Deep graph embedding for prioritizing synergistic anticancer drug combinations.

Drug combinations are frequently used for the treatment of cancer patients in order to increase efficacy, decrease adverse side effects, or overcome drug resistance. Given the enormous number of drug combinations, it is cost- and time-consuming to screen all possible drug pairs experimentally. Currently, it has not been fully explored to integrate multiple networks to predict synergistic drug combinations using recently developed deep learning technologies. In this study, we proposed a Graph Convolutional Network (GCN) model to predict synergistic drug combinations in particular cancer cell lines. Specifically, the GCN method used a convolutional neural network model to do heterogeneous graph embedding, and thus solved a link prediction task. The graph in this study was a multimodal graph, which was constructed by integrating the drug-drug combination, drug-protein interaction, and protein-protein interaction networks. We found that the GCN model was able to correctly predict cell line-specific synergistic drug combinations from a large heterogonous network. The majority (30) of the 39 cell line-specific models show an area under the receiver operational characteristic curve (AUC) larger than 0.80, resulting in a mean AUC of 0.84. Moreover, we conducted an in-depth literature survey to investigate the top predicted drug combinations in specific cancer cell lines and found that many of them have been found to show synergistic antitumor activity against the same or other cancers in vitro or in vivo. Taken together, the results indicate that our study provides a promising way to better predict and optimize synergistic drug pairs in silico.

Long non­coding RNA LINC00473/miR­195­5p promotes glioma progression via YAP1­TEAD1­Hippo signaling.

There is an urgent need to identify novel potential therapeutic targets for diagnosis and treatment of glioma, a common primary tumor in brain, due to its high­level invasiveness. Long non­coding RNA (lncRNA) LINC00473 has been reported as potentially critical regulators in various types of cancer tumorigenesis. However, the effects of LINC00473 on glioma cells is unclear. The present study aimed to investigate the clinical significance, effects and mechanism of LINC00437 on glioma tumorigenesis. In the present study, LINC00473 was significantly increased in glioma tissues and in cell models, and predicted a poor prognosis in patients with glioma. Notably, LINC00473 knockdown not only suppressed cell proliferation, invasion and migration of glioma cells, but also blocked cell cycle progression and induced apoptosis. Subcutaneous xenotransplanted tumor model experiments revealed that reduced LINC00473 expression was able to suppress in vivo glioma growth. Mechanistically, LINC00473 functioned as a competing endogenous (ce)RNA to decrease microRNA (miR)­195­5p expression. Moreover, Yes­associated protein 1 (YAP1) and TEA domain family member 1 (TEAD1) were identified as downstream targets of miR­195­5p, whose expression levels were inhibited by miR­195­5p. LINC00473 knockdown suppressed glioma progression through the decrease of miR­195­5p and subsequent increase of YAP1 and TEAD1 expression levels. These results indicated LINC00473 might act as a ceRNA to sponge miR­195­5p, thus promoting YAP1 and TEAD1 expressions, and shedding light on the underlying mechanisms of LINC00473­induced glioma progression.