FastDTI: Drug-Target Interaction Prediction using Multimodality and Transformers


  • Mathijs Boezer Eindhoven University of Technology
  • Maryam Tavakol Eindhoven University of Technology
  • Zahra Sajadi Eindhoven University of Technology



Drug-target interaction, Deep learning, Transformers, Graph neural networks, Multimodality


Recent advances in machine learning have proved effective in the application of drug discovery by predicting the drugs that are likely to interact with a protein target of a certain disease, leading to prioritizing drug development and re-purposing efforts. State-of-the-art techniques in Drug-Target Interaction (DTI) prediction are often computationally expensive and can only be trained on small specialized datasets. In this paper, we propose a novel architecture, called FastDTI, utilizing pretrained transformers and graph neural networks in a self-supervised manner on large-scale (unlabeled) data, which additionally allows for embedding of multimodal input representations, for both drug and protein properties. Extensive empirical study demonstrates that our approach outperforms state-of-the-art DTI methods on the KIBA benchmark dataset, while greatly improving the computational complexity of training, about 200 times faster, leading to excellent performance results.


K. Abbasi, P. Razzaghi, A. Poso, S. GhanbariAra, and A. Masoudi-Nejad. Deep learning in drug target interaction prediction: Current and future perspectives. Current Medicinal Chemistry, 28(11):2100–2113, 2021. doi: 10.2174/0929867327666200907141016.

M. Abdel-Basset, H. Hawash, M. Elhoseny, R. K. Chakrabortty, and M. Ryan. DeepHDTA: deep learning for predicting drug-target interactions: a case study of covid-19 drug repurposing. Ieee Access, 8:170433–170451, 2020. doi: 10.1109/ACCESS.2020.3024238.

T. Ashburn and K. B. Thor. Drug repositioning: identifying and developing new uses for existing drugs. Nature reviews Drug discovery, 3(8):673–683, 2004. doi: 10.1038/nrd1468.

L. Chen, X. Tan, D. Wang, F. Zhong, X. Liu, T. Yang, X. Luo, K. Chen, H. Jiang, and M. Zheng. Transformercpi: improving compound–protein interaction prediction by sequence-based deep learning with selfattention mechanism and label reversal experiments. Bioinformatics, 36(16):4406–4414, 2020. doi: 10.1093/bioinformatics/btaa524.

S. Chithrananda, G. Grand, and B. Ramsundar. Chemberta: Large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885, 2020.

J. Devlin, M. Chang, K. Lee, and K. Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.

A. Dhakal, C. McKay, J. J. Tanner, and J. Cheng. Artificial intelligence in the prediction of protein–ligand interactions: recent advances and future directions. Briefings in Bioinformatics, 23(1):bbab476, 2022. doi: 10. 1093/bib/bbab476.

A. Elnaggar, M. Heinzinger, C. Dallago, G. Rehawi, Y. Wang, L. Jones, T. Gibbs, T. Feher, et al. ProtTrans: towards cracking the language of life’s code through selfsupervised learning. bioRxiv, pages 2020–07, 2021. doi: 10.1101/2020.07.12.199554.

A. Ezzat. Challenges and solutions in drugtarget interaction prediction. PhD thesis, 2018.

T. He, M. Heidemeyer, F. Ban, A. Cherkasov, and M. Ester. Simboost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines. Journal of cheminformatics, 9(1):1–14, 2017. doi: 10.1186/s13321-017-0209-z.

K. Koyama, K. Kamiya, and K. Shimada. Cross attention DTI: drug-target interaction prediction with cross attention module in the blind evaluation setup. 2020.

Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019.

H. Lodish, A. Berk, C. A. Kaiser, C. Kaiser, M. Krieger, M. P. Scott, A. Bretscher, H. Ploegh, P. Matsudaira, et al. Molecular cell biology. Macmillan, 2008.

G. M. Morris and M. Lim-Wilby. Molecular docking. In Molecular modeling of proteins, pages 365–382. Springer, 2008. doi: 10.1007/ 978-1-59745-177-2 19.

T. Nguyen, H. Le, T. Quinn, T. Nguyen, T. D. Le, and S. Venkatesh. GraphDTA: Predicting 7 drug–target binding affinity with graph neural networks. Bioinformatics, 37(8):1140–1147, 2021. doi: 10.1093/bioinformatics/btaa921.

H. Ozturk, A. Ozgur, and E. Ozkirimli. Deep-DTA: deep drug–target binding affinity prediction. Bioinformatics, 34(17):i821–i829, 2018. doi: 10.1093/bioinformatics/bty593.

T. Pahikkala, A. Airola, S. Pietila, S. Shakyawar, A. Szwajda, J. Tang, and T. Aittokallio. Toward more realistic drug– target interaction predictions. Briefings in bioinformatics, 16(2):325–337, 2015. doi: 10.1093/bib/bbu010.

J. Piret and G. Boivin. Pandemics throughout history. Frontiers in microbiology, 11:631736, 2021. doi: 10.3389/fmicb.2020.631736.

P. Pratim Roy, S. Paul, I. Mitra, and K. Roy. On two novel parameters for validation of predictive qsar models. Molecules, 14(5):1660– 1701, 2009. doi: 10.3390/molecules14051660.

Y. Rong, Y. Bian, T. Xu, W. Xie, Y. Wei, W. Huang, and J. Huang. Self-supervised graph transformer on large-scale molecular data. Advances in Neural Information Processing Systems, 33:12559–12571, 2020.

S. Z. Sajadi, M. A. Zare Chahooki, S. Gharaghani, and K. Abbasi. Autodti++: deep unsupervised learning for dti prediction by autoencoders. BMC bioinformatics, 22(1): 1–19, 2021. doi: 10.1186/s12859-021-04127-2.

S. Z. Sajadi, M. A. Zare Chahooki, M. Tavakol, and S. Gharaghani. Matrix factorization with denoising autoencoders for prediction of drug– target interactions. Molecular Diversity, pages 1–11, 2022. doi: 10.1007/s11030-022-10492-8.

D. Szklarczyk, A. Santos, C. Von Mering, L. J. Jensen, P. Bork, and M. Kuhn. Stitch 5: augmenting protein–chemical interaction networks with tissue and affinity data. Nucleic acids research, 44(D1):D380–D384, 2016. doi: 10.1093/nar/gkv1277.

J. Tang, A. Szwajda, S. Shakyawar, T. Xu, P. Hintsanen, K. Wennerberg, and T. Aittokallio. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis. Journal of Chemical Information and Modeling, 54(3):735–743, 2014. doi: 10.1021/ci400709d.

X. Wang, H. Ji, C. Shi, B. Wang, Y. Ye, P. Cui, and P. S. Yu. Heterogeneous graph attention network. In The world wide web conference, pages 2022–2032, 2019. doi: 10.1145/3308558. 3313562.

D. Weininger. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences, 28(1):31–36, 1988. doi: 10.1021/ci00057a005.

M. Wen, Z. Zhang, S. Niu, H. Sha, R. Yang, Y. Yun, and H. Lu. Deep-learning-based drug– target interaction prediction. Journal of proteome research, 16(4):1401–1409, 2017. doi: 10.1021/acs.jproteome.6b00618.

K. Wuthrich. Protein structure determination in solution by nmr spectroscopy. Journal of Biological Chemistry, 265(36):22059–22062, 1990. doi: 10.1016/S0021-9258(18)45665-7.

Z. Yang, W. Zhong, L. Zhao, and C. Y.- C. Chen. Ml-dti: Mutual learning mechanism for interpretable drug–target interaction prediction. The Journal of Physical Chemistry Letters, 12(17):4247–4261, 2021. doi: 10.1021/acs.jpclett.1c00867.

W. Yuan, G. Chen, and C. Y.-C. Chen. Fusiondta: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction. Briefings in Bioinformatics, 23(1):bbab506, 2022. doi: 10.1093/ bib/bbab506.

L. Zhang, J. Tan, D. Han, and H. Zhu. From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug discovery today, 22(11):1680–1685, 2017. doi: 10.1016/j.drudis.2017.08.010.

P. Zhang, Z. Wei, C. Che, and B. Jin. Deepmgt-dti: Transformer network incorporating multilayer graph information for drug– target interaction prediction. Computers in Biology and Medicine, page 105214, 2022. doi: 10.1016/j.compbiomed.2022.105214.