Explore the vast range of titles available.

Identifying compound-protein (drug-target, DTI) interactions (CPI) accurately is a key step in drug discovery. Including virtual screening and drug reuse, it can significantly reduce the time it takes to identify drug candidates and provide patients with timely and effective treatment. Recently, more and more researchers have developed CPI’s deep learning model, including feature representation of a 2D molecular graph of a compound using a graph convolutional neural network, but this method loses much important information about the compound. In this paper, we propose a novel three-channel deep learning framework, named SSGraphCPI, for CPI prediction, which is composed of recurrent neural networks with an attentional mechanism and graph convolutional neural network. In our model, the characteristics of compounds are extracted from 1D SMILES string and 2D molecular graph. Using both the 1D SMILES string sequence and the 2D molecular graph can provide both sequential and structural features for CPI predictions. Additionally, we select the 1D CNN module to learn the hidden data patterns in the sequence to mine deeper information. Our model is much more suitable for collecting more effective information of compounds. Experimental results show that our method achieves significant performances with RMSE (Root Mean Square Error) = 2.24 and R2 (degree of linear fitting of the model) = 0.039 on the GPCR (G Protein-Coupled Receptors) dataset, and with RMSE = 2.64 and R2 = 0.018 on the GPCR dataset RMSE, which preforms better than some classical deep learning models, including RNN/GCNN-CNN, GCNNet and GATNet.

Doxorubicin (DOX) is a highly effective antineoplastic anthracycline drug; however, the adverse effect of the cardiotoxicity has limited its widespread application. Fibroblast growth factor 21 (FGF21), as a well-known regulator of glucose and lipid metabolism, was recently shown to exert cardioprotective effects. The aim of this study was to investigate the possible protective effects of FGF21 against DOX-induced cardiomyopathy. We preliminarily established DOX-induced cardiotoxicity models in H9c2 cells, adult mouse cardiomyocytes, and 129S1/SyImJ mice, which clearly showed cardiac dysfunction and myocardial collagen accumulation accompanying by inflammatory, oxidative stress, and apoptotic damage. Treatment with FGF21 obviously attenuated the DOX-induced cardiac dysfunction and pathological changes. Its effective anti-inflammatory activity was revealed by downregulation of inflammatory factors (tumor necrosis factor -α and interleukin-6) via the IKK/I κ B α /nuclear factor- κ B pathway. The anti-oxidative stress activity of FGF21 was achieved via reduced generation of reactive oxygen species through regulation of nuclear transcription factor erythroid 2-related factor 2 transcription. Its anti-apoptotic activity was shown by reductions in the number of TUNEL-positive cells and DNA fragments along with a decreased ratio of Bax/Bcl-2 expression. In a further mechanistic study, FGF21 enhanced sirtuin 1 (SIRT1) binding to liver kinase B1 (LKB1) and then decreased LKB1 acetylation, subsequently inducing AMP-activated protein kinase (AMPK) activation, which improved the cardiac inflammation, oxidative stress, and apoptosis. These alterations were significantly prohibited by SIRT1 RNAi. The present work demonstrates for the first time that FGF21 obviously prevented DOX-induced cardiotoxicity via the suppression of oxidative stress, inflammation, and apoptosis through the SIRT1/LKB1/AMPK signaling pathway.

Lung cancer is one of the most harmful malignant tumors to human health. The accurate judgment of the pathological type of lung cancer is vital for treatment. Traditionally, the pathological type of lung cancer requires a histopathological examination to determine, which is invasive and time consuming. In this work, a novel residual neural network is proposed to identify the pathological type of lung cancer via CT images. Due to the low amount of CT images in practice, we explored a medical-to-medical transfer learning strategy. Specifically, a residual neural network is pre-trained on public medical images dataset luna16, and then fine-tuned on our intellectual property lung cancer dataset collected in Shandong Provincial Hospital. Data experiments show that our method achieves 85.71% accuracy in identifying pathological types of lung cancer from CT images and outperforming other models trained with 2054 labels. Our method performs better than AlexNet, VGG16 and DenseNet, which provides an efficient, non-invasive detection tool for pathological diagnosis.

The response of terrestrial water storages to dryland vegetation growth remains poorly understood. Using multiple proxies from satellite observations and model outputs, we show an overall increase (decrease) in vegetation growth (terrestrial water storages) across drylands globally during 1982–2016. Terrestrial water storages in greening drylands correlate negatively with vegetation growth, particularly for cropland-dominated regions, and such response is pronounced when the growth rate of vegetation productivity is high. Reduction in terrestrial water storage is dominated by precipitation and evapotranspiration variability rather by than runoff. We predict reduction in terrestrial water storage of 41–84% by 2100, accompanying expansion of drylands by 4.1–10.6%. Our findings, which indicate sustained adverse response of terrestrial water storage to vegetation growth in drylands, highlight the need for concerted planning for balanced ecological restoration, agricultural management, and water resource utilization that will affect 5.17 billion people, 64% of whom live in developing countries.

Motivation Accurate identification of Drug-Target Interactions (DTIs) plays a crucial role in many stages of drug development and drug repurposing. (i) Traditional methods do not consider the use of multi-source data and do not consider the complex relationship between data sources. (ii) How to better mine the hidden features of drug and target space from high-dimensional data, and better solve the accuracy and robustness of the model. Results To solve the above problems, a novel prediction model named VGAEDTI is proposed in this paper. We constructed a heterogeneous network with multiple sources of information using multiple types of drug and target dataIn order to obtain deeper features of drugs and targets, we use two different autoencoders. One is variational graph autoencoder (VGAE) which is used to infer feature representations from drug and target spaces. The second is graph autoencoder (GAE) propagating labels between known DTIs. Experimental results on two public datasets show that the prediction accuracy of VGAEDTI is better than that of six DTIs prediction methods. These results indicate that model can predict new DTIs and provide an effective tool for accelerating drug development and repurposing.

Diabetic cardiomyopathy as an important threat to health occurs with or without coexistence of vascular diseases. The exact mechanisms underlying the disease remain incompletely clear. Although several pathological mechanisms responsible for diabetic cardiomyopathy have been proposed, oxidative stress is widely considered as one of the major causes for the pathogenesis of the disease. Hyperglycemia‐, hyperlipidemia‐, hypertension‐ and inflammation‐induced oxidative stress are major risk factors for the development of microvascular pathogenesis in the diabetic myocardium, which results in abnormal gene expression, altered signal transduction and the activation of pathways leading to programmed myocardial cell deaths. In the present article, we aim to provide an extensive review of the role of oxidative stress and anti‐oxidants in diabetic cardiomyopathy based on our own works and literature information available. Although several pathological mechanisms responsible for diabetic cardiomyopathy have been proposed, oxidative stress is widely considered as one of the major causes for the pathogenesis of the disease. Hyperglycemia‐, hyperlipidelima‐, hypertension‐, and inflammation‐induced oxidative stress is a major risk factor for the development of micro‐vascular pathogenesis in the diabetic myocardium, which results in abnormal gene expression, altered signal transduction, and the activation of pathways leading to programmed myocardial cell deaths.

Rupture of intracranial aneurysm is the first cause of subarachnoid hemorrhage, second only to cerebral thrombosis and hypertensive cerebral hemorrhage, and the mortality rate is very high. MRI technology plays an irreplaceable role in the early detection and diagnosis of intracranial aneurysms and supports evaluating the size and structure of aneurysms. The increase in many aneurysm images, may be a massive workload for the doctors, which is likely to produce a wrong diagnosis. Therefore, we proposed a simple and effective comprehensive residual attention network (CRANet) to improve the accuracy of aneurysm detection, using a residual network to extract the features of an aneurysm. Many experiments have shown that the proposed CRANet model could detect aneurysms effectively. In addition, on the test set, the accuracy and recall rates reached 97.81% and 94%, which significantly improved the detection rate of aneurysms.

Electron-phonon (e-ph) interaction in monolayer Janus MoSSe has been investigated using ab initio approach. We find that the asymmetric structure induced net dipole moment in MoSSe introduce an enhanced e-ph interaction compared to the symmetric MoS2. Through the mode resolved scattering analysis, we demonstrate that the out-of-plane optical mode in MoSSe contributing to the total e-ph scattering rates are much more than MoS2. Around the band edges, the maximum mean free paths (MFPs) of both electrons and holes along zigzag (ZZ) direction are found to be 4 nm in MoSSe, while the MFPs along armchair directions are significantly shorter than along ZZ direction, meaning the highly anisotropic transport properties in MoSSe.

Medical image segmentation is crucial for the diagnosis and analysis of disease. Deep convolutional neural network methods have achieved great success in medical image segmentation. However, they are highly susceptible to noise interference during the propagation of the network, where weak noise can dramatically alter the network output. As the network deepens, it can face problems such as gradient explosion and vanishing. To improve the robustness and segmentation performance of the network, we propose a wavelet residual attention network (WRANet) for medical image segmentation. We replace the standard downsampling modules (e.g., maximum pooling and average pooling) in CNNs with discrete wavelet transform, decompose the features into low- and high-frequency components, and remove the high-frequency components to eliminate noise. At the same time, the problem of feature loss can be effectively addressed by introducing an attention mechanism. The combined experimental results show that our method can effectively perform aneurysm segmentation, achieving a Dice score of 78.99%, an IoU score of 68.96%, a precision of 85.21%, and a sensitivity score of 80.98%. In polyp segmentation, a Dice score of 88.89%, an IoU score of 81.74%, a precision rate of 91.32%, and a sensitivity score of 91.07% were achieved. Furthermore, our comparison with state-of-the-art techniques demonstrates the competitiveness of the WRANet network.

Stacking sequence of bilayer van der Waals transition metal dichalcogenides determines their electronic and related optical excitations. When the Janus monolayer structure has been taken to construct bilayer TMDs, it would introduce another degree of freedom, the out-of-plane intrinsic dipole moment, to tune the electronic and optical properties. Here we reveal that the electronic band structures and interlayer excitons can be dramatically tuned via the stacking sequence of the bilayer MoSSe with the different intrinsic dipole orientations. Moreover, the lowest energy interlayer excitons exhibit diverse spatial extensions, and the corresponding radiative lifetimes can be tailored within the range of ∼10 −8 to ∼10 −2 seconds at room temperature, by means of optimizing the dipole orientation and stacking sequence, and when the dipole moment keeps the same orientation for the constituent layer, it will slower the radiative recombination. Our findings shed a light on the applications of the interlayer excitons in Janus MoSSe on optoelectronics.