DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning
Drug–drug interactions (DDIs) are entities composed of different chemical substructures (functional groups). In existing methods that predict drug–drug interactions based on the usage of substructures, each node is perceived as the epicenter of a sub-pattern, and adjacent nodes eventually become cen...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/19/10750 |
| _version_ | 1827722777489047552 |
|---|---|
| author | Yuan Liang |
| author_facet | Yuan Liang |
| author_sort | Yuan Liang |
| collection | DOAJ |
| description | Drug–drug interactions (DDIs) are entities composed of different chemical substructures (functional groups). In existing methods that predict drug–drug interactions based on the usage of substructures, each node is perceived as the epicenter of a sub-pattern, and adjacent nodes eventually become centers of similar substructures, resulting in redundancy. Furthermore, the significant differences in structure and properties among compounds can lead to unrelated pairings, making it difficult to integrate information. This heterogeneity negatively affects the prediction results. In response to these challenges, we propose a drug–drug interaction prediction method based on substructure signature learning (DDI-SSL). This method extracts useful information from local subgraphs surrounding drugs and effectively utilizes substructures to assist in predicting drug side effects. Additionally, a deep clustering algorithm is used to aggregate similar substructures, allowing any individual subgraph to be reconstructed using this set of global signatures. Furthermore, we developed a layer-independent collaborative attention mechanism to model the mutual influence between drugs, generating signal strength scores for each class of drugs to mitigate noise caused by heterogeneity. Finally, we evaluated DDI-SSL on a comprehensive dataset and demonstrated improved performance in DDI prediction compared to state-of-the-art methods. |
| first_indexed | 2024-03-10T21:49:39Z |
| format | Article |
| id | doaj.art-7f58d0ec957f429591dd189c14f3e161 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:49:39Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7f58d0ec957f429591dd189c14f3e1612023-11-19T14:03:42ZengMDPI AGApplied Sciences2076-34172023-09-0113191075010.3390/app131910750DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature LearningYuan Liang0School of Information Engineering, Suqian University, Suqian 223800, ChinaDrug–drug interactions (DDIs) are entities composed of different chemical substructures (functional groups). In existing methods that predict drug–drug interactions based on the usage of substructures, each node is perceived as the epicenter of a sub-pattern, and adjacent nodes eventually become centers of similar substructures, resulting in redundancy. Furthermore, the significant differences in structure and properties among compounds can lead to unrelated pairings, making it difficult to integrate information. This heterogeneity negatively affects the prediction results. In response to these challenges, we propose a drug–drug interaction prediction method based on substructure signature learning (DDI-SSL). This method extracts useful information from local subgraphs surrounding drugs and effectively utilizes substructures to assist in predicting drug side effects. Additionally, a deep clustering algorithm is used to aggregate similar substructures, allowing any individual subgraph to be reconstructed using this set of global signatures. Furthermore, we developed a layer-independent collaborative attention mechanism to model the mutual influence between drugs, generating signal strength scores for each class of drugs to mitigate noise caused by heterogeneity. Finally, we evaluated DDI-SSL on a comprehensive dataset and demonstrated improved performance in DDI prediction compared to state-of-the-art methods.https://www.mdpi.com/2076-3417/13/19/10750drug–drug interactionssubstructure graph convolution operatorsubstructure signaturessubstructure extractioncollaborative attention mechanism |
| spellingShingle | Yuan Liang DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning Applied Sciences drug–drug interactions substructure graph convolution operator substructure signatures substructure extraction collaborative attention mechanism |
| title | DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning |
| title_full | DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning |
| title_fullStr | DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning |
| title_full_unstemmed | DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning |
| title_short | DDI-SSL: Drug–Drug Interaction Prediction Based on Substructure Signature Learning |
| title_sort | ddi ssl drug drug interaction prediction based on substructure signature learning |
| topic | drug–drug interactions substructure graph convolution operator substructure signatures substructure extraction collaborative attention mechanism |
| url | https://www.mdpi.com/2076-3417/13/19/10750 |
| work_keys_str_mv | AT yuanliang ddissldrugdruginteractionpredictionbasedonsubstructuresignaturelearning |