarthritis (OA) is one of the most common causes of disability and its development is associated with numerous factors. A major challenge in the treatment of OA is the lack of early diagnosis. In the present study, a bioinformatics method was employed to filter key genes that may be responsible for the pathogenesis of OA. From the Gene Expression Omnibus database, the datasets GSE55457, GSE12021 and GSE55325 were downloaded, which comprised 59 samples. Of these, 30 samples were from patients diagnosed with osteoarthritis and 29 were normal. Differentially expressed genes (DEGs) were obtained by downloading and analyzing the original data using bioinformatics. The Gene Ontology enrichment and Kyoto Encyclopedia of Genes and Genomes pathways were analyzed using the Database for Annotation, Visualization and Integrated Discovery online database. Protein-protein interaction network analysis was performed using the Search Tool for the Retrieval of Interacting Genes/proteins online database. BSCL2 lipid droplet biogenesis associated, seipin, FOS-like 2, activator protein-1 transcription factor subunit (FOSL2), cyclin-dependent kinase inhibitor 1A (CDKN1A) and kinectin 1 (KTN1) genes were identified as key genes by using Cytoscape software. Functional enrichment revealed that the DEGs were mainly accumulated in the ErbB, MAPK and PI3K-Akt pathways. Reverse transcription-quantitative PCR analysis confirmed a significant reduction in the expression levels of FOSL2, CDKN1A and KTN1 in OA samples. These genes have the potential to become novel diagnostic and therapeutic targets for OA.

No abstract