EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction
The identification of drug-target interaction (DTI) plays a key role in drug discovery and development. Benefitting from large-scale drug databases and verified DTI relationships, a lot of machine-learning methods have been developed to predict DTIs. However, due to the difficulty in extracting usef...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/11/12/1783 |
| _version_ | 1827673927378272256 |
|---|---|
| author | Yuan Jin Jiarui Lu Runhan Shi Yang Yang |
| author_facet | Yuan Jin Jiarui Lu Runhan Shi Yang Yang |
| author_sort | Yuan Jin |
| collection | DOAJ |
| description | The identification of drug-target interaction (DTI) plays a key role in drug discovery and development. Benefitting from large-scale drug databases and verified DTI relationships, a lot of machine-learning methods have been developed to predict DTIs. However, due to the difficulty in extracting useful information from molecules, the performance of these methods is limited by the representation of drugs and target proteins. This study proposes a new model called EmbedDTI to enhance the representation of both drugs and target proteins, and improve the performance of DTI prediction. For protein sequences, we leverage language modeling for pretraining the feature embeddings of amino acids and feed them to a convolutional neural network model for further representation learning. For drugs, we build two levels of graphs to represent compound structural information, namely the atom graph and substructure graph, and adopt graph convolutional network with an attention module to learn the embedding vectors for the graphs. We compare EmbedDTI with the existing DTI predictors on two benchmark datasets. The experimental results show that EmbedDTI outperforms the state-of-the-art models, and the attention module can identify the components crucial for DTIs in compounds. |
| first_indexed | 2024-03-10T04:32:34Z |
| format | Article |
| id | doaj.art-32e786e7a336434999ea7c3af1037345 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-10T04:32:34Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-32e786e7a336434999ea7c3af10373452023-11-23T03:59:04ZengMDPI AGBiomolecules2218-273X2021-11-011112178310.3390/biom11121783EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target InteractionYuan Jin0Jiarui Lu1Runhan Shi2Yang Yang3Center for Brain-Like Computing and Machine Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd., Shanghai 200240, ChinaSchool of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd., Shanghai 200240, ChinaCenter for Brain-Like Computing and Machine Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd., Shanghai 200240, ChinaCenter for Brain-Like Computing and Machine Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd., Shanghai 200240, ChinaThe identification of drug-target interaction (DTI) plays a key role in drug discovery and development. Benefitting from large-scale drug databases and verified DTI relationships, a lot of machine-learning methods have been developed to predict DTIs. However, due to the difficulty in extracting useful information from molecules, the performance of these methods is limited by the representation of drugs and target proteins. This study proposes a new model called EmbedDTI to enhance the representation of both drugs and target proteins, and improve the performance of DTI prediction. For protein sequences, we leverage language modeling for pretraining the feature embeddings of amino acids and feed them to a convolutional neural network model for further representation learning. For drugs, we build two levels of graphs to represent compound structural information, namely the atom graph and substructure graph, and adopt graph convolutional network with an attention module to learn the embedding vectors for the graphs. We compare EmbedDTI with the existing DTI predictors on two benchmark datasets. The experimental results show that EmbedDTI outperforms the state-of-the-art models, and the attention module can identify the components crucial for DTIs in compounds.https://www.mdpi.com/2218-273X/11/12/1783drug-target interactiongraph convolutional networkmolecular representation |
| spellingShingle | Yuan Jin Jiarui Lu Runhan Shi Yang Yang EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction Biomolecules drug-target interaction graph convolutional network molecular representation |
| title | EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction |
| title_full | EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction |
| title_fullStr | EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction |
| title_full_unstemmed | EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction |
| title_short | EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction |
| title_sort | embeddti enhancing the molecular representations via sequence embedding and graph convolutional network for the prediction of drug target interaction |
| topic | drug-target interaction graph convolutional network molecular representation |
| url | https://www.mdpi.com/2218-273X/11/12/1783 |
| work_keys_str_mv | AT yuanjin embeddtienhancingthemolecularrepresentationsviasequenceembeddingandgraphconvolutionalnetworkforthepredictionofdrugtargetinteraction AT jiaruilu embeddtienhancingthemolecularrepresentationsviasequenceembeddingandgraphconvolutionalnetworkforthepredictionofdrugtargetinteraction AT runhanshi embeddtienhancingthemolecularrepresentationsviasequenceembeddingandgraphconvolutionalnetworkforthepredictionofdrugtargetinteraction AT yangyang embeddtienhancingthemolecularrepresentationsviasequenceembeddingandgraphconvolutionalnetworkforthepredictionofdrugtargetinteraction |