Enhancing generalizability and performance in drug–target interaction identification by integrating pharmacophore and pre-trained models
Open accessAbstract
Motivation: In drug discovery, it is crucial to assess the drug–target binding affinity (DTA). Although molecular docking is widely used, computational efficiency limits its application in large-scale virtual screening. Deep learning-based methods learn virtual scoring functions from labeled datasets and can quickly predict affinity. However, there are three limitations. First, existing methods only consider the atom-bond graph or one-dimensional sequence representations of compounds, ignoring the information about functional groups (pharmacophores) with specific biological activities. Second, relying on limited labeled datasets fails to learn comprehensive embedding representations of compounds and proteins, resulting in poor generalization performance in complex scenarios. Third, existing feature fusion methods cannot adequately capture contextual interaction information. Results: Therefore, we propose a novel DTA prediction method named HeteroDTA. Specifically, a multi-view compound feature extraction module is constructed to model the atom–bond graph and pharmacophore graph. The residue concat graph and protein sequence are also utilized to model protein structure and function. Moreover, to enhance the generalization capability and reduce the dependence on task-specific labeled data, pre-trained models are utilized to initialize the atomic features of the compounds and the embedding representations of the protein sequence. A context-aware nonlinear feature fusion method is also proposed to learn interaction patterns between compounds and proteins. Experimental results on public benchmark datasets show that HeteroDTA significantly outperforms existing methods. In addition, HeteroDTA shows excellent generalization performance in cold-start experiments and superiority in the representation learning ability of drug–target pairs. Finally, the effectiveness of HeteroDTA is demonstrated in a real-world drug discovery study. Availability and implementation: The source code and data are available at https://github.com/daydayupzzl/HeteroDTA.
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?
Various computational models for target prediction have been developed, leading to notable improvements in predictive accuracy and efficiency.
“To this end, various computational models for target prediction have been developed, leading to notable improvements in predictive accuracy and efficiency38–40.”
From Harnessing artificial intelligence to identify Bufalin as a molecular glue degrader of estrogen receptor alpha (2025) · cites this paper as [38]
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
No references could be resolved yet.
Research works printed but not linked: 20
- Abbasi K, Razzaghi P, Poso A et al DeepCDA: deep cross-domain compound-protein affinity prediction through LSTM and convolutional neural networks. Bioinformatics 2020; 36: 4633– 42. 10.1093/bioinformatics/btaa544 32462178 · DOI
- Choudhury C, Sastry GN. Pharmacophore Modelling and Screening: Concepts, Recent Developments and Applications in Rational Drug Design. Cham: Springer International Publishing, 2019, 25– 53. 10.1007/978-3-030-05282-9_2 · DOI
- Dai Y, Gieseke F, Oehmcke S et al Attentional feature fusion. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021, 3559–3568. 10.1109/WACV48630.2021.00360 · DOI · Paper page
- Davis MI, Hunt JP, Herrgard S et al Comprehensive analysis of kinase inhibitor selectivity. Nat Biotechnol 2011; 29: 1046– 51. 10.1038/nbt.1990 22037378 · DOI · Paper page
- Fang X, Liu L, Lei J et al Geometry-enhanced molecular representation learning for property prediction. Nat Mach Intell 2022; 4: 127– 34.
- He T, Heidemeyer M, Ban F et al Simboost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines. J Cheminform 2017; 9: 24. 29086119 PMC5395521
- Hossain M, Habib I, Singha K et al FDA-approved heterocyclic molecules for cancer treatment: synthesis, dosage, mechanism of action and their adverse effect. Heliyon 2023; 10: e23172. 38163206 PMC10755292
- Hosseini M, Chen W, Xiao D et al Computational molecular docking and virtual screening revealed promising SARS-CoV-2 drugs. Precis Clin Med 2021; 4: 1– 16. 10.1093/pcmedi/pbab001 33842834 PMC7928605 · DOI
- Jiang M, Wang S, Zhang S et al Sequence-based drug–target affinity prediction using weighted graph neural networks. BMC Genomics 2022; 23: 449. 10.1186/s12864-022-08648-9 35715739 PMC9205061 · DOI
- Landrum GA. Rdkit: open-source cheminformatics. release 2014.03.1. 2014. https://api.semanticscholar.org/CorpusID:61633255
- Li J, Liu G, Zhen Z et al Molecular docking for ligand–receptor binding process based on heterogeneous computing. Sci Program 2022; 2022: 1.
- Liao J, Chen H, Wei L et al GSAML-DTA: an interpretable drug–target binding affinity prediction model based on graph neural networks with self-attention mechanism and mutual information. Comput Biol Med 2022; 150: 106145. 10.1016/j.compbiomed.2022.106145 37859276 · DOI
- Liu H, Sun J, Guan J et al Improving compound–protein interaction prediction by building up highly credible negative samples. Bioinformatics 2015; 31: i221– 9. 10.1093/bioinformatics/btv256 26072486 PMC4765858 · DOI
- Maslehat S, Sardari S, Ganji M. Frequency and importance of six functional groups that play a role in drug discovery. Biosci Biotech Res Asia 2018; 15: 541– 8. 10.13005/bbra/2659 · DOI
- Nguyen T, Le H, Quinn TP et al GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics 2020; 37: 1140– 7. 10.1093/bioinformatics/btaa921 33119053 · DOI
- Öztürk H, Özgür A, Ozkirimli E. DeepDTA: deep drug–target binding affinity prediction. Bioinformatics 2018; 34: i821– 9. 10.1093/bioinformatics/bty593 30423097 PMC6129291 · DOI
- Pahikkala T, Airola A, Pietilä S et al Toward more realistic drug–target interaction predictions. Brief Bioinform 2014; 16: 325– 37. 10.1093/bib/bbu010 24723570 PMC4364066 · DOI
- Rives A, Meier J, Sercu T et al Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci U S A 2021; 118: e2016239118. 33876751 PMC8053943
- Sadybekov AV, Katritch V. Computational approaches streamlining drug discovery. Nature 2023; 616: 673– 85. 37100941
- Tang J, Szwajda A, Shakyawar S et al Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis. J Chem Inf Model 2014; 54: 735– 43. 10.1021/ci400709d 24521231 · DOI
Cited by
Sorted by citations
Jiang, S., Liu, K., Jiang, T., Li, H., Wei, X., Wan, X., Zhong, C., Gong, R., Chen, Z., Zou, C., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-62288-7 · Cited by 23 · see citing works
- Authors
- Zhang, Z., He, X., Long, D., Luo, G., & Chen, S.
- Affiliations
- Henan University (CN)
- Department of Urology, Ji’an Third People’s Hospital , Ji’an, Jiangxi Province 343000, China
- Nanchang University (CN)
- Corresponding author
- Chen, Shengbo
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-06-28
- Volume
- 40
- Issue
- Supplement_1
- Pages
- i539-i547
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC11211825
- OpenAlex
- W4400127628
- Cited by
- 8
- References
- 0
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 1
- FWCI
- 1.69
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- High-level and Urgently Needed Overseas Talent Programs of Jiangxi Province (20232BCJ25026)
- National Natural Science Foundation of China (62102133)
- Kaifeng Major Science and Technology (21ZD011)
- Ji’an Finance and Science Foundation (20211085454, 20222151746, 20222151704)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Degradation and Inhibitors
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Keywords
- drug-target interaction prediction, drug binding affinity, pharmacophore, pre-trained models, feature fusion, virtual screening, drug discovery, protein sequence embeddings
- MeSH terms
- Deep Learning, Pharmacophore, Proteins, Drug Discovery, Molecular Docking Simulation
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
