Graph Neural Networks with Multi-features for Predicting Cocrystals using APIs and Coformers Interactions


Cite item

Full Text

Abstract

Introduction:Active pharmaceutical ingredients (APIs) have gained direct pharmaceutical interest, along with their in vitro properties, and thus utilized as auxiliary solid dosage forms upon FDA guidance and approval on pharmaceutical cocrystals when reacting with coformers, as a potential and attractive route for drug substance development.

Methods:However, screening and selecting suitable and appropriate coformers that may potentially react with APIs to successfully form cocrystals is a time-consuming, inefficient, economically expensive, and labour-intensive task. In this study, we implemented GNNs to predict the formation of cocrystals using our introduced API-coformers relational graph data. We further compared our work with previous studies that implemented descriptor-based models (e.g., random forest, support vector machine, extreme gradient boosting, and artificial neural networks).

Results:All built graph-based models show compelling performance accuracies (i.e., 91.36, 94.60 and 95. 95% for GCN, GraphSAGE, and RGCN respectively). RGCN demonstrated effectiveness and prevailed among the built graph-based models due to its capability to capture intricate and learn nuanced relationships between entities such as non-ionic and non-covalent interactions or link information between APIs and coformers which are crucial for accurate predictions and representations.

Conclusion:These capabilities allows the model to adeptly learn the topological structure inherent in the graph data.

About the authors

Medard Edmund Mswahili

Department of Computer Engineering, Chungbuk National University

Email: info@benthamscience.net

Kyuri Jo

Department of Computer Engineering, Chungbuk National University

Email: info@benthamscience.net

SeungDong Lee

Department of Computer Engineering, Chungbuk National University

Email: info@benthamscience.net

Young-Seob Jeong

Department of Computer Engineering, Chungbuk National University

Author for correspondence.
Email: info@benthamscience.net

References

  1. Regulatory classification of pharmaceutical co-crystals guidance for industry. 2018. Available from: https://www.fda.gov/files/drugs/published/Regulatory-Classification-of-Pharmaceutical-Co-Crystals.pdf
  2. Aitipamula, S. Polymorphs, salts, and cocrystals: What’s in a name? Cryst. Growth Des., 2012, 12(5), 2147-2152.
  3. Mswahili, M.E.; Lee, M-J.; Martin, G.L.; Kim, J.; Kim, P.; Choi, G.J.; Jeong, Y-S. Cocrystal prediction using machine learning models and descriptors. Appl. Sci., 2021, 11(3), 1323. doi: 10.3390/app11031323
  4. Berry, D.J.; Steed, J.W. Pharmaceutical cocrystals, salts and multicomponent systems; intermolecular interactions and property based design. Adv. Drug Deliv. Rev., 2017, 117, 3-24. doi: 10.1016/j.addr.2017.03.003 PMID: 28344021
  5. Douroumis, D.; Ross, S.A.; Nokhodchi, A. Advanced methodologies for cocrystal synthesis. Adv. Drug Deliv. Rev., 2017, 117, 178-195. doi: 10.1016/j.addr.2017.07.008 PMID: 28712924
  6. Sokal, A.; Pindelska, E. Pharmaceutical cocrystals as an opportunity to modify drug properties: From the idea to application: A review. Curr. Pharm. Des., 2018, 24(13), 1357-1365. doi: 10.2174/1381612824666171226130828 PMID: 29278209
  7. Bolla, G.; Nangia, A. Pharmaceutical cocrystals: Walking the talk. Chem. Commun., 2016, 52(54), 8342-8360. doi: 10.1039/C6CC02943D PMID: 27278109
  8. Duggirala, N.K.; Perry, M.L.; Almarsson, Ö.; Zaworotko, M.J. Pharmaceutical cocrystals: Along the path to improved medicines. Chem. Commun., 2016, 52(4), 640-655. doi: 10.1039/C5CC08216A PMID: 26565650
  9. Karagianni, A.; Malamatari, M.; Kachrimanis, K. Pharmaceutical cocrystals: New solid phase modification approaches for the formulation of apis. Pharmaceutics, 2018, 10(1), 18. doi: 10.3390/pharmaceutics10010018 PMID: 29370068
  10. Wood, P.A.; Feeder, N.; Furlow, M.; Galek, P.T.A.; Groom, C.R.; Pidcock, E. Knowledge-based approaches to co-crystal design. CrystEngComm, 2014, 16(26), 5839-5848. doi: 10.1039/c4ce00316k
  11. Wicker, J.G.P.; Crowley, L.M.; Robshaw, O.; Little, E.J.; Stokes, S.P.; Cooper, R.I.; Lawrence, S.E. Will they co-crystallize? CrystEngComm, 2017, 19(36), 5336-5340. doi: 10.1039/C7CE00587C
  12. Xiao, F.; Cheng, Y.; Wang, J.R.; Wang, D.; Zhang, Y.; Chen, K.; Mei, X.; Luo, X. Cocrystal prediction of bexarotene by graph convolution network and bioavailability improvement. Pharmaceutics, 2022, 14(10), 2198. doi: 10.3390/pharmaceutics14102198 PMID: 36297633
  13. Desiraju, G.R. Supramolecular synthons in crystal engineering-A new organic synthesis. Angew. Chem. Int. Ed. Engl., 1995, 34(21), 2311-2327. doi: 10.1002/anie.199523111
  14. Almarsson, O.; Zaworotko, M.J. Crystal engineering of the composition of pharmaceutical phases. Do pharmaceutical co-crystals represent a new path to improved medicines? Chem. Commun., 2004, (17), 1889-1896. doi: 10.1039/b402150a PMID: 15340589
  15. Aakeröy, C.B.; Salmon, D.J. Building co-crystals with molecular sense and supramolecular sensibility. CrystEngComm, 2005, 7(72), 439-448. doi: 10.1039/b505883j
  16. Groom, C.R.; Bruno, I.J.; Lightfoot, M.P.; Ward, S.C. The cambridge structural database. Acta Crystallogr. B Struct. Sci. Cryst. Eng. Mater., 2016, 72(Pt 2), 171-179. doi: 10.1107/S2052520616003954 PMID: 27048719
  17. Taylor, R.; Wood, P.A. A million crystal structures: The whole is greater than the sum of its parts. Chem. Rev., 2019, 119(16), 9427-9477. doi: 10.1021/acs.chemrev.9b00155 PMID: 31244003
  18. Galek, P.T.A.; Allen, F.H.; Fábián, L.; Feeder, N. Knowledge-based H-bond prediction to aid experimental polymorph screening. CrystEngComm, 2009, 11(12), 2634-2639. doi: 10.1039/b910882c
  19. Delori, A.; Galek, P.T.A.; Pidcock, E.; Patni, M.; Jones, W. Knowledge-based hydrogen bond prediction and the synthesis of salts and cocrystals of the anti-malarial drug pyrimethamine with various drug and GRAS molecules. CrystEngComm, 2013, 15(15), 2916-2928. doi: 10.1039/c3ce26765b
  20. Kumar, A.; Nanda, A. In-silico methods of cocrystal screening: A review on tools for rational design of pharmaceutical cocrystals. J. Drug Deliv. Sci. Technol., 2021, 63, 102527. doi: 10.1016/j.jddst.2021.102527
  21. Fábián, L. Cambridge structural database analysis of molecular complementarity in cocrystals. Cryst. Growth Des., 2009, 9(3), 1436-1443. doi: 10.1021/cg800861m
  22. Devogelaer, J.J.; Meekes, H.; Vlieg, E.; de Gelder, R. Cocrystals in the cambridge structural database: A network approach. Acta Crystallogr. B Struct. Sci. Cryst. Eng. Mater., 2019, 75(Pt 3), 371-383. doi: 10.1107/S2052520619004694 PMID: 32830659
  23. Devogelaer, J.J.; Brugman, S.J.T.; Meekes, H.; Tinnemans, P.; Vlieg, E.; de Gelder, R. Cocrystal design by network-based link prediction. CrystEngComm, 2019, 21(44), 6875-6885. doi: 10.1039/C9CE01110B
  24. Devogelaer, J.J.; Charpentier, M.D.; Tijink, A.; Dupray, V.; Coquerel, G.; Johnston, K.; Meekes, H.; Tinnemans, P.; Vlieg, E.; Ter Horst, J.H.; de Gelder, R. Cocrystals of praziquantel: Discovery by network-based link prediction. Cryst. Growth Des., 2021, 21(6), 3428-3437. doi: 10.1021/acs.cgd.1c00211 PMID: 34276256
  25. Cabeza, C.A.J. Acid–base crystalline complexes and the pKa rule. CrystEngComm, 2012, 14(20), 6362-6365. doi: 10.1039/c2ce26055g
  26. Lemmerer, A.; Govindraju, S.; Johnston, M.; Motloung, X.; Savig, K.L. Co-crystals and molecular salts of carboxylic acid/pyridine complexes: Can calculated p Ka 's predict proton transfer? A case study of nine complexes. CrystEngComm, 2015, 17(19), 3591-3595. doi: 10.1039/C5CE00102A
  27. Taylor, C.R.; Day, G.M. Evaluating the energetic driving force for cocrystal formation. Cryst. Growth & Desig., 2018, 18, 892-904.
  28. Cruz-Cabeza, A.J.; Day, G.M.; Jones, W. Towards prediction of stoichiometry in crystalline multicomponent complexes. Chemistry, 2008, 14(29), 8830-8836. doi: 10.1002/chem.200800668 PMID: 18752227
  29. Issa, N.; Karamertzanis, P.G.; Welch, G.W.A.; Price, S.L. Can the formation of pharmaceutical cocrystals be computation- ally predicted? i. comparison of lattice energies. Cryst. Growth Des., 2009, 9(1), 442-453. doi: 10.1021/cg800685z
  30. Karamertzanis, P.G.; Kazantsev, A.V.; Issa, N.; Welch, G.W.A.; Adjiman, C.S.; Pantelides, C.C.; Price, S.L. Can the formation of pharmaceutical cocrystals be computationally predicted? 2. crystal structure prediction. J. Chem. Theory Comput., 2009, 5(5), 1432-1448. doi: 10.1021/ct8004326 PMID: 26609729
  31. Hunter, C.A. Quantifying intermolecular interactions: Guidelines for the molecular recognition toolbox. Angew. Chem. Int. Ed., 2004, 43(40), 5310-5324. doi: 10.1002/anie.200301739 PMID: 15468180
  32. McKenzie, J.; Feeder, N.; Hunter, C.A. H-bond competition experiments in solution and the solid state. CrystEngComm, 2016, 18(3), 394-397. doi: 10.1039/C5CE02223A
  33. Musumeci, D.; Hunter, C.A.; Prohens, R.; Scuderi, S.; McCabe, J.F. Virtual cocrystal screening. Chem. Sci., 2011, 2(5), 883-890. doi: 10.1039/c0sc00555j
  34. Grecu, T.; Hunter, C.A.; Gardiner, E.J.; McCabe, J.F. Validation of a computational cocrystal prediction tool: Comparison of virtual and experimental cocrystal screening results. Cryst. Growth & Desig., 2014, 14, 165-171.
  35. Salem, A.; Nagy, S.; Pál, S.; Széchenyi, A. Reliability of the Hansen solubility parameters as co-crystal formation prediction tool. Int. J. Pharm., 2019, 558, 319-327. doi: 10.1016/j.ijpharm.2019.01.007 PMID: 30654064
  36. Mohammad, M.A.; Alhalaweh, A.; Velaga, S.P. Hansen solubility parameter as a tool to predict cocrystal formation. Int. J. Pharm., 2011, 407(1-2), 63-71. doi: 10.1016/j.ijpharm.2011.01.030 PMID: 21256944
  37. Klamt, A. Solvent-screening and co-crystal screening for drug development with cosmo-rs. J. Cheminformat., 2012, 4, 1-2.
  38. Loschen, C.; Klamt, A. Cocrystal ternary phase diagrams from density functional theory and solvation thermodynamics. Cryst. Growth Des., 2018, 18(9), 5600-5608. doi: 10.1021/acs.cgd.8b00923
  39. Cysewski, P.; Przybyłek, M. Selection of effective cocrystals former for dissolution rate improvement of active pharmaceutical ingredients based on lipoaffinity index. Eur. J. Pharm. Sci., 2017, 107, 87-96. doi: 10.1016/j.ejps.2017.07.004 PMID: 28687528
  40. Roca-Paixão, L.; Correia, N.T.; Affouard, F. Affinity prediction computations and mechanosynthesis of carbamazepine based cocrystals. CrystEngComm, 2019, 21(45), 6991-7001. doi: 10.1039/C9CE01160A
  41. LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature, 2015, 521(7553), 436-444. doi: 10.1038/nature14539 PMID: 26017442
  42. Mswahili, M.E.; Martin, G.L.; Woo, J.; Choi, G.J.; Jeong, Y.S. Antimalarial drug predictions using molecular descriptors and machine learning against Plasmodium falciparum. Biomolecules, 2021, 11(12), 1750. doi: 10.3390/biom11121750 PMID: 34944394
  43. Jiang, D. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J. Cheminformat., 2021, 13, 1-23.
  44. Wu, F. Simplifying graph convolutional networks. arXiv: 1902.07153, 2019.
  45. Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907, 2016.
  46. Schlichtkrull, M. Modeling relational data with graph convolutional networks. 15th International Conference, ESWC 2018, June 3–7, 2018 Heraklion, Crete, Greece, pp. 593-607, 2018. doi: 10.1007/978-3-319-93417-4_38
  47. Thanapalasingam, T.; van Berkel, L.; Bloem, P.; Groth, P. Relational graph convolutional networks: A closer look. PeerJ Comput. Sci., 2022, 8, e1073. doi: 10.7717/peerj-cs.1073 PMID: 36426239
  48. Kim, S.; Bae, S.; Piao, Y.; Jo, K. Graph convolutional network for drug response prediction using gene expression data. Mathematics, 2021, 9(7), 772. doi: 10.3390/math9070772
  49. Lee, M.J.; Kim, J.Y.; Kim, P.; Lee, I.S.; Mswahili, M.E.; Jeong, Y.S.; Choi, G.J. Novel cocrystals of vonoprazan: Machine learning-assisted discovery. Pharmaceutics, 2022, 14(2), 429. doi: 10.3390/pharmaceutics14020429 PMID: 35214161
  50. Kim, P.; Lee, I.S.; Kim, J.Y.; Mswahili, M.E.; Jeong, Y.S.; Yoon, W.J.; Yun, H.S.; Lee, M.J.; Choi, G.J. A study to discover novel pharmaceutical cocrystals of pelubiprofen with a machine learning approach compared. CrystEngComm, 2022, 24(21), 3938-3952. doi: 10.1039/D2CE00153E
  51. Jiang, Y.; Yang, Z.; Guo, J.; Li, H.; Liu, Y.; Guo, Y.; Li, M.; Pu, X. Coupling complementary strategy to flexible graph neural network for quick discovery of coformer in diverse co-crystal materials. Nat. Commun., 2021, 12(1), 5950. doi: 10.1038/s41467-021-26226-7 PMID: 34642333
  52. sklearn.preprocessing.standardscaler. Available from: https://scikit-earn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html (Accessed on: 2023-03-15).
  53. Moriwaki, H.; Tian, Y.S.; Kawashita, N.; Takagi, T. Mordred: A molecular descriptor calculator. J. Cheminformat., 2018, 10, 1-14.
  54. RDKit: Open-source cheminformatics software. Available from: http://www.rdkit.org/
  55. Featurizers. Available from: https://deepchem.readthedocs.io/en/latest/api_reference/featurizers.html# mordreddescriptors (Accessed on: 2023-03-15).
  56. Ding, Y.; Jiang, X.; Kim, Y. Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules. Bioinformatics, 2022, 38(10), 2826-2831. PMID: 35561199
  57. Hu, Z.; Dong, Y.; Wang, K.; Sun, Y. Heterogeneous graph transformer. arXiv:2003.01332, 2020.
  58. Creating message passing networks. Available from: https://pytorch-geometric.readthedocs.io/en/latest/notes/create_gnn.html (Accessed on: 2023-03-15).
  59. Fey, M.; Lenssen, J.E. Fast graph representation learning with pytorch geometric. arXiv preprint arXiv: 1903.02428, 2019.
  60. Hamilton, W.; Ying, Z.; Leskovec, J. Inductive representation learning on large graphs. arXiv:1706.02216, 2017.
  61. Devogelaer, J-J.; Meekes, H.; Tinnemans, P.; Vlieg, E.; de Gelder, R. Co-crystal prediction by artificial neural networks. Angew. Chem. Int. Ed. Engl., 2020, 59(48), 21711-21718. doi: 10.1002/anie.202009467 PMID: 32797658
  62. Zhou, K. Understanding and resolving performance degradation in deep graph convolutional networks. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, November 1–5, 2021Virtual Event, Australia, 2021, pp. 2728-2737.
  63. Li, G.; Muller, M.; Thabet, A.; Ghanem, B. Deepgcns: Can gcns go as deep as cnns? Proceedings of the IEEE/CVF International Conference On Computer Vision, 2019-02 November 2019 27 October 2019-02 November 2019 Seoul, Korea, pp. 9267-9276, 2019.
  64. Rong, Y.; Huang, W.; Xu, T.; Huang, J. Dropedge: Towards deep graph convolutional networks on node classification. arXiv:1907.10903, 2019.
  65. Li, Q.; Han, Z.; Wu, X-M. Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, pp. 3538-3545.
  66. Li, G.; Xiong, C.; Thabet, A.; Ghanem, B. Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739, 2020.
  67. Do we need deep graph neural networks? Available from: https://towardsdatascience.com/ (Accessed on: 2023-03-15).
  68. Oono, K.; Suzuki, T. Graph neural networks exponentially lose expressive power for node classification. arXiv preprint arXiv:1905.10947, 2019.
  69. Chen, M.; Wei, Z.; Huang, Z.; Ding, B.; Li, Y. Simple and deep graph convolutional networks. Proceedings of the 37th International Conference on Machine Learning, PMLR, 2020, pp. 1725-1735.
  70. Chen, D. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 3438-3445.
  71. Alon, U.; Yahav, E. On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205, 2020. doi: 10.48550/arXiv.2006.05205

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2024 Bentham Science Publishers