Barlow Twins deep neural network for advanced 1D drug–target interaction prediction
Abstract Accurate prediction of drug–target interactions is critical for advancing drug discovery. By reducing time and cost, machine learning and deep learning can accelerate this laborious discovery process. In a novel approach, BarlowDTI, we utilise the powerful Barlow Twins architecture for feat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-025-00952-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861686593912832 |
|---|---|
| author | Maximilian G. Schuh Davide Boldini Annkathrin I. Bohne Stephan A. Sieber |
| author_facet | Maximilian G. Schuh Davide Boldini Annkathrin I. Bohne Stephan A. Sieber |
| author_sort | Maximilian G. Schuh |
| collection | DOAJ |
| description | Abstract Accurate prediction of drug–target interactions is critical for advancing drug discovery. By reducing time and cost, machine learning and deep learning can accelerate this laborious discovery process. In a novel approach, BarlowDTI, we utilise the powerful Barlow Twins architecture for feature-extraction while considering the structure of the target protein. Our method achieves state-of-the-art predictive performance against multiple established benchmarks using only one-dimensional input. The use of our hybrid approach of deep learning and gradient boosting machine as the underlying predictor ensures fast and efficient predictions without the need for substantial computational resources. We also propose the use of an influence method to investigate how the model reaches its decision based on individual training samples. By comparing co-crystal structures, we find that BarlowDTI effectively exploits catalytically active and stabilising residues, highlighting the model’s ability to generalise from one-dimensional input data. In addition, we further benchmark new baselines against existing methods. Together, these innovations improve the efficiency and effectiveness of drug–target interactions predictions, providing robust tools for accelerating drug development and deepening the understanding of molecular interactions. Therefore, we provide an easy-to-use web interface that can be freely accessed at https://www.bio.nat.tum.de/oc2/barlowdti . Scientific contribution Our computationally efficient and effective hybrid approach, combining the deep learning model Barlow Twins and gradient boosting machines, outperforms state-of-the-art methods across multiple splits and benchmarks using only one-dimensional input. Furthermore, we advance the field by proposing an influence method that elucidates model decision-making, thereby providing deeper insights into molecular interactions and improving the interpretability of drug-target interactions predictions. Graphical Abstract |
| format | Article |
| id | doaj-art-e9600bd1fdde439e9a1239f0932f8843 |
| institution | Kabale University |
| issn | 1758-2946 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj-art-e9600bd1fdde439e9a1239f0932f88432025-02-09T12:52:18ZengBMCJournal of Cheminformatics1758-29462025-02-0117111410.1186/s13321-025-00952-2Barlow Twins deep neural network for advanced 1D drug–target interaction predictionMaximilian G. Schuh0Davide Boldini1Annkathrin I. Bohne2Stephan A. Sieber3Chair of Organic Chemistry II, Department of Bioscience, TUM School of Natural Sciences, Center for Functional Protein Assemblies (CPA), Technical University of MunichChair of Organic Chemistry II, Department of Bioscience, TUM School of Natural Sciences, Center for Functional Protein Assemblies (CPA), Technical University of MunichChair of Biochemistry, Department of Bioscience, TUM School of Natural Sciences, Center for Functional Protein Assemblies (CPA), Technical University of MunichChair of Organic Chemistry II, Department of Bioscience, TUM School of Natural Sciences, Center for Functional Protein Assemblies (CPA), Technical University of MunichAbstract Accurate prediction of drug–target interactions is critical for advancing drug discovery. By reducing time and cost, machine learning and deep learning can accelerate this laborious discovery process. In a novel approach, BarlowDTI, we utilise the powerful Barlow Twins architecture for feature-extraction while considering the structure of the target protein. Our method achieves state-of-the-art predictive performance against multiple established benchmarks using only one-dimensional input. The use of our hybrid approach of deep learning and gradient boosting machine as the underlying predictor ensures fast and efficient predictions without the need for substantial computational resources. We also propose the use of an influence method to investigate how the model reaches its decision based on individual training samples. By comparing co-crystal structures, we find that BarlowDTI effectively exploits catalytically active and stabilising residues, highlighting the model’s ability to generalise from one-dimensional input data. In addition, we further benchmark new baselines against existing methods. Together, these innovations improve the efficiency and effectiveness of drug–target interactions predictions, providing robust tools for accelerating drug development and deepening the understanding of molecular interactions. Therefore, we provide an easy-to-use web interface that can be freely accessed at https://www.bio.nat.tum.de/oc2/barlowdti . Scientific contribution Our computationally efficient and effective hybrid approach, combining the deep learning model Barlow Twins and gradient boosting machines, outperforms state-of-the-art methods across multiple splits and benchmarks using only one-dimensional input. Furthermore, we advance the field by proposing an influence method that elucidates model decision-making, thereby providing deeper insights into molecular interactions and improving the interpretability of drug-target interactions predictions. Graphical Abstracthttps://doi.org/10.1186/s13321-025-00952-2Machine learningDeep neural networkDrug discoveryDrug–target interactions |
| spellingShingle | Maximilian G. Schuh Davide Boldini Annkathrin I. Bohne Stephan A. Sieber Barlow Twins deep neural network for advanced 1D drug–target interaction prediction Journal of Cheminformatics Machine learning Deep neural network Drug discovery Drug–target interactions |
| title | Barlow Twins deep neural network for advanced 1D drug–target interaction prediction |
| title_full | Barlow Twins deep neural network for advanced 1D drug–target interaction prediction |
| title_fullStr | Barlow Twins deep neural network for advanced 1D drug–target interaction prediction |
| title_full_unstemmed | Barlow Twins deep neural network for advanced 1D drug–target interaction prediction |
| title_short | Barlow Twins deep neural network for advanced 1D drug–target interaction prediction |
| title_sort | barlow twins deep neural network for advanced 1d drug target interaction prediction |
| topic | Machine learning Deep neural network Drug discovery Drug–target interactions |
| url | https://doi.org/10.1186/s13321-025-00952-2 |
| work_keys_str_mv | AT maximiliangschuh barlowtwinsdeepneuralnetworkforadvanced1ddrugtargetinteractionprediction AT davideboldini barlowtwinsdeepneuralnetworkforadvanced1ddrugtargetinteractionprediction AT annkathrinibohne barlowtwinsdeepneuralnetworkforadvanced1ddrugtargetinteractionprediction AT stephanasieber barlowtwinsdeepneuralnetworkforadvanced1ddrugtargetinteractionprediction |