个人简介

博士毕业于日本东京大学（泰晤士世界大学排名第28位）工学系，教授，博士生导师。主持和参与科研项目11项，先后主持并完成黑龙江省自然科学基金面上项目、中国博士后基金面上项目、黑龙江省教育厅科学技术研究项目、哈尔滨市科技青年创新人才项目。目前正主持国家自然科学基金面上项目和地区科学基金项目，具有较充足的研究经费。在国内外重要期刊和会议共发表70余篇学术论文，以第1作者或通讯作者发表SCI收录论文50篇，包括中科院1区top期刊论文4篇，中科院2区top期刊论文20篇，中国计算机学会（CCF）的B类国际期刊论文14篇；论文引用总数为1400余次。在生物信息学领域重要国际期刊上发表了一系列高水平学术论文，涉及的期刊包括《Knowledge-based Systems》（1篇，中科院1区top期刊）、《Applied Soft Computing》（1篇，中科院1区top期刊）、《IEEE Journal of Biomedical and Health Informatics》（4篇，2022年度中科院1区top期刊）、《Briefings in Bioinformatics》（8篇，计算生物学领域1区期刊；CCF B类国际期刊；中科院2区top期刊）、《Bioinformatics》（3篇，CCF B类国际期刊）、《IEEE/ACM Transactions on Computational Biology and Bioinformatics》（3篇，CCF B类国际期刊）、《Journal of Chemical Information and Modeling》（4篇，中科院2区top期刊）、《Computers in Biology and Medicine》（3篇，计算生物学领域1区top期刊；中科院2区top期刊）、Computer Methods and Programs in Biomedicine（1篇，中科院2区top期刊）等，具有一定的学术影响力。此外，作为TCBB、BIB、JCIM等多个国际领域重要期刊的审稿人。

课题组的主要研究方向包括：人工智能信息处理与分析，机器学习和深度学习算法研究，复杂网络构建与分析，大语言模型构建，物理驱动的深度学习，图像处理和分析

欢迎硕士研究生、博士研究生及博士后来到我们的课题组，共赴科研之旅。我们在海南大学，期待与你相遇。

请有意向加入课题组的同学，添加我的微信（ZTG_Taylor）或Email到邮箱（zhangtg@hainanu.edu.cn）。

国外访学经历

2019.11-2022.12，东京大学（泰晤士世界大学排名第28位），日本，工学系，访问学者

科研项目

主持和参与科研项目11项，其中包括主持和完成黑龙江省自然科学基金项目、黑龙江省高校基础科研青年创新人才项目、哈尔滨市青年科技创新人才项目。目前作为项目负责人主持国家自然科基金项目和校级项目，具有较充足的科研经费。

发表论文

在国内外重要的期刊和会议上发表论文70余篇，以第1作者或通讯作者发表SCI收录论文50篇，包括中科院1区top期刊论文4篇，中科院2区top期刊论文20篇，中国计算机学会（CCF）的B类国际期刊论文14篇；论文引用总数为1400余次。详细论文列表，请参看我的google scholar。以下仅列出近几年的代表性论文：

2025年

(1) 通讯作者. A multi-scale neighbor topology guided transformer and Kolmogorov-Arnold network enhanced feature learning model for disease-related circRNA prediction. IEEE Journal of Biomedical and Health Informatics, 2025. (中科院2区top期刊，SCI影响因子: 6.8)

(2) 通讯作者. Multi-knowledge graph and multi-view entity feature learning for predicting drug-related side effects. Journal of Chemical Information and Modeling, 2025. (中科院2区top期刊，SCI影响因子: 5.7)

(3) 通讯作者. KNDM: a knowledge graph transformer and node category sensitive contrastive learning Model for Drug and Microbe Association Prediction. Journal of Chemical Information and Modeling, 2025. (中科院2区top期刊，SCI影响因子: 5.7)

(4) 通讯作者. Subgraph topology and dynamic graph topology enhanced graph learning and pairwise feature context relationship integration for predicting disease-related miRNAs. Journal of Chemical Information and Modeling, 2025. (中科院2区top期刊，SCI影响因子: 5.7)

(5) 通讯作者. Interactive multi-hypergraph inferring and channel-enhanced and attribute-enhanced learning for drug-related side effect prediction. Computers in Biology and Medicine, 2025. (中科院2区期刊，SCI影响因子: 7)

2024年

(6) 通讯作者. Gating-Enhanced Hierarchical Structure Learning in Hyperbolic Space and Multi-scale Neighbor Topology Learning in Euclidean Space for Prediction of Microbe-Drug Associations. Journal of Chemical Information and Modeling, 2024 (SCI收录，JCR 1区top期刊，影响因子: 7.9)

(7)通讯作者. Dynamic category-sensitive hypergraph inferring and homo-heterogeneous neighbor feature learning for drug-related microbe prediction. Bioinformatics, 2024, 40.9: btae562. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(8) 通讯作者. Mask-Guided Target Node Feature Learning and Dynamic Detailed Feature Enhancement for lncRNA-Disease Association Prediction. Journal of Chemical Information and Modeling, 64(16), 6662-6675, 2024. (SCI收录，JCR 1区top期刊，影响因子: 7.9)

(9) 通讯作者. Multi-view attribute learning and context relationship encoding enhanced segmentation of lung tumors from CT images. Computers in Biology and Medicine, 177, 108640, 2024. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 6.698)

(10) 通讯作者. Graph reasoning method enhanced by relational transformers and knowledge distillation for drug-related side effect prediction. Iscience, 27(6), 2024. (中科院2区top期刊，JCR 1区, SCI影响因子:8.1)

(11) 通讯作者. Meta-Path Semantic and Global-Local Representation Learning Enhanced Graph Convolutional Model for Disease-Related miRNA Prediction. IEEE Journal of Biomedical and Health Informatics, 2024. (SCI收录，中科院1区top期刊，影响因子: 5.772)

(12) 通讯作者. Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs. Journal of Chemical Information and Modeling, 64(8), 3569-3578, 2024. (SCI收录，JCR 1区top期刊，影响因子: 7.9)

(13) 通讯作者. Mutually enhanced multi-view information learning for segmentation of lung tumor in CT images. Physics in Medicine & Biology, 69(7), 075008, 2024. (中科院2区期刊，JCR 1区 , SCI影响因子: )

(14) 通讯作者. Complementary feature learning across multiple heterogeneous networks and multimodal attribute learning for predicting disease-related miRNAs. Iscience, 27(2), 2024. (中科院2区top期刊，JCR 1区, SCI影响因子:8.1)

(15)通讯作者. Multi-scale topology and position feature learning and relationship-aware graph reasoning for prediction of drug-related microbes. Bioinformatics, 40(2), btae025, 2024. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

2023年

(16) 第1作者. Topological structure and global features enhanced graph reasoning model for non-small cell lung cancer segmentation from CT. Physics in Medicine and Biology, 1-14, 2023. (中科院2区top期刊，工程技术领域top期刊, SCI影响因子: 4.174)

(17) 通讯作者. Multi-scale random walk driven adaptive graph neural network with dual-head neighboring node attention for CT segmentation. Applied Soft Computing, 1-11, 2023. (中科院2区期刊，计算机科学领域top期刊, SCI影响因子: 8.7)

(18) 通讯作者. Specific topology and topological connection sensitivity enhanced graph learning for lncRNA-disease association prediction. Computers in Biology and Medicine, 1-10, 2023. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 6.698)

2022年

(19) 通讯作者. Graph based multi-scale neighboring topology deep learning for kidney and tumor segmentation. Physics in Medicine & Biology, 67(22), 225018, 2022. (中科院2区期刊，JCR 1区 , SCI影响因子: 7.5)

(20) 通讯作者. Convolutional bi-directional learning and spatial enhanced attentions for lung tumor segmentation. Computer Methods and Programs in Biomedicine, 226, 107147, 2022. (中科院2区期刊, JCR 1区, SCI影响因子: 7.4)

(21)通讯作者. Learning global dependencies and multi-semantics within heterogeneous graph for predicting disease-related lncRNAs. Briefings in Bioinformatics, 23(5), bbac361, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(22) 通讯作者. Multi-type neighbors enhanced global topology and pairwise attribute learning for drug–protein interaction prediction. Briefings in bioinformatics, 23(5), bbac120, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(23) 通讯作者. Fully connected autoencoder and convolutional neural network with attention-based method for inferring disease-related lncRNAs. Briefings in Bioinformatics, 23(3), bbac089, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(24) 通讯作者. Integration of neighbor topologies based on meta-paths and node attributes for predicting drug-related diseases. International journal of molecular sciences, 23(7), 3870, 2022. (SCI收录，影响因子4.183，中科院2区top期刊)

(25)通讯作者. Heterogeneous multi-scale neighbor topologies enhanced drug-disease association prediction. Briefings in Bioinformatics, pp. 1-9, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(26) 通讯作者. Multi-type neighbors enhanced global topology and pairwise attribute learning for drug-protein interaction prediction. Briefings in Bioinformatics, pp. 1-9, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(27) 通讯作者. Integrating specific and common topologies of heterogeneous graphs and pairwise attributes for drug-related side effect prediction. Briefings in Bioinformatics, pp. 1-9, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(28) 通讯作者. Integration of pairwise neighbor topologies and miRNA family and cluster attributes for miRNA-disease association prediction. Briefings in Bioinformatics, pp. 1-12, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(29) 通讯作者. GVDTI: graph convolutional and variational autoencoders with attribute-level attention for drug-protein interaction prediction. Briefings in Bioinformatics, pp. 1-12, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(30) 通讯作者. Dynamic graph convolutional autoencoder with node attribute-wise attention for kidney and tumor segmentation from CT volumes. Knowledge-based Systems, 1-16, 2022. (该杂志在人工智能领域202本期刊中排名第12，影响因子: 8.038，JCR 1区top期刊，中科院1区top期刊)

2021年

(31) 通讯作者. Graph triple-attention network for disease-related lncRNA prediction. IEEE Journal of Biomedical and Health Informatics, 1-11, 2021. (SCI收录，中科院1区top期刊, 影响因子: 5.772)

(32) 通讯作者. Integrating specific and common topologies of heterogeneous graphs and pairwise attributes for drug-related side effect prediction. Briefings in Bioinformatics, pp. 1-9, 2022. (中科院2区期刊, 计算生物学领域1区期刊, SCI影响因子: 11.622)

(33) 通讯作者. Learning multi-scale heterogeneous representations and global topology for drug-target interaction prediction. IEEE Journal of Biomedical and Health Informatics, 1-12, 2021. (SCI收录，中科院1区top期刊，影响因子: 5.772)

(34) 通讯作者. Graph convolutional autoencoder and fully-connected autoencoder with attention mechanism based method for predicting drug-disease associations. IEEE Journal of Biomedical and Health Informatics, 1793-1804, 2021. (SCI收录，中科院1区top期刊，影响因子: 5.223)

国际合作与交流

我们课题组与日本东京大学（泰晤士世界大学排名第28位）的Koshizuka教授、日本千叶大学（泰晤士世界大学排名，第801到1000之间）的Nakaguchi教授、澳大利亚La Trobe大学（泰晤士世界大学排名，第251到300之间）的Cui博士，具有长期的合作和交流。对于具有科研热情和工作勤奋的同学，可以优先推荐到国外读博；对于有意在国内读博的同学，则优先推荐到吉林大学、天津大学、厦门大学等国内知名学府。

指导学生情况

(1) 联合指导的多数硕士研究生均荣获国家级或校级奖学金；

(2) 部分研究生毕业分别去了百度、京东、小米、平安保险等国内知名IT公司和企业；

(3) 部分研究生去了天津大学、南开大学、吉林大学、厦门大学、西安交通大学、中山大学、华中科技大学等国内知名学府，继续攻读博士研究生。