Wenfeng Zheng¹, Guangyu Xu², Siyu Lu³, Junmin Lyu⁴, Feng Bao^5,*, Lirong Yin^6,*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.075741 - 29 January 2026

Abstract Graph Neural Networks (GNNs), as a deep learning framework specifically designed for graph-structured data, have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis. However, current reviews on GNN models are mainly focused on smaller domains, and there is a lack of systematic reviews on the classification and applications of GNN models. This review systematically synthesizes the three canonical branches of GNN, Graph Convolutional Network (GCN), Graph Attention Network (GAT), and Graph Sampling Aggregation Network (GraphSAGE), and analyzes their integration pathways More >

Sicong Zheng^#, Jingjing Song^#, Cheng Luo, Xin Li, Qiqi Ma, Beibei Jiang^*, Qinglin Liu, Yuanzhi Pan

Phyton-International Journal of Experimental Botany, Vol.91, No.3, pp. 525-539, 2022, DOI:10.32604/phyton.2022.017629 - 26 October 2021

Abstract Studying the genetic basis and regulatory mechanism of chrysanthemum lateral bud outgrowth is of great significance for reduction the production cost of cut chrysanthemum. To clarify the molecular basis of lateral bud elongation after removal of apical dominance in chrysanthemum, label-free quantification analysis was used to analyze the proteome changes after apical bud removal. Quantitative real-time PCR (qPCR) was used to analyze the changes in the expression of three plant hormone-related genes. A total of 440 differentially expressed proteins were successfully identified at three time points during the lateral bud elongation. The number of differentially… More >

Liaquat Ali Lund^1,2,*, Zurni Omar¹, Ilyas Khan³, El-Sayed M. Sherif^4,5

CMC-Computers, Materials & Continua, Vol.66, No.1, pp. 127-139, 2021, DOI:10.32604/cmc.2020.013120 - 30 October 2020

Abstract In this study, magnetohydrodynamic (MHD) three-dimensional (3D) flow of alumina (Al₂O₃) and copper (Cu) nanoparticles of an electrically conducting incompressible fluid in a rotating frame has been investigated. The shrinking surface generates the flow that also has been examined. The single-phase (i.e., Tiwari and Das) model is implemented for the hybrid nanofluid transport phenomena. Results for alumina and copper nanomaterials in the water base fluid are achieved. Boundary layer approximations are used to reduce governing partial differential (PDEs) system into the system of the ordinary differential equations (ODEs). The three-stage Lobatto IIIa method in bvp4c solver is More >

Aike Qiao^1,*, Honghui Zhang¹, Jun Xia¹

Molecular & Cellular Biomechanics, Vol.16, Suppl.1, pp. 35-35, 2019, DOI:10.32604/mcb.2019.05715

Abstract In order to improve the calculation accuracy of computed tomography angiography-derived fractional flow reserve (FFR_CT), a mathematical model for setting the patient-specific flow boundary condition was proposed, in which some independent physiological parameters, such as myocardial mass, diastolic blood pressure, heart rate and vessel volume were considered. This model was employed to simulate hemodynamics in sixteen patients with coronary stenosis. The results of FFR_CT demonstrated good consistency with invasively measured FFR. The diagnostic accuracy of FFR_CT was 85%. The proposed model offers a new approach to improve the accuracy of FFR_CT, as well as promotes the clinical More >