LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911518702960640 |
|---|---|
| author | Dun, Zihan Xu, Liuyi Lu, An-Yang Li, Shuang Qian, Yining |
| author_facet | Dun, Zihan Xu, Liuyi Lu, An-Yang Li, Shuang Qian, Yining |
| contents | Drug--target affinity prediction is pivotal for accelerating drug discovery, yet existing methods suffer from significant performance degradation in realistic cold-start scenarios (unseen drugs/targets/pairs), primarily driven by overfitting to training instances and information loss from irrelevant target sequences. In this paper, we propose LaPro-DTA, a framework designed to achieve robust and generalizable DTA prediction. To tackle overfitting, we devise a latent dual-view drug representation mechanism. It synergizes an instance-level view to capture fine-grained substructures with stochastic perturbation and a distribution-level view to distill generalized chemical scaffolds via semantic remapping, thereby enforcing the model to learn transferable structural rules rather than memorizing specific samples. To mitigate information loss, we introduce a salient protein feature extraction strategy using pattern-aware top-$k$ pooling, which effectively filters background noise and isolates high-response bioactive regions. Furthermore, a cross-view multi-head attention mechanism fuses these purified features to model comprehensive interactions. Extensive experiments on benchmark datasets demonstrate that LaPro-DTA significantly outperforms state-of-the-art methods, achieving an 8\% MSE reduction on the Davis dataset in the challenging unseen-drug setting, while offering interpretable insights into binding mechanisms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14792 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction Dun, Zihan Xu, Liuyi Lu, An-Yang Li, Shuang Qian, Yining Machine Learning Artificial Intelligence J.3; I.2.6; I.2.0 Drug--target affinity prediction is pivotal for accelerating drug discovery, yet existing methods suffer from significant performance degradation in realistic cold-start scenarios (unseen drugs/targets/pairs), primarily driven by overfitting to training instances and information loss from irrelevant target sequences. In this paper, we propose LaPro-DTA, a framework designed to achieve robust and generalizable DTA prediction. To tackle overfitting, we devise a latent dual-view drug representation mechanism. It synergizes an instance-level view to capture fine-grained substructures with stochastic perturbation and a distribution-level view to distill generalized chemical scaffolds via semantic remapping, thereby enforcing the model to learn transferable structural rules rather than memorizing specific samples. To mitigate information loss, we introduce a salient protein feature extraction strategy using pattern-aware top-$k$ pooling, which effectively filters background noise and isolates high-response bioactive regions. Furthermore, a cross-view multi-head attention mechanism fuses these purified features to model comprehensive interactions. Extensive experiments on benchmark datasets demonstrate that LaPro-DTA significantly outperforms state-of-the-art methods, achieving an 8\% MSE reduction on the Davis dataset in the challenging unseen-drug setting, while offering interpretable insights into binding mechanisms. |
| title | LaPro-DTA: Latent Dual-View Drug Representations and Salient Protein Feature Extraction for Generalizable Drug--Target Affinity Prediction |
| topic | Machine Learning Artificial Intelligence J.3; I.2.6; I.2.0 |
| url | https://arxiv.org/abs/2603.14792 |