YWYansong Wang

Yansong Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yansong Wang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GTPLM-GO: Enhancing Protein Function Prediction Through Dual-Branch Graph Transformer and Protein Language Model Fusing Sequence and Local–Global PPI Information

    by Haotian Zhang, Yundong Sun, Yansong Wang, Xiaoling Luo, Yumeng Liu, Bin Chen, Xiaopeng Jin, Dongjie Zhu

    Currently, protein–protein interaction (PPI) networks have become an essential data source for protein function prediction. However, methods utilizing graph neural networks (GNNs) face significant challenges in modeling PPI networks. A primary issue is over-smoothing, which occurs when multiple GNN layers are stacked to capture global information. This architectural limitation inherently impairs the integration of local and global information within PPI networks, thereby limiting the accuracy of protein function prediction. To effectively utilize information within PPI networks, we propose GTPLM-GO, a protein function prediction method based on a dual-branch Graph Transformer and protein language model. The dual-branch Graph Transformer achieves the collaborative modeling of local and global information in PPI networks through two branches: a graph neural network and a linear attention-based Transformer encoder. GTPLM-GO integrates local–global PPI information with the functional semantic encoding constructed by the protein language model, overcoming the issue of inadequate information extraction in existing methods. Experimental results demonstrate that GTPLM-GO outperforms advanced network-based and sequence-based methods on PPI network datasets of varying scales.


  • Spectrum-BERT: Pretraining of Deep Bidirectional Transformers for Spectral Classification of Chinese Liquors

    by Yansong Wang, Yundong Sun, Yansheng Fu, Dongjie Zhu, Zhaoshuo Tian

    Counterfeit Chinese liquor incidents in China have significantly disrupted market order and jeopardized the health of consumers. Currently, deep learning-based spectral detection techniques are extensively leveraged in non-invasive food inspection. Excessive reliance on labels severely limits its application in real scenarios. To make better use of limited samples, we are the first to use the “unsupervised pre-training & supervised fine-tuning” paradigm in combining the Transformer architecture for feature extraction and classification of the Chinese liquor spectrum, and propose Spectrum-BERT, which represents Bidirectional Encoder Representations from Transformers for Spectrum. Specifically, we creatively propose spectral curve partitioning and 1-D convolutional layer mapping to maintain the model’s sensitivity to characteristic peak locations and local information of spectral curves. Moreover, the paradigm of “unsupervised pre-training & supervised fine-tuning” addresses the limitation of label deficiency, thus improving the model’s applicability. Finally, we have conducted extensive experiments on the real liquor spectral dataset. Comparative experiments demonstrate that Spectrum-BERT outperforms all baselines on all metrics using only 70% supervised signal. The limit experimental results show that Spectrum-BERT can still maintain its lead using only the 10% supervised signal. Thanks to the more efficient model architecture, Spectrum-BERT’s model parameters and FLOPs are only 1/568 and 1/322 of those of baselines.


  • Open Access

    Surface modifications of titanium dental implants with strontium eucommia ulmoides to enhance osseointegration and suppress inflammation

    by Avery Rui Sun, Qili Sun, Yansong Wang, Liqiu Hu, Yutong Wu, Fenbo Ma, Jiayi Liu, Xiangchao Pang, Bin Tang

    Background: Titanium (Ti) is now widely used as implant material due to its excellent mechanical properties and superior biocompatibilities, while its inert bioactivities might lead to insufficient osseointegration, and limit its performance in dental applications. Methods: We introduced a robust and simple approach of modifying titanium surfaces with polysaccharide complexes. Titanium samples were subjected to hydrothermal treatment to create a uniform porous structure on the surface, followed by coating with a bioinspired and self-assembly polydopamine layer. Strontium Eucommia Ulmoides Polysaccharide (EUP-Sr) complexes are then introduced to the polydopamine-coated porous titanium. Multiple morphological and physiochemical characterizations are employed for material evaluation, while cell proliferation and gene expression tests using macrophages, primary alveolar bone osteoblasts, and vascular endothelial cells are used to provide an overall insight into the functions of the product. The significances of statistical differences were analyzed using student’s t-test. Results: Microscopic and spectrometric characterizations confirmed that the Ti surface formed a porous structure with an adequate amount of EUP-Sr loading. The attachment was attributed to hydrogen bonding between the ubiquitous glycosidic linkage of the polysaccharide complex and the ring structure of polydopamine, yet the loaded EUP-Sr complex can be gradually released, consequently benefiting the neighboring microenvironment. Cell experiments showed no cytotoxicity of the material, and the product showed promising anti-inflammation, osseointegration, and angiogenesis properties, which were further confirmed by in vivo evaluations. Conclusion: We believe the EUP-Sr modified titanium implant is a promising candidate to be used in dental applications with notable osteoimmunomodulation and angiogenesis functions. And the novel technique proposed in this study would benefit the modification of metal/inorganic surfaces with polysaccharides for future research.


  • An Information Identification Method for Venture Firms Based on Frequent Itemset Discovery

    by Ning Cao, Yansong Wang, Xiaoyu Chen, Yulan Zhou, Mingrui Wu, Xiaofang Li, Jianrui Ding, Dongjie Zhu

  • Open Access

    Study on broadband low-frequency sound insulation of multi-channel resonator acoustic metamaterials

    by Chi Xu, Hui Guo, Yinghang Chen, Xiaori Dong, Hongling Ye, Yansong Wang

    A novel acoustic metamaterial structure, made up of both resonator and multiple channels, is proposed to insulate low-frequency broadband noises. Three bandgaps with a total width of 658 Hz can be obtained below 900 Hz when the structure appears as a single negative characteristic within specific frequency ranges. These bandgaps are caused by the standing-wave characteristics under the coupling action of the interior and exterior cavities and the multiple channels. By changing structural parameters and materials, the low-frequency broadband sound insulation performance of the structure can be improved. Experimental results further prove the sound insulation characteristics. The results obtained herein can be used as a guide toward achieving low-frequency broadband sound insulation using a lightweight structure.


  • Open Access

    Research on the Key Techniques of TCP Protocol Normalization for Mimic Defense Architecture

    by Mingxing Zhu, Yansong Wang, Ruyun Zhang, Tianning Zhang, Heyuan Li, Hanguang Luo, Shunbin Li

    The Mimic Defense (MD) is an endogenous security technology with the core technique of Dynamic Heterogeneous Redundancy (DHR) architecture. It can effectively resist unknown vulnerabilities, backdoors, and other security threats by schedule strategy, negative feedback control, and other mechanisms. To solve the problem that Cyber Mimic Defense devices difficulty of supporting the TCP protocol. This paper proposes a TCP protocol normalization scheme for DHR architecture. Theoretical analysis and experimental results show that this scheme can realize the support of DHR-based network devices to TCP protocol without affecting the security of mimicry defense architecture.


  • Fixture layout design based on two-stage method for sheet metal components

    by Yanfeng Xing, Yansong Wang

    The optimal fixture scheme can effectively reduce the deformation of sheet metal parts in the normal direction of their main plane. The fixture layout design requires a great deal of finite element analysis, which limits efficiency and quality of fixture design. This article proposes a two-stage method to decrease the number of finite element analyses for fixture layout design. First, three locating points are generated by using particle swarm optimization based on the rigid model. Second, the other points are optimized by establishing a response surface modeling based on radial basis function. Finally, through the case of rear bracket plate, this work elaborates two-stage fixture locating scheme design process. The results show that the two-stage method has good simulation effect and higher prediction accuracy.