Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
11,761
result(s) for
"Feng, Yue"
Sort by:
DPDDI: a deep predictor for drug-drug interactions
Background
The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases.
Results
In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs.
Conclusion
We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.
Journal Article
Recent Advances in the Synthesis of Aromatic Azo Compounds
Aromatic azo compounds have -N=N- double bonds as well as a larger π electron conjugation system, which endows aromatic azo compounds with wide applications in the fields of functional materials. The properties of aromatic azo compounds are closely related to the substituents on their aromatic rings. However, traditional synthesis methods, such as the coupling of diazo salts, have a significant limitation with respect to the structural design of aromatic azo compounds. Therefore, many scientists have devoted their efforts to developing new synthetic methods. Moreover, recent advances in the synthesis of aromatic azo compounds have led to improvements in the design and preparation of light-response materials at the molecular level. This review summarizes the important synthetic progress of aromatic azo compounds in recent years, with an emphasis on the pioneering contribution of functional nanomaterials to the field.
Journal Article
Seismic Design of Structures by Sequential Quadratic Programming with Trust Region Strategy and Endurance Time Method
The optimal design of structures subjected to seismic loading poses significant challenges due to the presence of high nonlinearity and computational complexity. To address these challenges, this paper presents a novel methodology that combines Sequential Quadratic Programming with Trust-Region strategy (SQP-TR) and Endurance Time Method (ETM). SQP-TR is initially presented as a numerical optimization approach to address optimization problems by linearizing the constraints and approximating the objective function with Taylor expansion, as well as employing the filter method and trust region strategy to ensure convergence and feasibility. A five-story linear frame validates its effectiveness and demonstrates promising outcomes. ETM is successfully implemented as a seismic analysis approach to perform nonlinear time history analyses in order to capture the dynamic input feature of the seismic load and evaluate the nonlinear dynamic behaviors of structures. Its practical application is demonstrated by a nine-story structure with nonlinearity, which shows satisfactory results. Finally, the proposed methodology is applied to optimize a twelve-story three-Dimensional (3D) Reinforced Concrete (RC) nonlinear building under seismic load, and the results demonstrate that the method can accomplish optimal seismic design with high accuracy and efficiency.
Journal Article
Prediction of Drug-Drug Interaction Using an Attention-Based Graph Neural Network on Drug Molecular Graphs
The treatment of complex diseases by using multiple drugs has become popular. However, drug-drug interactions (DDI) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. Therefore, for polypharmacy safety it is crucial to identify DDIs and explore their underlying mechanisms. The detection of DDI in the wet lab is expensive and time-consuming, due to the need for experimental research over a large volume of drug combinations. Although many computational methods have been developed to predict DDIs, most of these are incapable of predicting potential DDIs between drugs within the DDI network and new drugs from outside the DDI network. In addition, they are not designed to explore the underlying mechanisms of DDIs and lack interpretative capacity. Thus, here we propose a novel method of GNN-DDI to predict potential DDIs by constructing a five-layer graph attention network to identify k-hops low-dimensional feature representations for each drug from its chemical molecular graph, concatenating all identified features of each drug pair, and inputting them into a MLP predictor to obtain the final DDI prediction score. The experimental results demonstrate that our GNN-DDI is suitable for each of two DDI predicting scenarios, namely the potential DDIs among known drugs in the DDI network and those between drugs within the DDI network and new drugs from outside DDI network. The case study indicates that our method can explore the specific drug substructures that lead to the potential DDIs, which helps to improve interpretability and discover the underlying interaction mechanisms of drug pairs.
Journal Article
Coherently coupled solitons, breathers and rogue waves for polarized optical waves in an isotropic medium
Under investigation in this paper is a coherently coupled nonlinear Schrödinger system which describes the propagation of polarized optical waves in an isotropic medium. By virtue of the Darboux transformation, some new solutions have been generated on the vanishing and non-vanishing backgrounds, including multi-solitons, bound solitons, one-breathers, bound breathers, two-breathers, first-order and higher-order rogue waves. Dynamic behaviors of those solitons, breathers and rogue waves have been discussed through graphic simulation.
Journal Article
Research on the Impact of Corporate Environmental, Social, and Corporate Governance Scores on Cash Dividend Distribution
In recent years, environment, society, and governance (ESG) related research has covered hot areas such as social responsibility, investment, and corporate governance. Cash dividend distribution, as an important way of returning to investors, reflects the fulfillment of corporate ESG responsibilities to a certain extent and promotes the sound development of enterprises. This paper explores the impact of ESG scores of A-share listed companies in the passenger car industry on cash dividend distribution from 2020 to 2023. Companies with cash dividends of 0 are excluded, and Huazheng ESG rating is used. Profitability, growth ability, cash holdings, management shareholding ratio and independent director ratio are used as control variables. Finally, 20 samples are obtained. The data comes from the CNRDS platform and corporate financial reports. Due to the small sample size, short time span, industry selection bias, incomplete data disclosure and other reasons, only the management shareholding ratio has a significant impact on the cash dividend distribution, and other variables are not significant.
Journal Article
The 3D Genome Browser: a web-based browser for visualizing 3D genome organization and long-range chromatin interactions
Here, we introduce the 3D Genome Browser,
http://3dgenome.org
, which allows users to conveniently explore both their own and over 300 publicly available chromatin interaction data of different types. We design a new binary data format for Hi-C data that reduces the file size by at least a magnitude and allows users to visualize chromatin interactions over millions of base pairs within seconds. Our browser provides multiple methods linking distal
cis
-regulatory elements with their potential target genes. Users can seamlessly integrate thousands of other omics data to gain a comprehensive view of both regulatory landscape and 3D genome structure.
Journal Article
Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus
Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.
Despite its popularity for measuring the spatial organization of mammalian genomes, the resolution of most Hi-C datasets is coarse due to sequencing cost. Here, Zhang et al. develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data.
Journal Article
Size-effect induced controllable Cu0-Cu+ sites for ampere-level nitrate electroreduction coupled with biomass upgrading
The synergistic Cu
0
-Cu
+
sites is regarded as the active species towards NH
3
synthesis from the nitrate electrochemical reduction reaction (NO
3
-
RR) process. However, the mechanistic understanding and the roles of Cu
0
and Cu
+
remain exclusive. The big obstacle is that it is challenging to effectively regulate the interfacial motifs of Cu
0
-Cu
+
sites. In this paper, we describe the tunable construction of Cu
0
-Cu
+
interfacial structure by modulating the size-effect of Cu
2
O nanocube electrocatalysts to NO
3
-
RR performance. We elucidate the formation mechanism of Cu
0
-Cu
+
motifs by correlating the macroscopic particle size with the microscopic coordinated structure properties, and identify the synergistic effect of Cu
0
-Cu
+
motifs on NO
3
-
RR. Based on the rational design of Cu
0
-Cu
+
interfacial electrocatalyst, we develop an efficient paired-electrolysis system to simultaneously achieve the efficient production of NH
3
and 2,5-furandicarboxylic acid at an industrially relevant current densities (2 A cm
−2
), while maintaining high Faradaic efficiencies, high yield rates, and long-term operational stability in a 100 cm
2
electrolyzers, indicating promising practical applications.
It is challenging to regulate the interfacial motifs of Cu
0
-Cu
+
sites to understand roles of Cu
0
and Cu
+
for nitrate electrochemical reduction reaction. Here, the authors report a tunable construction of Cu
0
-Cu
+
interfacial structure by modulating the size-effect of Cu
2
O electrocatalysts.
Journal Article