Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Interpretable bilinear attention network with domain adaptation improves drug–target prediction

A preprint version of the article is available at arXiv.


Predicting drug–target interaction is key for drug discovery. Recent deep learning-based methods show promising performance, but two challenges remain: how to explicitly model and learn local interactions between drugs and targets for better prediction and interpretation and how to optimize generalization performance of predictions on novel drug–target pairs. Here, we present DrugBAN, a deep bilinear attention network (BAN) framework with domain adaptation to explicitly learn pairwise local interactions between drugs and targets, and adapt in response to out-of-distribution data. DrugBAN works on drug molecular graphs and target protein sequences to perform prediction, with conditional domain adversarial learning to align learned interaction representations across different distributions for better generalization on novel drug–target pairs. Experiments on three benchmark datasets under both in-domain and cross-domain settings show that DrugBAN achieves the best overall performance against five state-of-the-art baseline models. Moreover, visualizing the learned bilinear attention map provides interpretable insights from prediction results.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of the DrugBAN framework.
Fig. 2: In-domain performance comparison on the Human dataset with random split and cold pair split (statistics over five random runs).
Fig. 3: Cross-domain performance comparison on the BindingDB and BioSNAP datasets with clustering-based pair split (statistics over five random runs).
Fig. 4: Visualization of ligands and binding pockets for interpretability study.

Similar content being viewed by others

Data availability

The experimental data used in this work are available at All data used in this work are from public resources. The BindingDB48 source can be found at; the BioSNAP17,30 source can be found at and the Human31 source used in a previous study16 can be found at The co-crystalized ligands from PDB40 are available at by searching their PDB IDs.

Code availability

The source code and implementation details of DrugBAN are freely available at both GitHub repository ( and CodeOcean capsule ( The code is also archived at Zenodo (


  1. Luo, Y. et al. A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nat. Commun. 8, 1–13 (2017).

  2. Öztürk, H., Olmez, E. O. & Özgür, A. DeepDTA: deep drug-target binding affinity prediction. Bioinformatics 34, i821–i829 (2018).

    Article  Google Scholar 

  3. Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W. & Kanehisa, M. Prediction of drug-target interaction networks from the integration of chemical and genomic spaces. Bioinformatics 24, i232 – i240 (2008).

    Article  Google Scholar 

  4. Zitnik, M. et al. Machine learning for integrating data in biology and medicine: principles, practice, and opportunities. Inf. Fusion 50, 71–91 (2019).

    Article  Google Scholar 

  5. Bagherian, M. et al. Machine learning approaches and databases for prediction of drug-target interaction: a survey paper. Brief. Bioinform. 22, 247–269 (2021).

    Google Scholar 

  6. Wen, M. et al. Deep-learning-based drug-target interaction prediction. J. Proteome Res. 16, 1401–1409 (2017).

    Article  Google Scholar 

  7. Sieg, J., Flachsenberg, F. & Rarey, M. In need of bias control: evaluating chemical data for machine learning in structure-based virtual screening. J. Chem. Inf. Model. 59, 947–961 (2019).

    Article  Google Scholar 

  8. Lim, S. et al. A review on compound-protein interaction prediction methods: data, format, representation and model. Comput. Struct. Biotechnol. J. 19, 1541–1556 (2021).

    Google Scholar 

  9. Gao, K. Y. et al. Interpretable drug target prediction using deep neural representation. In Int. Joint Conf. on Artificial Intelligence (IJCAI) 3371–3377 (2018).

  10. Bredel, M. & Jacoby, E. Chemogenomics: an emerging strategy for rapid target and drug discovery. Nat. Rev. Genet. 5, 262–275 (2004).

    Article  Google Scholar 

  11. Lee, I., Keum, J. & Nam, H. DeepConv-DTI: prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput. Biol. 15, e1007129 (2019).

    Article  Google Scholar 

  12. Hinnerichs, T. & Hoehndorf, R. DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug-target interactions. Bioinformatics 37, 4835–4843 (2021).

    Article  Google Scholar 

  13. Nguyen, T. et al. GraphDTA: predicting drug-target binding affinity with graph neural networks. Bioinformatics 37, 1140–1147 (2021).

    Article  Google Scholar 

  14. Tsubaki, M., Tomii, K. & Sese, J. Compound protein interaction prediction with end to end learning of neural networks for graphs and sequences. Bioinformatics 35, 309–318 (2019).

    Article  Google Scholar 

  15. Feng, Q., Dueva, E., Cherkasov, A. & Ester, M. PADME: a deep learning-based framework for drug-target interaction prediction. Preprint at arXiv (2018).

  16. Chen, L. et al. TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36, 4406–4414 (2020).

  17. Huang, K., Xiao, C., Glass, L. & Sun, J. MolTrans: molecular interaction transformer for drug-target interaction prediction. Bioinformatics 37, 830–836 (2021).

    Article  Google Scholar 

  18. Schenone, M., Dancík, V., Wagner, B. K. & Clemons, P. A. Target identification and mechanism of action in chemical biology and drug discovery. Nat. Chem. Biol. 9, 232–40 (2013).

    Article  Google Scholar 

  19. Öztürk, H., Ozkirimli, E. & Özgür, A. WideDTA: prediction of drug-target binding affinity. Preprint at arXiv (2019).

  20. Zheng, S., Li, Y., Chen, S., Xu, J. & Yang, Y. Predicting drug-protein interaction using quasi-visual question answering system. Nat. Mach. Intell. 2, 134–140 (2020).

    Article  Google Scholar 

  21. Abbasi, K. et al. DeepCDA: deep cross-domain compound–protein affinity prediction through lstm and convolutional neural networks. Bioinformatics 36, 4633–4642 (2020).

    Article  Google Scholar 

  22. Kao, P.-Y., Kao, S.-M., Huang, N.-L. & Lin, Y.-C. Toward drug-target interaction prediction via ensemble modeling and transfer learning. In IEEE Int. Conf. on Bioinformatics and Biomedicine (BIBM) 2384–2391 (2021).

  23. Abbasi, K., Razzaghi, P., Poso, A., Ghanbari-Ara, S. & Masoudi-Nejad, A. Deep learning in drug target interaction prediction: current and future perspectives. Curr. Med. Chem. 28, 2100–2113 (2021).

    Article  Google Scholar 

  24. Kipf, T. & Welling, M. Semi-supervised classification with graph convolutional networks. In Int. Conf. on Learning Representations (ICLR, 2017).

  25. Yu, Z., Yu, J., Xiang, C., Fan, J. & Tao, D. Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29, 5947–5959 (2018).

    Article  Google Scholar 

  26. Kim, J. -H., Jun, J. & Zhang, B. -T. Bilinear attention networks. In Advances in Neural Information Processing Systems (NeurIPS, 2018).

  27. Long, M., Cao, Z., Wang, J. & Jordan, M. I. Conditional adversarial domain adaptation. In Advances in Neural Information Processing Systems (NeurIPS, 2018).

  28. Weininger, D. SMILES, a chemical language and information system. 1. introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988).

    Article  Google Scholar 

  29. Liu, T., Lin, Y., Wen, X., Jorissen, R. N. & Gilson, M. K. BindingDB: a web-accessible database of experimentally determined protein-ligand binding affinities. Nucleic Acids Res. 35, D198–D201 (2007).

  30. Zitnik, M., Sosič, R., Maheshwari, S. & Leskovec, J. BioSNAP datasets: Stanford biomedical network dataset collection. (2018).

  31. Liu, H., Sun, J., Guan, J., Zheng, J. & Zhou, S. Improving compound-protein interaction prediction by building up highly credible negative samples. Bioinformatics 31, i221–i229 (2015).

    Article  Google Scholar 

  32. Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010).

  33. Cao, D., Xu, Q. & Liang, Y. Propy: a tool to generate various modes of chou’s pseaac. Bioinformatics 29, 960–962 (2013).

  34. Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273–297 (1995).

    Article  MATH  Google Scholar 

  35. Ho, T. K. Random decision forests. In Int. Conf. on Document Analysis and Recognition, vol. 1, 278–282 (1995).

  36. Ganin, Y. et al. Domain-adversarial training of neural networks. In J. Mach. Learn. Res. 17, 1–35 (2016).

  37. Kazokaitė, J. et al. Engineered carbonic anhydrase vi-mimic enzyme switched the structure and affinities of inhibitors. Sci. Rep. 9, 1–17 (2019).

    Article  Google Scholar 

  38. Rai, G. et al. Discovery and optimization of potent, cell-active pyrazole-based inhibitors of lactate dehydrogenase (ldh). J. Med. Chem. 60, 9184–9204 (2017).

    Article  Google Scholar 

  39. Fenalti, G. et al. Molecular control of δ-opioid receptor signalling. Nature 506, 191–196 (2014).

    Article  Google Scholar 

  40. Berman, H. M. et al. The protein data bank. Nucleic Acids Res. 28, 235–242 (2000).

    Article  Google Scholar 

  41. Jumper, J. M. et al. Highly accurate protein structure prediction with alphafold. Nature 596, 583–589 (2021).

    Article  Google Scholar 

  42. Pan, S. J. & Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2010).

    Article  Google Scholar 

  43. Gong, B., Grauman, K. & Sha, F. Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In Int. Conf. on Machine Learning (ICML) 222-230 (2013).

  44. Huang, J., Smola, A., Gretton, A., Borgwardt, K. M. & Schölkopf, B. Correcting sample selection bias by unlabeled data. In Advances in Neural Information Processing Systems (NIPS) 601–608 (2006).

  45. Li, M. et al. DGL-LifeSci: an open-source toolkit for deep learning on graphs in life science. ACS Omega 6, 27233–27238 (2021).

  46. Song, L., Huang, J., Smola, A. & Fukumizu, K. Hilbert space embeddings of conditional distributions with applications to dynamical systems. In Int. Conf. on Machine Learning (ICML) 961–968 (2009).

  47. Song, L. & Dai, B. Robust low rank kernel embeddings of multivariate distributions. In Advances in Neural Information Processing Systems (NIPS) 3228–3236 (2013).

  48. Gilson, M. K. et al. BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res. 44, D1045–D1053 (2016).

    Article  Google Scholar 

  49. Bai, P. et al. Hierarchical clustering split for low-bias evaluation of drug-target interaction prediction. In IEEE Int. Conf. on Bioinformatics and Biomedicine (BIBM) 641–644 (2021).

  50. Wishart, D. S. et al. DrugBank: a knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res. 36, D901–D906 (2008).

    Article  Google Scholar 

  51. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS, 2019).

  52. Wang, M. et al. Deep graph library: a graph-centric, highly-performant package for graph neural networks. Preprint at arXiv (2019).

  53. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).

    MATH  MathSciNet  Google Scholar 

  54. Harris, C. R. et al. Array programming with numpy. Nature 585, 357–362 (2020).

    Article  Google Scholar 

  55. The pandas development team. pandas-dev/pandas: Pandas 1.2.4. Zenodo (2021).

  56. Landrum, G. et al. RDKit: open-source cheminformatics. (2006).

  57. Bai, P., Miljković, F., John, B. & Lu, H. Interpretable bilinear attention network with domain adaptation improves drug-target prediction. CodeOcean (2022).

  58. Bai, P., Miljković, F., John, B. & Lu, H. peizhenbai/drugban: v1.2.0. Zenodo (2022).

  59. Kim, J.-H. et al. Hadamard product for low-rank milinear pooling. In Int. Conf. on Learning Representations (ICLR, 2017).

Download references


We thank S. Zhou, X. Liu and L. Schöbs for their helpful suggestions and discussion on the work. P.B. is supported by a University of Sheffield Faculty of Engineering Research Scholarship (grant no. 169426530).

Author information

Authors and Affiliations



P.B., F.M., B.J. and H.L. conceived and designed the work. P.B. developed the models and performed the experiments under the guidance of B.J. and H.L. F.M. and P.B. analysed the data and conducted method comparisons. F.M. contributed to materials and the analysis tool. All authors contributed to writing the paper.

Corresponding author

Correspondence to Haiping Lu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks the anonymous reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Background Information; Discussion; Figs. 1–3; Tables 1–7.

Reporting Summary

Source data

Source Data Fig. 2

Statistical Source Data.

Source Data Fig. 3

Statistical Source Data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bai, P., Miljković, F., John, B. et al. Interpretable bilinear attention network with domain adaptation improves drug–target prediction. Nat Mach Intell 5, 126–136 (2023).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing: AI and Robotics