{"title":"MHGTMDA:基于生物实体图的分子异质图转换器,用于 miRNA 与疾病的关联预测","authors":"Haitao Zou, Boya Ji, Meng Zhang, Fen Liu, Xiaolan Xie, Shaoliang Peng","doi":"10.1016/j.omtn.2024.102139","DOIUrl":null,"url":null,"abstract":"<p>MicroRNAs (miRNAs) play a crucial role in the prevention, prognosis, diagnosis, and treatment of complex diseases. Existing computational methods primarily focus on biologically relevant molecules directly associated with miRNA or disease, overlooking the fact that the human body is a highly complex system where miRNA or disease may indirectly correlate with various types of biomolecules. To address this, we propose a novel prediction model named MHGTMDA (miRNA and disease association prediction using Heterogeneous Graph Transformer based on Molecular Heterogeneous Graph). MHGTMDA integrates biological entity relationships of eight biomolecules, constructing a relatively comprehensive heterogeneous biological entity graph. MHGTMDA serves as a powerful molecular heterogeneity map transformer, capturing structural elements and properties of miRNAs and diseases, revealing potential associations. In a 5-fold cross-validation study, MHGTMDA achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9569, surpassing state-of-the-art methods by at least 3%. Feature ablation experiments suggest that considering features among multiple biomolecules is more effective in uncovering miRNA-disease correlations. Furthermore, we conducted differential expression analyses on breast cancer and lung cancer, using MHGTMDA to further validate differentially expressed miRNAs. The results demonstrate MHGTMDA’s capability to identify novel MDAs. MHGTMDA is free and available at <span>https://github.com/zht-code/HGTMDA.git</span><svg aria-label=\"Opens in new window\" focusable=\"false\" height=\"8px\" viewbox=\"0 0 8 8\" width=\"8px\"><path d=\"M1.12949 2.1072V1H7V6.85795H5.89111V2.90281L0.784057 8L0 7.21635L5.11902 2.1072H1.12949Z\"></path></svg>.</p>","PeriodicalId":18821,"journal":{"name":"Molecular Therapy. Nucleic Acids","volume":null,"pages":null},"PeriodicalIF":6.5000,"publicationDate":"2024-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MHGTMDA: molecular heterogeneous graph transformer based on biological entity graph for miRNA-disease associations prediction\",\"authors\":\"Haitao Zou, Boya Ji, Meng Zhang, Fen Liu, Xiaolan Xie, Shaoliang Peng\",\"doi\":\"10.1016/j.omtn.2024.102139\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>MicroRNAs (miRNAs) play a crucial role in the prevention, prognosis, diagnosis, and treatment of complex diseases. Existing computational methods primarily focus on biologically relevant molecules directly associated with miRNA or disease, overlooking the fact that the human body is a highly complex system where miRNA or disease may indirectly correlate with various types of biomolecules. To address this, we propose a novel prediction model named MHGTMDA (miRNA and disease association prediction using Heterogeneous Graph Transformer based on Molecular Heterogeneous Graph). MHGTMDA integrates biological entity relationships of eight biomolecules, constructing a relatively comprehensive heterogeneous biological entity graph. MHGTMDA serves as a powerful molecular heterogeneity map transformer, capturing structural elements and properties of miRNAs and diseases, revealing potential associations. In a 5-fold cross-validation study, MHGTMDA achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9569, surpassing state-of-the-art methods by at least 3%. Feature ablation experiments suggest that considering features among multiple biomolecules is more effective in uncovering miRNA-disease correlations. Furthermore, we conducted differential expression analyses on breast cancer and lung cancer, using MHGTMDA to further validate differentially expressed miRNAs. The results demonstrate MHGTMDA’s capability to identify novel MDAs. MHGTMDA is free and available at <span>https://github.com/zht-code/HGTMDA.git</span><svg aria-label=\\\"Opens in new window\\\" focusable=\\\"false\\\" height=\\\"8px\\\" viewbox=\\\"0 0 8 8\\\" width=\\\"8px\\\"><path d=\\\"M1.12949 2.1072V1H7V6.85795H5.89111V2.90281L0.784057 8L0 7.21635L5.11902 2.1072H1.12949Z\\\"></path></svg>.</p>\",\"PeriodicalId\":18821,\"journal\":{\"name\":\"Molecular Therapy. Nucleic Acids\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.5000,\"publicationDate\":\"2024-02-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Molecular Therapy. Nucleic Acids\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.omtn.2024.102139\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICINE, RESEARCH & EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Molecular Therapy. Nucleic Acids","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.omtn.2024.102139","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
MHGTMDA: molecular heterogeneous graph transformer based on biological entity graph for miRNA-disease associations prediction
MicroRNAs (miRNAs) play a crucial role in the prevention, prognosis, diagnosis, and treatment of complex diseases. Existing computational methods primarily focus on biologically relevant molecules directly associated with miRNA or disease, overlooking the fact that the human body is a highly complex system where miRNA or disease may indirectly correlate with various types of biomolecules. To address this, we propose a novel prediction model named MHGTMDA (miRNA and disease association prediction using Heterogeneous Graph Transformer based on Molecular Heterogeneous Graph). MHGTMDA integrates biological entity relationships of eight biomolecules, constructing a relatively comprehensive heterogeneous biological entity graph. MHGTMDA serves as a powerful molecular heterogeneity map transformer, capturing structural elements and properties of miRNAs and diseases, revealing potential associations. In a 5-fold cross-validation study, MHGTMDA achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9569, surpassing state-of-the-art methods by at least 3%. Feature ablation experiments suggest that considering features among multiple biomolecules is more effective in uncovering miRNA-disease correlations. Furthermore, we conducted differential expression analyses on breast cancer and lung cancer, using MHGTMDA to further validate differentially expressed miRNAs. The results demonstrate MHGTMDA’s capability to identify novel MDAs. MHGTMDA is free and available at https://github.com/zht-code/HGTMDA.git.
期刊介绍:
Molecular Therapy Nucleic Acids is an international, open-access journal that publishes high-quality research in nucleic-acid-based therapeutics to treat and correct genetic and acquired diseases. It is the official journal of the American Society of Gene & Cell Therapy and is built upon the success of Molecular Therapy. The journal focuses on gene- and oligonucleotide-based therapies and publishes peer-reviewed research, reviews, and commentaries. Its impact factor for 2022 is 8.8. The subject areas covered include the development of therapeutics based on nucleic acids and their derivatives, vector development for RNA-based therapeutics delivery, utilization of gene-modifying agents like Zn finger nucleases and triplex-forming oligonucleotides, pre-clinical target validation, safety and efficacy studies, and clinical trials.