TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments
Open accessAbstract
Motivation: Identifying compound–protein interaction (CPI) is a crucial task in drug discovery and chemogenomics studies, and proteins without three-dimensional structure account for a large part of potential biological targets, which requires developing methods using only protein sequence information to predict CPI. However, sequence-based CPI models may face some specific pitfalls, including using inappropriate datasets, hidden ligand bias and splitting datasets inappropriately, resulting in overestimation of their prediction performance. Results: To address these issues, we here constructed new datasets specific for CPI prediction, proposed a novel transformer neural network named TransformerCPI, and introduced a more rigorous label reversal experiment to test whether a model learns true interaction features. TransformerCPI achieved much improved performance on the new experiments, and it can be deconvolved to highlight important interacting regions of protein sequences and compound atoms, which may contribute chemical biology studies with useful guidance for further ligand structural optimization. Availability and implementation: https://github.com/lifanchen-simm/transformerCPI.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Because ligand-receptor interactions are directed, they could be used to infer causal interactions of previously unknown ligand-receptor pairs.
“In fact, as ligand-receptor interactions are directed, they could be used to infer causal interactions of previously unknown ligand-receptor pairs [161, 163].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [161]
A cell neighborhood graph and a gene pair expression matrix allow classic GNNs to predict ligand-receptor interactions.
“For instance, a cell neighborhood graph and a gene pair expression matrix enable classic GNNs to predict ligand-receptor interactions [161].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [161]
Spatial transcriptomics data can be used to construct cell graphs, spatial gene expression graphs, gene co-expression networks, or molecular similarity graphs.
“As a result, spatial transcriptomics data can be used to construct cell graphs [161], spatial gene expression graphs [162], gene co-expression networks, or molecular similarity graphs [35].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [161]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · see citing works
Self-citationSemi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · see citing works
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · see citing works
Self-citationThe graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · see citing works
Applications of machine learning in drug discovery and development
Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/s41573-019-0024-5 · Cited by 3,228 · see citing works
DrugBank: a knowledgebase for drugs, drug actions and drug targets
Wishart, D. S., Knox, C., Guo, A. C., Cheng, D., Shrivastava, S., Tzur, D., Gautam, B., & Hassanali, M. (2007) · Nucleic Acids Research · doi:10.1093/nar/gkm958 · Cited by 2,852 · see citing works
Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking.
Mysinger, M. M., Carchia, M., Irwin, J. J., & Shoichet, B. K. (2012) · Journal of Medicinal Chemistry · doi:10.1021/jm300687e · Cited by 2,412 · see citing works
BindingDB: a web-accessible database of experimentally determined protein-ligand binding affinities
Liu, T., Lin, Y., Wen, X., Jorissen, R. N., & Gilson, M. K. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkl999 · Cited by 2,145 · see citing works
DeepDTA: deep drug–target binding affinity prediction
Öztürk, H., Özgür, A., & Özkırımlı, E. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty593 · Cited by 1,728 · see citing works
STITCH 5: augmenting protein–chemical interaction networks with tissue and affinity data
Szklarczyk, D., Santos, A., von Mering, C., Jensen, L. J., Peer Bork, B., & Kuhn, M. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv1277 · Cited by 1,702 · see citing works
Gilson, M. K., Liu, T., Baitaluk, M., Nicola, G., Hwang, L., & Chong, J. P. C. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv1072 · Cited by 1,632 · see citing works
On the Variance of the Adaptive Learning Rate and BeyondPreprint
Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03265 · Cited by 1,529 · see citing works
Self-citationPrediction of drug–target interaction networks from the integration of chemical and genomic spaces
Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W., & Kanehisa, M. I. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn162 · Cited by 1,148 · see citing works
Unified rational protein engineering with sequence-based deep representation learning
Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M., & Church, G. M. (2019) · Nature Methods · doi:10.1038/s41592-019-0598-1 · Cited by 1,131 · see citing works
Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
Schwaller, P., Laino, T., Gaudin, T., Bolgar, P., Hunter, C. A., Bekas, C., & Lee, A. A. (2019) · ACS Central Science · doi:10.1021/acscentsci.9b00576 · Cited by 1,078 · see citing works
Gaussian interaction profile kernels for predicting drug–target interaction
van Laarhoven, T., Nabuurs, S. B., & Marchiori, E. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr500 · Cited by 935 · see citing works
Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics
Asgari, E., & Mofrad, M. R. K. (2015) · PLoS ONE · doi:10.1371/journal.pone.0141287 · Cited by 817 · see citing works
Tsubaki, M., Tomii, K., & Sese, J. (2019) · Bioinformatics · doi:10.1093/bioinformatics/bty535 · Cited by 688 · see citing works
Lee, I., Keum, J., & Nam, H. (2019) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007129 · Cited by 671 · see citing works
Tang, J. P., Szwajda, A., Shakyawar, S. K., Xu, T., Hintsanen, P., Wennerberg, K., & Aittokallio, T. A. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci400709d · Cited by 662 · see citing works
SuperTarget and Matador: resources for exploring drug-target relationships
Gunther, S., Kuhn, M., Dunkel, M., Campillos, M., Senger, C., Petsalaki, E., Ahmed, J., Urdiales, E. G., Gewiess, A., Jensen, L. J., et al. (2007) · Nucleic Acids Research · doi:10.1093/nar/gkm862 · Cited by 647 · see citing works
Supervised prediction of drug–target interactions using bipartite local models
Kevin Bleakley, A., & Yamanishi, Y. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp433 · Cited by 631 · see citing works
Karimi, M., Wu, D. J., Wang, Z., & Shen, Y. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz111 · Cited by 536 · see citing works
He, T., Heidemeyer, M., Ban, F., Cherkasov, A. R., & Ester, M. (2017) · Journal of Cheminformatics · doi:10.1186/s13321-017-0209-z · Cited by 516 · see citing works
Lookahead Optimizer: k steps forward, 1 step backPreprint
Zhang, M. R., Lucas, J., Hinton, G., & Ba, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.08610 · Cited by 470 · see citing works
Gönen, M. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts360 · Cited by 383 · see citing works
Protein-ligand interaction prediction: an improved chemogenomics approach
Jacob, L., & Vert, J. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn409 · Cited by 382 · see citing works
Improving compound–protein interaction prediction by building up highly credible negative samples
Liu, H., Sun, J., Guan, J., Zheng, J., & Zhou, S. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv256 · Cited by 359 · see citing works
Chemogenomics: an emerging strategy for rapid target and drug discovery
Bredel, M., & Jacoby, E. (2004) · Nature Reviews Genetics · doi:10.1038/nrg1317 · Cited by 357 · see citing works
Sieg, J., Flachsenberg, F., & Rarey, M. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.8b00712 · Cited by 323 · see citing works
Learned protein embeddings for machine learning
Yang, K., Wu, Z., Bedbrook, C. N., & Arnold, F. H. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty178 · Cited by 316 · see citing works
Predicting drug–protein interaction using quasi-visual question answering system
Zheng, S., Li, Y., Chen, S., Xu, J., & Yang, Y. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0152-y · Cited by 310 · see citing works
Chen, L., Cruz, A., Ramsey, S., Dickson, C. J., Duca, J. S., Horn̆ák, V., Koes, D. R., & Kurtzman, T. (2019) · PLoS ONE · doi:10.1371/journal.pone.0220113 · Cited by 291 · see citing works
Self-citationPredicting drug-target interactions using restricted Boltzmann machines
Wang, Y., & Zeng, J. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt234 · Cited by 211 · see citing works
Boosting compound-protein interaction prediction by deep learning
Tian, K., Shao, M., Wang, Y., Guan, J., & Zhou, S. (2016) · Methods · doi:10.1016/j.ymeth.2016.06.024 · Cited by 183 · see citing works
WideDTA: prediction of drug-target binding affinityPreprint
Öztürk, H., Özkırımlı, E., & Özgür, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.04166 · Cited by 150 · see citing works
GLASS: a comprehensive database for experimentally validated GPCR-ligand associations
Chan, W. K. B., Zhang, H., Yang, J., Brender, J., Hur, J., Özgür, A., & Zhang, Y. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv302 · Cited by 148 · see citing works
Three pitfalls to avoid in machine learning.
Riley, P. (2019) · Nature · doi:10.1038/d41586-019-02307-y · Cited by 142 · see citing works
Cheng, F., Zhou, Y., Li, J., Li, W., Liu, G., & Tang, Y. (2012) · Molecular BioSystems · doi:10.1039/c2mb25110h · Cited by 114 · see citing works
GraphDTA: Predicting drug–target binding affinity with graph neural networksPreprint
Nguyen, T., Le, H., Quinn, T. P., Nguyen, T., Le, T. D., & Venkatesh, S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/684662 · Cited by 103 · see citing works
Deep learning with feature embedding for compound-protein interaction predictionPreprint
Wan, F., & Zeng, J. (2016) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/086033 · Cited by 93 · see citing works
DeepCPI: A Deep Learning-Based Framework for Large-Scale <i>in Silico</i> Drug Screening
Wan, F., Zhu, Y., Hu, H., Dai, A., Cai, X., Chen, L., Gong, H., Xia, T., Yang, D., Wang, M.-W., et al. (2019) · Genomics, Proteomics & Bioinformatics · doi:10.1016/j.gpb.2019.04.003 · Cited by 92 · see citing works
Self-citationDistributed Representations for Biological Sequence AnalysisPreprint
Kimothi, D., Soni, A., Biyani, P., & Hogan, J. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.05949 · Cited by 84 · see citing works
Wang, F., Liu, D., Wang, H., et al. (2011) · Journal of Chemical Information and Modeling · doi:10.1021/ci200264h · Cited by 80 · see citing works
CGBVS‐DNN: Prediction of Compound‐protein Interactions Based on Deep Learning
Hamanaka, M., Taneishi, K., Iwata, H., Ye, J., Pei, J., Hou, J., & Okuno, Y. (2016) · Molecular Informatics · doi:10.1002/minf.201600045 · Cited by 70 · see citing works
Predicting Protein Binding Affinity With Word Embeddings and Recurrent Neural NetworksPreprint
Mazzaferro, C. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/128223 · Cited by 16 · see citing works
Flagged first, then by citations
Research works printed but not linked: 7
- Dai,Z. et al. (2019) Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978-2988. Association for Computational Linguistics. Florence, Italy.
- Dauphin,Y. et al. (2016) Language modeling with gated convolutional net- works. In Proceedings of the 34th International Conference on Machine Learning, JMLR.org, Sydney, NSW, Australia, pp. 933-941.
- Devlin,J. et al. (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171-4186. Association for Computational Linguistics, Minneapolis, Minnesota.
- Gao,K. et al. (2018) Interpretable drug target prediction using deep neural rep- resentation. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, AAAI Press, Stockholm, Sweden. pp. 3371-3377.
- Qiu,X. et al. (2020) Pre-trained Models for Natural Language Processing: A Survey. In, arXiv e-prints. 2020. p. arXiv:2003.08271. · arXiv
- Vaswani,A. et al. (2017) Attention Is All You Need. In Advances in Neural Information Processing Systems, pp. 6000-6010.
- Yang,Z. et al. (2019) XLNet: Generalized Autoregressive Pretraining for Language Understanding. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28-August 2, 2019, Volume 1: Long Papers, pp. 2978-2988. Association for Computational Linguistics. Florence, Italy.
Cited by
Sorted by citations
Graph representation learning in biomedicine and healthcare
Li, M. M., Huang, K., & Zitnik, M. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00942-x · Cited by 294 · see citing works
AlphaFold2-aware protein–DNA binding site prediction using graph transformer
Yuan, Q., Chen, S., Rao, J., Zheng, S., Zhao, H., & Yang, Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab564 · Cited by 137 · see citing works
Dai, Y., Tan, X., Wang, H., Ma, G., Xiong, Y., & Qiu, X. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.109163
Self-citation
- Authors
- Chen, L., Tan, X., Wang, D., Zhong, F., Liu, X., Yang, T., Luo, X., Chen, K., Jiang, H., & Zheng, M.
- Affiliations
- Chinese Academy of Sciences (CN)
- Corresponding author
- Jiang, Hualiang
- Zheng, Mingyue
- ORCID
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-05-19
- Volume
- 36
- Issue
- 16
- Pages
- 4406-4414
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W3028589594
- Cited by
- 607
- References
- 46
- Citations by year
- 2026: 139 · 2025: 159 · 2024: 132 · 2023: 86 · 2022: 61 · 2021: 25 · 2020: 4
- FWCI
- 21.86
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Bioinformatics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (81773634)
- National Science & Technology Major
- Key New Drug Creation and Manufacturing Program (2018ZX09711002)
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDA12050201)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- compound-protein interaction prediction, sequence-based deep learning, self-attention, dataset construction, protein sequences, compound structure, chemogenomics, drug discovery
- MeSH terms
- Deep Learning, Amino Acid Sequence, Ligands, Proteins, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
