Skip to main content
SpringerLink
Log in

GPCRLigNet: rapid screening for GPCR active ligands using machine learning

  • Published:
Journal of Computer-Aided Molecular Design Aims and scope Submit manuscript

Abstract

Molecules with bioactivity towards G protein-coupled receptors represent a subset of the vast space of small drug-like molecules. Here, we compare machine learning models, including dilated graph convolutional networks, that conduct binary classification to quickly identify molecules with activity towards G protein-coupled receptors. The models are trained and validated using a large set of over 600,000 active, inactive, and decoy compounds. The best performing machine learning model, dubbed GPCRLigNet, was a surprisingly simple feedforward dense neural network mapping from Morgan fingerprints to activity. Incorporation of GPCRLigNet into a high-throughput virtual screening workflow is demonstrated with molecular docking towards a particular G protein-coupled receptor, the pituitary adenylate cyclase-activating polypeptide receptor type 1. Through rigorous comparison of docking scores for molecules selected with and without using GPCRLigNet, we demonstrate an enrichment of potentially potent molecules using GPCRLigNet. This work provides a proof of principle that GPCRLigNet can effectively hone the chemical search space towards ligands with G protein-coupled receptor activity.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data and Software availability

The Python scripts for generating the training and validation datasets, building, and training machine learning models, and evaluating them are all available on GitHub https://github.com/jrem-chem/GPCRLigNet.git. In addition, the datasets themselves and indexes used for training and validation are provided along with the data and Python scripts to produce the figures in the paper.

References

  1. Sriram K, Insel PAG Protein-Coupled Receptors as Targets for Approved Drugs: How Many Targets and How Many Drugs?Mol Pharmacol2018, 93 (4),251. https://doi.org/10.1124/mol.117.111062

  2. Kratochwil NA, Malherbe P, Lindemann L, Ebeling M, Hoener MC, Mühlemann A, Porter RHP, Stahl M, Gerber PR An Automated System for the Analysis of G Protein-Coupled Receptor Transmembrane Binding Pockets: Alignment, Receptor-Based Pharmacophores, and Their Application.J. Chem. Inf. Model2005, 45 (5),1324–1336. https://doi.org/10.1021/ci050221u

  3. Porter HP, Steward R, Kolczewski L, Panousis SG, Narquizian C, Hertel R, Grether C, Dehmlow U, Winnig H, Slack MP, Kratochwil JA, Malherbe N, Martin PE, Guba R, Green WG, Christ LD, Lindemann A, Hoener LC, Gatti-McArthur M S. G Protein-Coupled Receptor Transmembrane Binding Pockets and Their Applications in GPCR Research and Drug Discovery: A Survey.Current Topics in Medicinal Chemistry2011, 11 (15),1902–1924. https://doi.org/10.2174/156802611796391267

  4. Mckay K, Hamilton NB, Remington JM, Schneebeli ST, Li J (2022) Essential Dynamics Ensemble Docking for Structure-Based GPCR Drug Discovery. Front. Mol. Bioscihttps://doi.org/fmolb.879212

  5. Balakin KV, Tkachenko SE, Lang SA, Okun I, Ivashchenko AA, Savchuk NP Property-Based Design of GPCR-Targeted Library.J. Chem. Inf. Comput. Sci2002, 42 (6),1332–1342. https://doi.org/10.1021/ci025538y

  6. Balakin KV, Lang SA, Skorenko AV, Tkachenko SE, Ivashchenko AA, Savchuk NP Structure-Based versus Property-Based Approaches in the Design of G-Protein-Coupled Receptor-Targeted Libraries.J. Chem. Inf. Comput. Sci2003, 43 (5),1553–1562. https://doi.org/10.1021/ci034114g

  7. von Korff M, Steger M GPCR-Tailored Pharmacophore Pattern Recognition of Small Molecular Ligands.J. Chem. Inf. Comput. Sci2004, 44 (3),1137–1147. https://doi.org/10.1021/ci0303013

  8. Lamb ML, Bradley EK, Beaton G, Bondy SS, Castellino AJ, Gibbons PA, Suto MJ, Grootenhuis PD J. Design of a Gene Family Screening Library Targeting G-Protein Coupled Receptors.Journal of Molecular Graphics and Modelling2004, 23 (1),15–21. https://doi.org/10.1016/j.jmgm.2004.03.001

  9. Givehchi A, Schneider G Multi-Space Classification for Predicting GPCR-Ligands.Molecular Diversity2005, 9 (4),371–383. https://doi.org/10.1007/s11030-005-6293-4

  10. Kelemen ÁA, Ferenczy GG, Keserű GM A Desirability Function-Based Scoring Scheme for Selecting Fragment-like Class A Aminergic GPCR Ligands.Journal of Computer-Aided Molecular Design2015, 29 (1),59–66. https://doi.org/10.1007/s10822-014-9804-5

  11. van der Horst E, Okuno Y, Bender A, IJzerman AP Substructure Mining of GPCR Ligands Reveals Activity-Class Specific Functional Groups in an Unbiased Manner.J. Chem. Inf. Model2009, 49 (2),348–360. https://doi.org/10.1021/ci8003896

  12. Seo S, Choi J, Ahn SK, Kim KW, Kim J, Choi J, Kim J, Ahn J Prediction of GPCR-Ligand Binding Using Machine Learning Algorithms. Comput Math Methods Med 2018, 2018, 6565241–6565241. https://doi.org/10.1155/2018/6565241

  13. Raschka S, Kaufman B Machine Learning and AI-Based Approaches for Bioactive Ligand Discovery and GPCR-Ligand Recognition.Methods2020, 180,89–110. https://doi.org/10.1016/j.ymeth.2020.06.016

  14. Chan WKB, Zhang H, Yang J, Brender JR, Hur J, Özgür A, Zhang YGLASS A Comprehensive Database for Experimentally Validated GPCR-Ligand Associations.Bioinformatics2015, 31 (18),3035–3042. https://doi.org/10.1093/bioinformatics/btv302

  15. Mysinger MM, Carchia M, Irwin JJ, Shoichet BK Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking.J. Med. Chem2012, 55 (14),6582–6594. https://doi.org/10.1021/jm300687e

  16. NCI/CADD, group. Cactus Web Server (2021) https://cactus.nci.nih.gov/

  17. RDKit Open-Source Cheminformatics. http://www.rdkit.org

  18. Durant JL, Leland BA, Henry DR, Nourse JG Reoptimization of MDL Keys for Use in Drug Discovery.J. Chem. Inf. Comput. Sci2002, 42 (6),1273–1280. https://doi.org/10.1021/ci010132r

  19. Rogers D, Hahn M, Extended-Connectivity, FingerprintsJ. Chem. Inf. Model2010, 50 (5),742–754. https://doi.org/10.1021/ci100050t

  20. Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray D, Steiner B, Tucker P, Vasudevan V, Warden P, Zhang X TensorFlow:A System for Large-Scale Machine Learning. 2016

  21. Kipf TN, Welling M Semi-Supervised Classification with Graph Convolutional Networks. CoRR 2016, abs/1609.02907

  22. Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J, G\’mez-Bombarelli R, Hirzel T, Aspuru-Guzik A ’n; Adams, R. P. Convolutional Networks on Graphs for Learning Molecular Fingerprints. Nips’15 2015, 2224–2232

  23. Kearnes S, McCloskey K, Berndl M, Pande V, Riley P Molecular Graph Convolutions: Moving beyond Fingerprints.Journal of computer-aided molecular design2016, 30 (8),595–608. https://doi.org/10.1007/s10822-016-9938-8

  24. Xiong Z, Wang D, Liu X, Zhong F, Wan X, Li X, Li Z, Luo X, Chen K, Jiang H, Zheng M Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism.J. Med. Chem2020, 63 (16),8749–8760. https://doi.org/10.1021/acs.jmedchem.9b00959

  25. Yang K, Swanson K, Jin W, Coley C, Eiden P, Gao H, Guzman-Perez A, Hopper T, Kelley B, Mathea M, Palmer A, Settels V, Jaakkola T, Jensen K, Barzilay R Analyzing Learned Molecular Representations for Property Prediction.J. Chem. Inf. Model2019, 59 (8),3370–3388. https://doi.org/10.1021/acs.jcim.9b00237

  26. Visini R, Awale M, Reymond J-L, Fragment Database FDB-17J. Chem. Inf. Model2017, 57 (4),700–709. https://doi.org/10.1021/acs.jcim.7b00020

  27. Lipinski CA, Lombardo F, Dominy BW, Feeney PJ Experimental and Computational Approaches to Estimate Solubility and Permeability in Drug Discovery and Development Settings.Adv Drug Deliv Rev2001, 46 (1–3),3–26. https://doi.org/10.1016/s0169-409x(00)00129-0

  28. Veber DF, Johnson SR, Cheng H-Y, Smith BR, Ward KW, Kopple KD Molecular Properties That Influence the Oral Bioavailability of Drug Candidates.J Med Chem2002, 45 (12),2615–2623. https://doi.org/10.1021/jm020017n

  29. Ghose AK, Viswanadhan VN, Wendoloski JJ A Knowledge-Based Approach in Designing Combinatorial or Medicinal Chemistry Libraries for Drug Discovery. 1. A Qualitative and Quantitative Characterization of Known Drug Databases.J Comb Chem1999, 1 (1),55–68. https://doi.org/10.1021/cc9800071

  30. Bickerton GR, Paolini GV, Besnard J, Muresan S, Hopkins AL Quantifying the Chemical Beauty of Drugs.Nature Chemistry2012, 4 (2),90–98. https://doi.org/10.1038/nchem.1243

  31. Heifetz A, Chudyk EI, Gleave L, Aldeghi M, Cherezov V, Fedorov DG, Biggin PC, Bodkin MJ The Fragment Molecular Orbital Method Reveals New Insight into the Chemical Nature of GPCR–Ligand Interactions.J. Chem. Inf. Model2016, 56 (1),159–172. https://doi.org/10.1021/acs.jcim.5b00644

  32. Morao I, Fedorov DG, Robinson R, Southey M, Townsend-Nicholson A, Bodkin MJ, Heifetz A Rapid and Accurate Assessment of GPCR–Ligand Interactions Using the Fragment Molecular Orbital-Based Density-Functional Tight-Binding Method.Journal of Computational Chemistry2017, 38 (23),1987–1990. https://doi.org/10.1002/jcc.24850

  33. Chudyk EI, Sarrat L, Aldeghi M, Fedorov DG, Bodkin MJ, James T, Southey M, Robinson R, Morao I, Heifetz A (2018) Exploring GPCR-Ligand Interactions with the Fragment Molecular Orbital (FMO) Method. In Computational Methods for GPCR Drug Discovery; Heifetz, A., Ed.; Springer New York: New York, NY, ; pp 179–195. https://doi.org/10.1007/978-1-4939-7465-8_8

  34. Vistoli G, Pedretti A, Testa B Assessing Drug-Likeness–What Are We Missing?Drug Discov Today2008, 13 (7–8),285–294. https://doi.org/10.1016/j.drudis.2007.11.007

  35. Liao C, de Molliens MP, Schneebeli ST, Brewer M, Song G, Chatenet D, Braas KM, May V, Li J Targeting the PAC1 Receptor for Neurological and Metabolic Disorders.Curr Top Med Chem2019, 19 (16),1399–1417. https://doi.org/10.2174/1568026619666190709092647

  36. Liao C, Remington JM, May V, Li J Molecular Basis of Class B GPCR Selectivity for the Neuropeptides PACAP and VIP. Frontiers in Molecular Biosciences 2021, 8

  37. Beebe X, Darczak D, Davis-Taber RA, Uchic ME, Scott VE, Jarvis MF, Stewart AO Discovery and SAR of Hydrazide Antagonists of the Pituitary Adenylate Cyclase-Activating Polypeptide (PACAP) Receptor Type 1 (PAC1-R).Bioorganic & Medicinal Chemistry Letters2008, 18 (6),2162–2166. https://doi.org/10.1016/j.bmcl.2008.01.052

Download references

Acknowledgements

The work was mainly supported by an NIH grant R01-GM129431 to J.L. J.B.F. was supported by an NSF award (CHE-1945394 to J.L.). S.T.S. was supported by an NIH R35 award (R35-GM147579).

Author information

Authors and Affiliations

  1. Department of Chemistry, University of Vermont, Burlington, VT, 05405, USA

    Jacob M Remington, Kyle T McKay, Noah B Beckage, Jonathon B Ferrell, Severin T. Schneebeli & Jianing Li

  2. Department of Industrial and Physical Pharmacy, Department of Chemistry, Purdue University, West Lafayette, IN, 47906, USA

    Severin T. Schneebeli

  3. Department of Pathology, University of Vermont, Burlington, VT, 05405, USA

    Severin T. Schneebeli & Jianing Li

  4. Department of Medicinal Chemistry and Molecular Pharmacology, Purdue University, West Lafayette, IN, 47906, USA

    Jianing Li

Authors
  1. Jacob M Remington
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kyle T McKay
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Noah B Beckage
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jonathon B Ferrell
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Severin T. Schneebeli
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jianing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

J.R. and J.L. wrote the main manuscript text. J.R., K.M, and N.B. prepared the figures. All authors reviewed and revised the manuscript.

Corresponding author

Correspondence to Jianing Li.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

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

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

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

Remington, J.M., McKay, K., Beckage, N.B. et al. GPCRLigNet: rapid screening for GPCR active ligands using machine learning. J Comput Aided Mol Des 37, 147–156 (2023). https://doi.org/10.1007/s10822-023-00497-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10822-023-00497-2

Keywords

Search

Navigation