DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation
Abstract Identifying novel drugs that can interact with target proteins is a highly challenging, time-consuming, and costly task in drug discovery and development. Numerous machine learning-based models have recently been utilized to accelerate the drug discovery process. However, these existing met...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-59917-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850243038645846016 |
|---|---|
| author | Pir Masoom Shah Huimin Zhu Zhangli Lu Kaili Wang Jing Tang Min Li |
| author_facet | Pir Masoom Shah Huimin Zhu Zhangli Lu Kaili Wang Jing Tang Min Li |
| author_sort | Pir Masoom Shah |
| collection | DOAJ |
| description | Abstract Identifying novel drugs that can interact with target proteins is a highly challenging, time-consuming, and costly task in drug discovery and development. Numerous machine learning-based models have recently been utilized to accelerate the drug discovery process. However, these existing methods are primarily uni-tasking, either designed to predict drug-target interaction (DTI) or generate new drugs. Through the lens of pharmacological research, these tasks are intrinsically interconnected and play a critical role in effective drug development. Therefore, the learning models must be utilized in such a manner to learn the structural properties of drug molecules, the conformational dynamics of proteins, and the bioactivity between drugs and targets. To this end, this paper develops a novel multitask learning framework that can predict drug-target binding affinities and simultaneously generate new target-aware drug variants, using common features for both tasks. In addition, we developed the FetterGrad algorithm to address the optimization challenges associated with multitask learning particularly those caused by gradient conflicts between distinct tasks. Comprehensive experiments on three real-world datasets demonstrate that the proposed model provides an effective mechanism for predicting drug-target binding affinities and generating novel drugs, thus greatly facilitating the drug discovery process. |
| format | Article |
| id | doaj-art-e31504601a1b4667b6ce49c84b6aaec9 |
| institution | OA Journals |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-e31504601a1b4667b6ce49c84b6aaec92025-08-20T02:00:07ZengNature PortfolioNature Communications2041-17232025-05-0116111510.1038/s41467-025-59917-6DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generationPir Masoom Shah0Huimin Zhu1Zhangli Lu2Kaili Wang3Jing Tang4Min Li5School of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Technology, Donghua UniversityResearch Program in Systems Oncology, Faculty of Medicine, University of HelsinkiSchool of Computer Science and Engineering, Central South UniversityAbstract Identifying novel drugs that can interact with target proteins is a highly challenging, time-consuming, and costly task in drug discovery and development. Numerous machine learning-based models have recently been utilized to accelerate the drug discovery process. However, these existing methods are primarily uni-tasking, either designed to predict drug-target interaction (DTI) or generate new drugs. Through the lens of pharmacological research, these tasks are intrinsically interconnected and play a critical role in effective drug development. Therefore, the learning models must be utilized in such a manner to learn the structural properties of drug molecules, the conformational dynamics of proteins, and the bioactivity between drugs and targets. To this end, this paper develops a novel multitask learning framework that can predict drug-target binding affinities and simultaneously generate new target-aware drug variants, using common features for both tasks. In addition, we developed the FetterGrad algorithm to address the optimization challenges associated with multitask learning particularly those caused by gradient conflicts between distinct tasks. Comprehensive experiments on three real-world datasets demonstrate that the proposed model provides an effective mechanism for predicting drug-target binding affinities and generating novel drugs, thus greatly facilitating the drug discovery process.https://doi.org/10.1038/s41467-025-59917-6 |
| spellingShingle | Pir Masoom Shah Huimin Zhu Zhangli Lu Kaili Wang Jing Tang Min Li DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation Nature Communications |
| title | DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation |
| title_full | DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation |
| title_fullStr | DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation |
| title_full_unstemmed | DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation |
| title_short | DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation |
| title_sort | deepdtagen a multitask deep learning framework for drug target affinity prediction and target aware drugs generation |
| url | https://doi.org/10.1038/s41467-025-59917-6 |
| work_keys_str_mv | AT pirmasoomshah deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration AT huiminzhu deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration AT zhanglilu deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration AT kailiwang deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration AT jingtang deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration AT minli deepdtagenamultitaskdeeplearningframeworkfordrugtargetaffinitypredictionandtargetawaredrugsgeneration |