GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures
The prediction of drug–target interactions is always a key task in the field of drug redirection. However, traditional methods of predicting drug–target interactions are either mediocre or rely heavily on data stacking. In this work, we proposed our model named GraphMS. We merged heterogeneous graph...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/7/3239 |
| _version_ | 1797538849905180672 |
|---|---|
| author | Shicheng Cheng Liang Zhang Bo Jin Qiang Zhang Xinjiang Lu Mao You Xueqing Tian |
| author_facet | Shicheng Cheng Liang Zhang Bo Jin Qiang Zhang Xinjiang Lu Mao You Xueqing Tian |
| author_sort | Shicheng Cheng |
| collection | DOAJ |
| description | The prediction of drug–target interactions is always a key task in the field of drug redirection. However, traditional methods of predicting drug–target interactions are either mediocre or rely heavily on data stacking. In this work, we proposed our model named GraphMS. We merged heterogeneous graph information and obtained effective node information and substructure information based on mutual information in graph embeddings. We then learned high quality representations for downstream tasks, and proposed an end–to–end auto–encoder model to complete the task of link prediction. Experimental results show that our method outperforms several state–of–the–art models. The model can achieve the area under the receiver operating characteristics (AUROC) curve of 0.959 and area under the precise recall curve (AUPR) of 0.847. We found that the mutual information between the substructure and graph–level representations contributes most to the mutual information index in a relatively sparse network. And the mutual information between the node–level and graph–level representations contributes most in a relatively dense network. |
| first_indexed | 2024-03-10T12:37:16Z |
| format | Article |
| id | doaj.art-f78e65a4ace74ae38a3b31da6b07f45b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T12:37:16Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f78e65a4ace74ae38a3b31da6b07f45b2023-11-21T14:13:16ZengMDPI AGApplied Sciences2076-34172021-04-01117323910.3390/app11073239GraphMS: Drug Target Prediction Using Graph Representation Learning with SubstructuresShicheng Cheng0Liang Zhang1Bo Jin2Qiang Zhang3Xinjiang Lu4Mao You5Xueqing Tian6Department of Computer Science and Technology, Dalian University of Technology, DaLian 116000, ChinaInstitute of Economics and Management, Dongbei University of Finance and Economics, DaLian 116000, ChinaDepartment of Computer Science and Technology, Dalian University of Technology, DaLian 116000, ChinaDepartment of Computer Science and Technology, Dalian University of Technology, DaLian 116000, ChinaArtificial Intelligence Group, Baidu Inc., Beijing 100089, ChinaDepartment of Health Technology Assessmen, China National Health Development Research Center, Beijing 100089, ChinaDepartment of Health Technology Assessmen, China National Health Development Research Center, Beijing 100089, ChinaThe prediction of drug–target interactions is always a key task in the field of drug redirection. However, traditional methods of predicting drug–target interactions are either mediocre or rely heavily on data stacking. In this work, we proposed our model named GraphMS. We merged heterogeneous graph information and obtained effective node information and substructure information based on mutual information in graph embeddings. We then learned high quality representations for downstream tasks, and proposed an end–to–end auto–encoder model to complete the task of link prediction. Experimental results show that our method outperforms several state–of–the–art models. The model can achieve the area under the receiver operating characteristics (AUROC) curve of 0.959 and area under the precise recall curve (AUPR) of 0.847. We found that the mutual information between the substructure and graph–level representations contributes most to the mutual information index in a relatively sparse network. And the mutual information between the node–level and graph–level representations contributes most in a relatively dense network.https://www.mdpi.com/2076-3417/11/7/3239graph embeddinglink predictionmutual informationsubgraph |
| spellingShingle | Shicheng Cheng Liang Zhang Bo Jin Qiang Zhang Xinjiang Lu Mao You Xueqing Tian GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures Applied Sciences graph embedding link prediction mutual information subgraph |
| title | GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures |
| title_full | GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures |
| title_fullStr | GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures |
| title_full_unstemmed | GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures |
| title_short | GraphMS: Drug Target Prediction Using Graph Representation Learning with Substructures |
| title_sort | graphms drug target prediction using graph representation learning with substructures |
| topic | graph embedding link prediction mutual information subgraph |
| url | https://www.mdpi.com/2076-3417/11/7/3239 |
| work_keys_str_mv | AT shichengcheng graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT liangzhang graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT bojin graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT qiangzhang graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT xinjianglu graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT maoyou graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures AT xueqingtian graphmsdrugtargetpredictionusinggraphrepresentationlearningwithsubstructures |