检索结果-南通市图书馆

An Encoding-Decoding Framework Based on CNN for circ RNA-RBP Binding Sites Prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 256-263页

作者： Yajing GUO Xiujuan lei Yi pan School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Department of Computer Science Georgia State University

Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.

关键词： Circular RNAs (circRNAs) RNA binding proteins Convolutional neural network Temporal convolutional network Encoder-decoder network

Molecular Generation and Optimization of Molecular Properties Using a Transformer Model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 142-155页

作者： Zhongyin Xu Xiujuan lei Mei Ma Yi pan School of Computer Science Shaanxi Normal UniversityXi'an 710119China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Generating novel molecules to satisfy specific properties is a challenging task in modern drug discovery,which requires the optimization of a specific objective based on satisfying chemical rules.Herein,we aim to optimize the properties of a specific molecule to satisfy the specific properties of the generated molecule.The Matched Molecular Pairs(MMPs),which contain the source and target molecules,are used herein,and logD and solubility are selected as the optimization properties.The main innovative work lies in the calculation related to a specific transformer from the perspective of a matrix dimension.Threshold intervals and state changes are then used to encode logD and solubility for subsequent tests.During the experiments,we screen the data based on the proportion of heavy atoms to all atoms in the groups and select 12365,1503,and 1570 MMPs as the training,validation,and test sets,respectively.Transformer models are compared with the baseline models with respect to their abilities to generate molecules with specific properties.Results show that the transformer model can accurately optimize the source molecules to satisfy specific properties.

关键词： molecular optimization transformer Matched Molecular Pairs(MMPs) logD solubility

Shear band evolution and acoustic emission characteristics of sandstone containing non-persistent flaws

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical Engineering 2024年第2期16卷 497-513页

作者： Shuting Miao Peng-Zhi pan Chuanqing Zhang lei Huo State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil MechanicsChinese Academy of SciencesWuhan430071China University of Chinese Academy of Sciences Beijing100049China CASIC Research Institute of Intelligent Decision Engineering Wuhan430040China

Direct shear tests were conducted on sandstone specimens under different constant normal stresses to study the coalescence of cracks between non-persistent flaws and the shear sliding characteristics of the shear-formed fault.Digital image correlation and acoustic emission(AE)techniques were used to monitor the evolution of shear bands at the rock bridge area and microcracking behaviors.The experimental results revealed that the shear stresses corresponding to the peak and sub-peak in the stressdisplacement curve are significantly affected by the normal stress.Strain localization bands emerged at both the tip of joints and the rock bridge,and their extension and interaction near the peak stress caused a surge in the AE hit rate and a significant decrease in the AE b value.Short and curvilinear strain bands were detected at low normal stress,while high normal stress generally led to more microcracking events and longer coplanar cracks at the rock bridge area.Furthermore,an increase in normal stress resulted in a higher AE count rate and more energetic AE events during friction sliding along the shearformed fault.It was observed that the elastic energy released during the crack coalescence at the prepeak stage was much greater than that released during friction sliding at the post-peak stage.More than 75%of AE events were located in the low-frequency band(0e100 kHz),and this proportion continued to rise with increasing normal stress.Moreover,more AE events of low AF value and high RA value were observed in specimens subjected to high normal stress,indicating that greater normal stress led to more microcracks of shear nature.

关键词： Shear band evolution Acoustic emission(AE) Crack coalescence Normal stress Shear sliding

Double-ring high-frequency common-mode switching oscillation current sensor for inverter-fed machine winding insulation monitoring

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Global Energy Interconnection 2024年第1期7卷 106-116页

作者： Lingqing pan Xizhou Du Xing lei Ting Ye Dawei Xiang Hao Li College of Electrical Power Engineering Shanghai University of Electric PowerShanghai 200090P.R.China State Grid Shanghai Municipal Electric Power Company Shanghai 200122P.R.China College of Electronics and Information Engineering Tongji UniversityShanghai 201804P.R.China

Insulation failure significantly contributes to the unpredictable shutdown of power equipment.Compared to the partial discharge and high-frequency(HF)injection methods,the HF common-mode(CM)leakage current method offers a non-intrusive and highly sensitive alternative.However,the detection of HF CM currents is susceptible to interference from differential-mode(DM)currents,which exhibit high-amplitude and multifrequency components during normal operation.To address this challenge,this paper proposes a double-ring current sensor based on the principle of magnetic shielding for inverter-fed machine winding insulation monitoring.The inner ring harnesses the magnetic aggregation effect to isolate the DM current magnetic field,whereas the outer ring serves as the magnetic core of the Rogowski current sensor,enabling HF CM current monitoring.First,the magnetic field distributions of the CM and DM currents were analyzed.Then,a correlation between the sensor parameters and signal-to-noise ratio of the target HF CM current was established.Finally,an experimental study was conducted on a 3-kW PMSM for verification.The results indicate that the proposed double-ring HF CM sensor can effectively mitigate DM current interference.Compared to a single-ring sensor,a reduction of approximately 40%in the DM component was achieved,which significantly enhanced the precision of online insulation monitoring.

关键词： Magnetic shielding Double-ring Common-mode current Maxwell simulation

维普期刊数据库

Drug-Target Interactions Prediction Based on Signed Heterogeneous Graph Neural Networks

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 231-244页

作者： Ming CHEN Yajian JIANG Xiujuan lei Yi pan Chunyan JI Wei JIANG College of Information Science and Engineering Hunan Normal University School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Computer Science Department BNU-HKBU United International College

Drug-target interactions(DTIs) prediction plays an important role in the process of drug discovery.Most computational methods treat it as a binary prediction problem, determining whether there are connections between drugs and targets while ignoring relational types information. Considering the positive or negative effects of DTIs will facilitate the study on comprehensive mechanisms of multiple drugs on a common target, in this work, we model DTIs on signed heterogeneous networks, through categorizing interaction patterns of DTIs and additionally extracting interactions within drug pairs and target protein pairs. We propose signed heterogeneous graph neural networks(SHGNNs), further put forward an end-to-end framework for signed DTIs prediction, called SHGNN-DTI,which not only adapts to signed bipartite networks, but also could naturally incorporate auxiliary information from drug-drug interactions(DDIs) and protein-protein interactions(PPIs). For the framework, we solve the message passing and aggregation problem on signed DTI networks, and consider different training modes on the whole networks consisting of DTIs, DDIs and PPIs. Experiments are conducted on two datasets extracted from Drug Bank and related databases, under different settings of initial inputs, embedding dimensions and training modes. The prediction results show excellent performance in terms of metric indicators, and the feasibility is further verified by the case study with two drugs on breast cancer.

关键词： Drug-target interactions Signed heterogeneous network Link sign prediction Graph neural networks

Rapid surface texturing to achieve robust superhydrophobicity,controllable droplet impact,and anti-frosting performances

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Friction 2024年第2期12卷 291-304页

作者： Qingwen DAI lei CHEN Jiabao pan Liping SHI Dameng LIU Wei HUANG Xiaolei WANG College of Mechanical and Electrical Engineering Nanjing University of Aeronautics&AstronauticsNanjing 210016China State Key Laboratory of Tribology in Advanced Equipment Department of Mechanical EngineeringTsinghua UniversityBeijing 100084China School of Mechanical Engineering Anhui Polytechnic UniversityWuhu 241000China School of Mechanical Engineering Anhui University of TechnologyMa’anshan 243032China

Robust superhydrophobic surfaces with excellent capacities of repelling water and anti-frosting are of importance for many mechanical components.In this work,wear-resistant superhydrophobic surfaces were fabricated by curing a mixture of polyurethane acrylate(PUA)coating and 1H,1H,2H,2H-Perfluorodecyltrichlorosilane(HFTCS)on titanium alloy(TC4)surfaces decorated with micropillars pattern,thus,composite functional surfaces with PUA coating in the valleys around the micropillars pattern of TC4 were achieved.Apparent contact angle on fabricated surfaces could reach 167°.Influences of the geometric parameters of micropillars pattern on the apparent contact angle were investigated,and the corresponding wear-resistant property was compared.Droplet impact and anti-frosting performances on the prepared surfaces were highlighted.An optimized design of surface texture with robust superhydrophobicity,controllable droplet impact,and anti-frosting performances was proposed.This design principle is of promising prospects for fabricating superhydrophobic surfaces in traditional mechanical systems.

关键词： surface texture robust superhydrophobic wear-resistant droplet impact anti-frosting

In situ atomic-scale tracking of unusual interface reaction circulation and phase reversibility in(de)potassiated alloy-typed anode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第8期95卷 241-249页

作者： Lin Su Ruining Fu Shuangying lei Yuchen pan Chongyang Zhu Pengcheng Liu Feng Xu SEU-FEI Nano-Pico Center Key Laboratory of MEMS of the Ministry of Education Southeast University

Alloy-typed anode materials,endowed innately with high theoretical specific capacity,hold great promise as an alternative to intercalation-typed counterparts for alkali-ion batteries.Despite tremendous efforts devoted to addressing drastic volume change and severe pulverization issues of such anodes,the underlying mechanisms involving dynamic phase evolutions and reaction kinetics have not yet been fully comprehended.Herein,taking antimony（Sb） anode as a representative paradigm,its microscopic operating mechanisms down to the atomic scale during live（de）potassiation cycling are systematically unraveled using in situ transmission electron microscopy.Highly reversible phase transformations at single-particle level,that are Sb■KSb2■KSb■K5Sb4■K3Sb,were revealed during cycling.Meanwhile,multiple phase interfaces associated with different reaction kinetics coexisted and this phenomenon was properly elucidated in the context of density functional theory calculations.Impressively,previously unexplored unidirectional circulation of reaction interfaces within individual Sb particle is confirmed for both potassiation and depotassiation.Based on the empirical results,the surface diffusion-mediated potassiation-depotassiation pathways at single-particle level are suggested.This work affords new insights into energy storage mechanisms of Sb anode and valuable guidance for targeted optimization of alloy-typed anodes（not limited to Sb） toward advanced potassium-ion batteries.

关键词： Alloy-typed anode In situ transmission electron microscopy Potassium storage mechanism Reaction interface

Bioinspired Closed-loop CPG-based Control of a Robotic Manta for Autonomous Swimming

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第1期21卷 177-191页

作者： Yiwei Hao Yonghui Cao Yingzhuo Cao Xiong Mo Qiaogao Huang lei Gong Guang pan Yong Cao School of Marine Science and Technology Northwestern Polytechnical UniversityXi'an 710072China Unmanned Vehicle Innovation Center Ningbo Institute of NPUNingbo 315103China Key Laboratory of Unmanned Underwater Vehicle Technology of Ministry of Industry and Information Technology Xi'an 710072China

Fish in nature exhibit a variety of swimming modes such as forward swimming,backward swimming,turning,pitching,etc.,enabling them to swim in complex scenes such as coral reefs.It is still difficult for a robotic fish to swim autonomously in a confined area as a real fish.Here,we develop an untethered robotic manta as an experimental platform,which consists of two flexible pectoral fins and a tail fin,with three infrared sensors installed on the front,left,and right sides of the head to sense the surrounding obstacles.To generate multiple swimming modes of the robotic manta and online switching of different modes,we design a closed-loop Central Pattern Generator(CPG)controller based on distance information and use a combination of phase difference and amplitude of the CPG model to achieve stable and rapid adjustment of yaw angle.To verify the autonomous swimming ability of the robotic manta in complex scenes,we design an experimental scenario with a concave obstacle.The experimental results show that the robotic manta can achieve forward swimming,backward swimming,in situ turning within the concave obstacle,and finally exit from the area safely while relying on the perception of external obstacles,which can provide insight into the autonomous exploration of complex scenes by the biomimetic robotic fish.Finally,the swimming ability of the robotic manta is verified by field tests.

关键词： Biomimetic robotic manta Central Pattern Generator Closed-loop control Backward swimming

Development and evaluation of an online monitoring single-particle optical particle counter with polarization detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第4期138卷 585-596页

作者： Weijie Yao Xiaole pan Yu Tian Hang Liu Yuting Zhang Shandong lei Junbo Zhang Yinzhou Zhang LinWu Yele Sun Zifa Wang State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China College of Earth and Planetary Sciences University of Chinese Academy of SciencesBeijing 100049China Center for Excellence in Regional Atmospheric Environment Institute of Urban EnvironmentChinese Academy of SciencesXiamen 361021China

We developed a single-particle optical particle counter with polarization detection(SOPC)for the real-time measurement of the optical size and depolarization ratio(defined as the ratio of the vertical component to the parallel component of backward scattering)of atmospheric particles,the polarization ratio(DR)value can reflect the irregularity of the particles.The SOPC can detect aerosol particles with size larger than 500 nm and the maximum particle count rate reaches~1.8×10^(5)particles per liter.The SOPC uses a modulated polarization laser to measure the optical size of particles according to forward scattering signal and the DR value of the particles by backward S and P signal components.The sampling rate of the SOPC was 106#/(sec·channel),and all the raw data were processed online.The calibration curve was obtained by polystyrene latex spheres with sizes of 0.5-10μm,and the average relative deviation of measurement was 3.96% for sub 3μm particles.T-matrix method calculations showed that the DR value of backscatter light at 120°could describe the variations in the aspect ratio of particles in the above size range.We performed insitu observations for the evaluation of the SOPC,the mass concentration constructed by the SOPC showed good agreement with the PM_(2.5)measurements in a nearby state-controlled monitoring site.This instrument could provide useful data for source appointment and regulations against air pollution.

关键词： Instrument development Single particle detection Measurement uncertainty Optical simulation Mass concentration

维普期刊数据库