Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction
Abstract Background Long noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12864-024-09998-2 |
| _version_ | 1797350127657025536 |
|---|---|
| author | Guanghui Li Peihao Bai Cheng Liang Jiawei Luo |
| author_facet | Guanghui Li Peihao Bai Cheng Liang Jiawei Luo |
| author_sort | Guanghui Li |
| collection | DOAJ |
| description | Abstract Background Long noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribute to a better understanding of the pathogenic mechanisms of disease and provide strong support for the development of advanced treatment methods. Results Therefore, we present an innovative Node-Adaptive Graph Transformer model for predicting unknown LncRNA-Disease Associations, named NAGTLDA. First, we utilize the node-adaptive feature smoothing (NAFS) method to learn the local feature information of nodes and encode the structural information of the fusion similarity network of diseases and lncRNAs using Structural Deep Network Embedding (SDNE). Next, the Transformer module is used to capture potential association information between the network nodes. Finally, we employ a Transformer module with two multi-headed attention layers for learning global-level embedding fusion. Network structure coding is added as the structural inductive bias of the network to compensate for the missing message-passing mechanism in Transformer. NAGTLDA achieved an average AUC of 0.9531 and AUPR of 0.9537 significantly higher than state-of-the-art methods in 5-fold cross validation. We perform case studies on 4 diseases; 55 out of 60 associations between lncRNAs and diseases have been validated in the literatures. The results demonstrate the enormous potential of the graph Transformer structure to incorporate graph structural information for uncovering lncRNA-disease unknown correlations. Conclusions Our proposed NAGTLDA model can serve as a highly efficient computational method for predicting biological information associations. |
| first_indexed | 2024-03-08T12:40:21Z |
| format | Article |
| id | doaj.art-5edb62a336b8452097400c9530d3e81f |
| institution | Directory Open Access Journal |
| issn | 1471-2164 |
| language | English |
| last_indexed | 2024-03-08T12:40:21Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj.art-5edb62a336b8452097400c9530d3e81f2024-01-21T12:11:48ZengBMCBMC Genomics1471-21642024-01-0125112610.1186/s12864-024-09998-2Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association predictionGuanghui Li0Peihao Bai1Cheng Liang2Jiawei Luo3School of Information Engineering, East China Jiaotong UniversitySchool of Information Engineering, East China Jiaotong UniversitySchool of Information Science and Engineering, Shandong Normal UniversityCollege of Computer Science and Electronic Engineering, Hunan UniversityAbstract Background Long noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribute to a better understanding of the pathogenic mechanisms of disease and provide strong support for the development of advanced treatment methods. Results Therefore, we present an innovative Node-Adaptive Graph Transformer model for predicting unknown LncRNA-Disease Associations, named NAGTLDA. First, we utilize the node-adaptive feature smoothing (NAFS) method to learn the local feature information of nodes and encode the structural information of the fusion similarity network of diseases and lncRNAs using Structural Deep Network Embedding (SDNE). Next, the Transformer module is used to capture potential association information between the network nodes. Finally, we employ a Transformer module with two multi-headed attention layers for learning global-level embedding fusion. Network structure coding is added as the structural inductive bias of the network to compensate for the missing message-passing mechanism in Transformer. NAGTLDA achieved an average AUC of 0.9531 and AUPR of 0.9537 significantly higher than state-of-the-art methods in 5-fold cross validation. We perform case studies on 4 diseases; 55 out of 60 associations between lncRNAs and diseases have been validated in the literatures. The results demonstrate the enormous potential of the graph Transformer structure to incorporate graph structural information for uncovering lncRNA-disease unknown correlations. Conclusions Our proposed NAGTLDA model can serve as a highly efficient computational method for predicting biological information associations.https://doi.org/10.1186/s12864-024-09998-2lncRNA-disease associationsTransformerStructural deep network embeddingNode-adaptive feature smoothing |
| spellingShingle | Guanghui Li Peihao Bai Cheng Liang Jiawei Luo Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction BMC Genomics lncRNA-disease associations Transformer Structural deep network embedding Node-adaptive feature smoothing |
| title | Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction |
| title_full | Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction |
| title_fullStr | Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction |
| title_full_unstemmed | Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction |
| title_short | Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction |
| title_sort | node adaptive graph transformer with structural encoding for accurate and robust lncrna disease association prediction |
| topic | lncRNA-disease associations Transformer Structural deep network embedding Node-adaptive feature smoothing |
| url | https://doi.org/10.1186/s12864-024-09998-2 |
| work_keys_str_mv | AT guanghuili nodeadaptivegraphtransformerwithstructuralencodingforaccurateandrobustlncrnadiseaseassociationprediction AT peihaobai nodeadaptivegraphtransformerwithstructuralencodingforaccurateandrobustlncrnadiseaseassociationprediction AT chengliang nodeadaptivegraphtransformerwithstructuralencodingforaccurateandrobustlncrnadiseaseassociationprediction AT jiaweiluo nodeadaptivegraphtransformerwithstructuralencodingforaccurateandrobustlncrnadiseaseassociationprediction |