Predicting drug and target interaction with dilated reparameterize convolution
Abstract Predicting drug-target interaction (DTI) stands as a pivotal and formidable challenge in pharmaceutical research. Many existing deep learning methods only learn the high-dimensional representation of ligands and targets on a small scale. However, it is difficult for the model to obtain the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86918-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585771702288384 |
|---|---|
| author | Moping Deng Jian Wang Yiming Zhao Yongjia Zhao Hao Cao Zhuo Wang |
| author_facet | Moping Deng Jian Wang Yiming Zhao Yongjia Zhao Hao Cao Zhuo Wang |
| author_sort | Moping Deng |
| collection | DOAJ |
| description | Abstract Predicting drug-target interaction (DTI) stands as a pivotal and formidable challenge in pharmaceutical research. Many existing deep learning methods only learn the high-dimensional representation of ligands and targets on a small scale. However, it is difficult for the model to obtain the potential law of combining pockets or multiple binding sites on a large scale. To address this lacuna, we designed a large-kernel convolutional block for extracting large-scale sequence information and proposed a novel DTI prediction framework, named Rep-ConvDTI. The reparameterization method is introduced to help large-kernel convolutions capture small-scale information. We have also developed a gated attention mechanism to more efficiently characterize the interaction of drugs and targets. Extensive experiments demonstrate that Rep-ConvDTI achieves the most competitive performance against state-of-the-art baselines on the three benchmark datasets. Furthermore, we validated the potential of Rep-ConvDTI as a drug screening tool through model interpretative studies and drug screening experiments with cystathionine-β-synthase. |
| format | Article |
| id | doaj-art-4ffc68f6ea564f75bb837318fe41ed53 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-4ffc68f6ea564f75bb837318fe41ed532025-01-26T12:29:22ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-025-86918-8Predicting drug and target interaction with dilated reparameterize convolutionMoping Deng0Jian Wang1Yiming Zhao2Yongjia Zhao3Hao Cao4Zhuo Wang5Shenyang Institute of Automation, Chinese Academy of ScienceShenyang Institute of Automation, Chinese Academy of ScienceShenyang Institute of Automation, Chinese Academy of ScienceShenyang Institute of Automation, Chinese Academy of ScienceSchool of Life Science and Biopharmaceutics, Shenyang Pharmaceutical UniversityShenyang Institute of Automation, Chinese Academy of ScienceAbstract Predicting drug-target interaction (DTI) stands as a pivotal and formidable challenge in pharmaceutical research. Many existing deep learning methods only learn the high-dimensional representation of ligands and targets on a small scale. However, it is difficult for the model to obtain the potential law of combining pockets or multiple binding sites on a large scale. To address this lacuna, we designed a large-kernel convolutional block for extracting large-scale sequence information and proposed a novel DTI prediction framework, named Rep-ConvDTI. The reparameterization method is introduced to help large-kernel convolutions capture small-scale information. We have also developed a gated attention mechanism to more efficiently characterize the interaction of drugs and targets. Extensive experiments demonstrate that Rep-ConvDTI achieves the most competitive performance against state-of-the-art baselines on the three benchmark datasets. Furthermore, we validated the potential of Rep-ConvDTI as a drug screening tool through model interpretative studies and drug screening experiments with cystathionine-β-synthase.https://doi.org/10.1038/s41598-025-86918-8Drug-target interactionLarge-kernel convolutionAttention mechanismDrug screeningDeep learning |
| spellingShingle | Moping Deng Jian Wang Yiming Zhao Yongjia Zhao Hao Cao Zhuo Wang Predicting drug and target interaction with dilated reparameterize convolution Scientific Reports Drug-target interaction Large-kernel convolution Attention mechanism Drug screening Deep learning |
| title | Predicting drug and target interaction with dilated reparameterize convolution |
| title_full | Predicting drug and target interaction with dilated reparameterize convolution |
| title_fullStr | Predicting drug and target interaction with dilated reparameterize convolution |
| title_full_unstemmed | Predicting drug and target interaction with dilated reparameterize convolution |
| title_short | Predicting drug and target interaction with dilated reparameterize convolution |
| title_sort | predicting drug and target interaction with dilated reparameterize convolution |
| topic | Drug-target interaction Large-kernel convolution Attention mechanism Drug screening Deep learning |
| url | https://doi.org/10.1038/s41598-025-86918-8 |
| work_keys_str_mv | AT mopingdeng predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution AT jianwang predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution AT yimingzhao predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution AT yongjiazhao predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution AT haocao predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution AT zhuowang predictingdrugandtargetinteractionwithdilatedreparameterizeconvolution |