CoChat
Sign Up
PreprintCited by 1Computational Drug Discovery MethodsMachine Learning in BioinformaticsProtein Interaction Studies and Fluorescence Analysis

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

GenSPARC: Generalized Structure- and Property-Aware Representations of Language Models for Compound-Protein Interaction Prediction

Open access
Tomita, Atsuhiro, Zhang, Yiming, Takemoto, Mizuki, Ishitani, Ryuichiro·2025·Communications Chemistry
DOI 10.21203/rs.3.rs-6326235/v1PMC PMC12823658

Preprint — published as 10.1038/s42004-025-01844-0 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Compound-protein interaction (CPI) prediction plays a crucial role in drug discovery by aiding the identification of binding and affinities between small molecules and proteins. Current deep learning models rely heavily on sequence-based representations and suffer from a lack of labeled data, which restricts their accuracy and generalizability. To overcome these challenges, we propose GenSPARC ( Gen eralized S tructure and P roperty A ware R epresentation for C PI prediction), a deep learning model that leverages structure-aware protein representations derived from AlphaFold2 predictions and Foldseek’s 3D interaction alphabet. Compound features were extracted using graph convolutional networks and a pretrained chemical language model, thereby ensuring comprehensive multimodal representation. A novel attention mechanism further enhanced interaction modeling by capturing intricate binding patterns. GenSPARC was validated successfully with multiple CPI benchmark datasets, demonstrating strong generalizability across challenging data splits and competitive results in virtual screening tasks. Therefore, GenSPARC will substantially advance artificial intelligence-driven drug discovery.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-6326235/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 56

  1. Bohacek RS, McMartin C, Guida WC (1996) The art and practice of structure-based drug design: a molecular modeling perspective. Med Res Rev 16:3–50 · DOI
  2. Torng W, Altman RB (2019) Graph convolutional neural networks for predicting drug-target interactions. J Chem Inf Model 59:4131–4149 · DOI · Paper page
  3. Gao KY et al in IJCAI 3371–3377
  4. Jiang M et al (2020) Drug–target affinity prediction using graph neural network and contact maps. RSC Adv 10:20701–20712 · DOI · Paper page
  5. Tsubaki M, Tomii K, Sese J (2019) Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics 35:309–318 · DOI · Paper page
  6. Wu L et al in Proceedings of the AAAI Conference on Artificial Intelligence. 310–319
  7. Trott O, Olson AJ (2010) AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem 31:455–461 · DOI · Paper page
  8. Verdonk ML, Cole JC, Hartshorn MJ, Murray CW, Taylor RD (2003) Improved protein–ligand docking using GOLD. Proteins Struct Funct Bioinform 52:609–623 · DOI
  9. Holcomb M, Chang YT, Goodsell DS, Forli S (2023) Evaluation of AlphaFold2 structures as docking targets. Protein Sci 32:e4530 · DOI
  10. Lee S et al (2023) Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure prediction. Comput Struct Biotechnol J 21:158–167. https://doi.org/https://doi.org/10.1016/j.csbj.2022.11.057 · DOI
  11. Karimi M, Wu D, Wang Z, Shen Y (2020) Explainable deep relational networks for predicting compound–protein affinities and contacts. J Chem Inf Model 61:46–66 · DOI · Paper page
  12. Li S et al in International Conference on Research in Computational Molecular Biology. 259–260 (Springer)
  13. Nguyen T et al (2021) GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics 37:1140–1147 · DOI
  14. Öztürk H, Özgür A, Ozkirimli E (2018) DeepDTA: deep drug–target binding affinity prediction. Bioinformatics 34:i821–i829 · DOI
  15. Lee I, Keum J, Nam H (2019) DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput Biol 15:e1007129 · DOI
  16. Karimi M, Wu D, Wang Z, Shen Y (2019) DeepAffinity: interpretable deep learning of compound–protein affinity through unified recurrent and convolutional neural networks. Bioinformatics 35:3329–3338 · DOI
  17. Chen L et al (2020) TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36:4406–4414 · DOI · Paper page
  18. Zhao Q, Zhao H, Zheng K, Wang J (2022) HyperAttentionDTI: improving drug–protein interaction prediction by sequence-based deep learning with attention mechanism. Bioinformatics 38:655–662 · DOI
  19. Nguyen N-Q, Jang G, Kim H, Kang J (2023) Perceiver CPI: a nested cross-attention network for compound–protein interaction prediction. Bioinformatics 39:btac731 · DOI · Paper page
  20. You Y, Shen Y (2022) Cross-modality and self-supervised protein embedding for compound–protein affinity and contact prediction. Bioinformatics 38:ii68–ii74 · DOI · Paper page
  21. Davis MI et al (2011) Comprehensive analysis of kinase inhibitor selectivity. Nat Biotechnol 29:1046–1051 · DOI · Paper page
  22. Tang J et al (2014) Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis. J Chem Inf Model 54:735–743 · DOI
  23. Metz JT et al (2011) Navigating the kinome. Nat Chem Biol 7:200–202 · DOI
  24. Mistry J et al (2021) Pfam: The protein families database in 2021. Nucleic Acids Res 49:D412–D419. https://doi.org/doi.org/10.1093/nar/gkaa913 · DOI · Paper page
  25. Hillisch A, Hilgenfeld R (2003) The role of protein 3D-structures in the drug discovery process. Mod methods drug discovery, 157–181 · DOI
  26. Wang H (2024) Prediction of protein–ligand binding affinity via deep learning models. Brief Bioinform 25:bbae081 · DOI
  27. Su J et al (2001) Saprot: Protein language modeling with structure-aware vocabulary. bioRxiv, 2023.2010. 560349 (2023)
  28. Chang J, Ye JC (2024) Bidirectional generation of structure and properties through a single molecular foundation model. Nat Commun 15:2323 · DOI
  29. Van Kempen M et al (2024) Fast and accurate protein structure search with Foldseek. Nat Biotechnol 42:243–246 · DOI · Paper page
  30. Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 · arXiv
  31. Vaswani A et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30
  32. Halgren TA et al (2004) Glide: a new approach for rapid, accurate docking and scoring. 2. Enrichment factors in database screening. J Med Chem 47:1750–1759 · DOI
  33. Durrant JD, McCammon JA (2011) NNScore 2.0: a neural-network receptor–ligand scoring function. J Chem Inf Model 51:2897–2903 · DOI
  34. Ballester PJ, Mitchell JB (2010) A machine learning approach to predicting protein–ligand binding affinity with applications to molecular docking. Bioinformatics 26:1169–1175 · DOI
  35. Zheng L, Fan J, Mu Y (2019) Onionnet: a multiple-layer intermolecular-contact-based convolutional neural network for protein–ligand binding affinity prediction. ACS omega 4:15956–15965 · DOI
  36. Zhang X et al (2023) Planet: a multi-objective graph neural network model for protein–ligand binding affinity prediction. J Chem Inf Model 64:2205–2220 · DOI
  37. Gao B et al (2024) Drugclip: Contrasive protein-molecule representation learning for virtual screening. Adv Neural Inf Process Syst 36
  38. Ragoza M, Hochuli J, Idrobo E, Sunseri J, Koes DR (2017) Protein–ligand scoring with convolutional neural networks. J Chem Inf Model 57:942–957 · DOI
  39. Gao Z, Tan C, Wu L, Li SZ, Cosp (2022) Co-supervised pretraining of pocket and ligand. arXiv preprint arXiv:2206.12241 · arXiv
  40. Zheng S, Li Y, Chen S, Xu J, Yang Y (2020) Predicting drug–protein interaction using quasi-visual question answering system. Nat Mach Intell 2:134–140 · DOI
  41. Yazdani-Jahromi M et al (2022) AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification. Brief Bioinform 23:bbac272 · DOI
  42. Truchon J-F, Bayly CI (2007) Evaluating virtual screening methods: good and bad metrics for the early recognition problem. J Chem Inf Model 47:488–508 · DOI
  43. Zhao W, Hevener KE, White SW, Lee RE, Boyett J (2009) M. A statistical framework to evaluate virtual screening. BMC Bioinformatics 10:1–13 · DOI
  44. Pearlman DA, Charifson PS (2001) Improved scoring of ligand – protein interactions using OWFEG free energy grids. J Med Chem 44:502–511 · DOI
  45. Jain AN, Nicholls A (2008) Recommendations for evaluation of computational methods. J Comput Aided Mol Des 22:133–139 · DOI
  46. Nicholls A (2008) What do we know and when do we know it? J Comput Aided Mol Des 22:239–255 · DOI
  47. Lin Z et al (2023) Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379:1123–1130. https://doi.org/10.1126/science.ade2574 · DOI · Paper page
  48. Liu Z et al (2015) PDB-wide collection of binding data: current status of the PDBbind database. Bioinformatics 31:405–412 · DOI
  49. Liu T, Lin Y, Wen X, Jorissen RN, Gilson MK (2007) BindingDB: a web-accessible database of experimentally determined protein–ligand binding affinities. Nucleic Acids Res 35:D198–D201 · DOI
  50. Camacho C et al (2009) BLAST+: architecture and applications. BMC Bioinformatics 10:1–9 · DOI · Paper page
  51. Mysinger MM, Carchia M, Irwin JJ, Shoichet BK (2012) Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J Med Chem 55:6582–6594 · DOI · Paper page
  52. Scardapane S, Comminiello D, Hussain A, Uncini A (2017) Group sparse regularization for deep neural networks. Neurocomputing 241:81–89 · DOI
  53. Tibshirani R, Saunders M, Rosset S, Zhu J, Knight K (2005) Sparsity and smoothness via the fused lasso. J Royal Stat Soc Ser B: Stat Methodol 67:91–108 · DOI
  54. Wang R, Fang X, Lu Y, Yang C-Y, Wang S (2005) The PDBbind Database: Methodologies and Updates. J Med Chem 48:4111–4119. https://doi.org/10.1021/jm048957q · DOI · Paper page
  55. Radford A et al in International conference on machine learning. 8748–8763 (PMLR)
  56. Lyu J et al (2019) Ultra-large library docking for discovering new chemotypes. Nature 566:224–229 · DOI · Paper page

Metadata

Authors
Tomita, A., Zhang, Y., Takemoto, M., & Ishitani, R.
Affiliations
  • Preferred Networks (Japan) (JP)
  • Institute of Science Tokyo (JP)
Corresponding author
Tomita, Atsuhiro
ORCID
Venue
Communications Chemistry
Publisher
Springer Science and Business Media LLC
Published
2025-05-08
Volume
9
Issue
1
Pages
37-37
ISSN
2399-3669 (ISSN-L)
DOI
10.21203/rs.3.rs-6326235/v1
PMC
PMC12823658
OpenAlex
W4417479088
Cited by
1
References
1
Citations by year
2026: 1
FWCI
0.52
Type
journal article
Language
en
Open access
Licence
Locations
  • Communications Chemistry (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › 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 › Protein Interaction Studies and Fluorescence Analysis
Keywords
compound-protein interaction prediction, protein-ligand binding affinity, chemical language models, AlphaFold2, graph convolutional networks, multimodal representation, attention mechanism, virtual screening, drug discovery

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