Multi-Kernel Graph Attention Deep Autoencoder for MiRNA-Disease Association Prediction.

Accumulating evidence indicates that microRNAs (miRNAs) can control and coordinate various biological processes. Consequently, abnormal expressions of miRNAs have been linked to various complex diseases. Recognizable proof of miRNA-disease associations (MDAs) will contribute to the diagnosis and treatment of human diseases. Nevertheless, traditional experimental verification of MDAs is laborious and limited to small-scale. Therefore, it is necessary to develop reliable and effective computational methods to predict novel MDAs. In this work, a multi-kernel graph attention deep autoencoder (MGADAE) method is proposed to predict potential MDAs. In detail, MGADAE first employs the multiple kernel learning (MKL) algorithm to construct an integrated miRNA similarity and disease similarity, providing more biological information for further feature learning. Second, MGADAE combines the known MDAs, disease similarity, and miRNA similarity into a heterogeneous network, then learns the representations of miRNAs and diseases through graph convolution operation. After that, an attention mechanism is introduced into MGADAE to integrate the representations from multiple graph convolutional network (GCN) layers. Lastly, the integrated representations of miRNAs and diseases are input into the bilinear decoder to obtain the final predicted association scores. Corresponding experiments prove that the proposed method outperforms existing advanced approaches in MDA prediction. Furthermore, case studies related to two human cancers provide further confirmation of the reliability of MGADAE in practice.

A new framework for drug-disease association prediction combing light-gated message passing neural network and gated fusion mechanism.

With the development of research on the complex aetiology of many diseases, computational drug repositioning methodology has proven to be a shortcut to costly and inefficient traditional methods. Therefore, developing more promising computational methods is indispensable for finding new candidate diseases to treat with existing drugs. In this paper, a model integrating a new variant of message passing neural network and a novel-gated fusion mechanism called GLGMPNN is proposed for drug-disease association prediction. First, a light-gated message passing neural network (LGMPNN), including message passing, aggregation and updating, is proposed to separately extract multiple pieces of information from the similarity networks and the association network. Then, a gated fusion mechanism consisting of a forget gate and an output gate is applied to integrate the multiple pieces of information to extent. The forget gate calculated by the multiple embeddings is built to integrate the association information into the similarity information. Furthermore, the final node representations are controlled by the output gate, which fuses the topology information of the networks and the initial similarity information. Finally, a bilinear decoder is adopted to reconstruct an adjacency matrix for drug-disease associations. Evaluated by 10-fold cross-validations, GLGMPNN achieves excellent performance compared with the current models. The following studies show that our model can effectively discover novel drug-disease associations.

Cardiac Complications in 38 Cases of Kawasaki Disease with Coronary Artery Aneurysm Diagnosed by Echocardiography.

BACKGROUND: The long-term prognosis of patients with Kawasaki disease (KD) complicated by coronary artery aneurysm (CAA) is unclear. The aim of this study was to evaluate the complications of KD with CAAs. METHOD: We retrospectively analyzed the clinical data and complications of 38 KD patients with CAAs who were treated and underwent regular follow-up with echocardiography between January 1989 and May 2013. RESULTS: During a period of 29 days to 19 years after disease onset, complications seen included coronary stenosis and occlusion (six patients), thrombosis (17 patients), myocardial infarction (six patients), and calcification of CAAs (seven patients). Rupture of giant CAAs occurred in two patients and caused sudden death in one of these patients at 29 days and in the other patient at 5 months after disease onset. A total of seven deaths occurred, with five deaths caused by myocardial infarction. Three of these had undiagnosed incomplete KD or had not received regular treatment, while two experienced sudden death after several asymptomatic myocardial infarctions. CONCLUSION: Cardiac complications of KD with CAAs include thrombosis, coronary stenosis, myocardial infarction, sudden death, and calcification. Although rare, rupture of giant CAAs is fatal and might occur earlier after the onset of disease. Mortality occurred primarily in the earlier cases when anticoagulant therapy was insufficient and in patients who did not receive regular treatment. Echocardiography can provide reliable information for assessing the progression and prognosis of this condition.

Synthesis and biological evaluation of a series of 6,7-dimethoxy-1-(3,4-dimethoxybenzyl)-2-substituted tetrahydroisoquinoline derivatives.

Multidrug resistance in cancer is a major cause of failure in cancer chemotherapy. In search of new compounds with strong reversal activity and simple molecular structure, we have synthesized a series of compounds in which different substituents were linked to the 2-position of the 6,7-dimethoxy-1-(3,4-dimethoxybenzyl)- tetrahydroisoquinoline system. Compounds were analyzed for their cytotoxicity by MTT in K562 cell line in vitro, all of the derivatives exhibited little cytotoxic activity. In the meantime, these compounds were evaluated by MTT in K562/A02 cell line in vitro, 6e, 6h and 7c exhibited similar or more potent activities than verapamil with the IC50 values at 0.66, 0.65 and 0.96µM, and with the ratio factor of 24.13, 24.50 and 16.59, respectively.