Deep learning is currently an extremely active research area in machine learning and pattern recognition society. It has gained huge successes in a broad area of applications such as speech recognition, computer vision, and natural language processing. With the sheer size of data available today, big data brings big opportunities and transformative potential for various sectors; on the other hand, it also presents unprecedented challenges to harnessing data and information. As the data keeps getting bigger, deep learning is coming to play a key role in providing big data predictive analytics solutions. In this paper, we provide a brief overview of deep learning, and highlight current research efforts and the challenges to big data, as well as the future trends.INDEX TERMS Classifier design and evaluation, feature representation, machine learning, neural nets models, parallel processing.

Chiral tertiary alcohols are an important class of organic compounds which have found wide applications in both academia and industry. Therefore, various synthetic strategies towards these compounds have already been developed. Among them, the catalytic asymmetric addition of carbon nucleophiles to ketones is the most desirable route owing to its straightforwardness as well as its economic, efficient and versatile advantages. This review summarizes and discusses the recent achievements in this field classified according to the reaction types. Special attention is paid to the mechanisms, advantages and limitations of each reaction. In addition, the applications of these catalytic processes in the synthesis of related natural products, pharmaceuticals or their analogues are briefly discussed as well.

While genome sequencing projects have generated tremendous amounts of protein sequence data for a vast number of genomes, substantial portions of most genomes are still unannotated. Despite the success of experimental methods for identifying protein functions, they are often lab intensive and time consuming. Thus, it is only practical to use in silico methods for the genome-wide functional annotations. In this paper, we propose new features extracted from protein sequence only and machine learning-based methods for computational function prediction. These features are derived from a position-specific scoring matrix, which has shown great potential in other bininformatics problems. We evaluate these features using four different classifiers and yeast protein data. Our experimental results show that features derived from the position-specific scoring matrix are appropriate for automatic function annotation.

Background: Recently, multiple lines of evidence have demonstrated that linc00662 serves as an oncogene in various cancers. However, the exact mechanism of oncogenesis mediated by linc00662 in colorectal cancer (CRC) remains unknown. In this study, we aimed to explore the biological role of linc00662 in the regulation of CRC progression.Methods: Both gene expression omnibus (GEO) and the cancer genome atlas (TCGA) datasets were used to evaluate the expression of linc00662. RT-qPCR was used to analyze the expression of linc00662, miR-497-5p, and AVL9 in CRC clinical samples and cell lines. Cell Counting Kit-8 (CCK-8), flow cytometry, transwell assay, and xenograft model were used to investigate the effect of linc00662 on CRC cell proliferation, cell cycle, and metastasis. Western blot analysis was used to analyze the expression of the epithelial-mesenchymal transition (EMT)-associated markers. Furthermore, bioinformatics analysis and mechanism assays were used to elucidate the underlying mechanism. Dual-luciferase reporter assays were used to analyze the regulatory relationships among linc00662, miR-497-5p, and AVL9.Results: In this study, we found that the expression of linc00662 was significantly upregulated in CRC tissues compared to normal tissues and positively correlated with tissue differentiation, T stage, and lymphatic metastasis. Further, our data showed that the expression of linc00662 was positively associated with lymph node metastasis, TMN stage, and poor-moderate differentiation. Patients with higher linc00662 expression level were more likely to have poorer overall survival. Knockdown of linc00662 inhibited CRC cell growth, induced cell apoptosis, triggered cell cycle arrest at G2/M phase, and suppressed cell migration and invasion through regulating the EMT pathway. Further, mechanistic studies revealed that knockdown of linc00662 significantly reduced the expression of AVL9, a direct target of miR-497-5p.Conclusions: Linc00662 was significantly upregulated in CRC, and mediated CRC progression and metastasis by competing with miR-497-5p to modulate the expression of AVL9. Therefore, our result sheds light on the potential application of linc00662 in CRC diagnosis and therapy.

Liver tumorigenesis Lung metastasis p53 mut/+ Highlights Tsc1 deficiency facilitates p53 (haplo)insufficiency-mediated activation of the PTEN/Akt/mTOR axis to drive HCC tumorigenesis and metastasis. Inhibiting mTOR activation is a potential therapeutic strategy for p53 insufficiency and Tsc1 insufficiency-driven hepatocarcinogenesis. The oncogenic activity of the Akt/mTOR axis relies on Abcc4, which labels an aggressive subtype of human HCC.