Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
Source abstract
Abstract
Abstract Machine learning models for exploring structure-property relation for hydroxyapatite nanoparticles (HANPs) are still lacking. A multiscale multisource dataset is presented, including both experimental data (TEM/SEM, XRD/crystallinity, ROS, anti-tumor effects, and zeta potential) and computation results (containing 41,976 data samples with up to 9768 atoms) of nanoparticles with different sizes and morphologies at density functional theory (DFT), semi-empirical DFTB, and force field, respectively. Three geometric descriptors are set for the explainable machine learning methods to predict surface energies and surface stress of HANPs with satisfactory performance. To avoid the pre-determination of features, we also developed a predictive deep learning model within the framework of graph convolution neural network with good generalizability. Energies with DFT accuracy are achievable for large-sized nanoparticles from the learned correlations and scale functions for mapping different theoretical levels and particle sizes. The simulated XRD spectra and crystallinity values are in good agreement with experiments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Bone Tissue Engineering Materials · Machine Learning in Materials Science · Calcium Carbonate Crystallization and Inhibition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (59)
Show source-provided references
1. Batchelar, D. L., Davidson, M., Dabrowski, W. & Cunningham, I. A. Bone-composition imaging using coherent-scatter computed tomography: assessing bone health beyond bone mineral density. Med. Phys. 33, 904–915 (2006).10.1118/1.2179151 ↗
2. Sato, K. Mechanism of hydroxyapatite mineralization in biological systems. J. Ceram. Soc. Jpn. 115, 124–130 (2007).10.2109/jcersj.115.124 ↗
3. Malmberg, P. & Nygren, H. Methods for the analysis of the composition of bone tissue, with a focus on imaging mass spectrometry (TOF-SIMS). Proteomics 8, 3755–3762 (2008).10.1002/pmic.200800198 ↗
4. Habibovic, P. et al. Comparative in vivo study of six hydroxyapatite‐based bone graft substitutes. J. Orthop. Res. 26, 1363–1370 (2008).10.1002/jor.20648 ↗
5. Kokubo, T. & Takadama, H. How useful is SBF in predicting in vivo bone bioactivity? Biomaterials 27, 2907–2915 (2006).10.1016/j.biomaterials.2006.01.017 ↗
6. Wu, H. et al. The in vitro and in vivo anti-melanoma effects of hydroxyapatite nanoparticles: influences of material factors. Int. J. Nanomed. 14, 1177–1191 (2019).10.2147/IJN.S184792 ↗
7. Dorozhkin, S. V. Calcium Orthophosphates in Nature, Biology and Medicine. Materials 2, 399–498 (2009).10.3390/ma2020399 ↗
8. Simmer, J. P. & Fincham, A. G. Molecular mechanisms of dental enamel formation. Crit. Rev. Oral. Biol. M. 6, 84–108 (1995).10.1177/10454411950060020701 ↗
9. Gajjeraman, S., Narayanan, K., Hao, J. J., Qin, C. L. & George, A. Matrix macromolecules in hard tissues control the nucleation and hierarchical assembly of hydroxyapatite. J. Biol. Chem. 282, 1193–1204 (2007).10.1074/jbc.M604732200 ↗
10. Doi, Y., Eanes, E. D., Shimokawa, H. & Termine, J. D. Inhibition of seeded growth of enamel apatite crystals by amelogenin and enamelin proteins in vitro. J. Dent. Res. 63, 98–105 (1984).10.1177/00220345840630021801 ↗
11. Cai, Y. R. et al. Role of hydroxyapatite nanoparticle size in bone cell proliferation. J. Mater. Chem. 17, 3780–3787 (2007).10.1039/b705129h ↗
12. Li, J. J., Yin, Y. J., Yao, F. L., Zhang, L. L. & Yao, K. D. Effect of nano- and micro-hydroxyapatite/chitosan-gelatin network film on human gastric cancer cells. Mater. Lett. 62, 3220–3223 (2008).10.1016/j.matlet.2008.02.072 ↗
13. Hong, Y. L. et al. Fabrication, biological effects, and medical applications of calcium phosphate nanoceramics. Mat. Sci. Eng. R. 70, 225–242 (2010).10.1016/j.mser.2010.06.010 ↗
14. Mann, S. Molecular tectonics in biomineralization and biomimetic materials chemistry. Nature 365, 499–505 (1993).10.1038/365499a0 ↗
15. Vallet-Regi, M. & Gonzalez-Calbet, J. M. Calcium phosphates as substitution of bone tissues. Prog. Solid State Chem. 32, 1–31 (2004).10.1016/j.progsolidstchem.2004.07.001 ↗
16. Wang, W. Y. Universal nanohydrophobicity predictions using virtual nanoparticle library. J. Cheminformatics 11, 6 (2019).10.1186/s13321-019-0329-8 ↗
17. Yan, X. et al. In silico profiling nanoparticles: predictive nanomodeling using universal nanodescriptors and various machine learning approaches. Nanoscale 11, 8352–8362 (2019).10.1039/C9NR00844F ↗
18. Yan, X. L., Sedykh, A., Wang, W. Y., Yan, B. & Zhu, H. Construction of a web-based nanomaterial database by big data curation and modeling friendly nanostructure annotations. Nat. Commun. 11, 2519 (2020).10.1038/s41467-020-16413-3 ↗
19. Utgoff, P. E., Berkman, N. C. & Clouse, J. A. Decision tree induction based on efficient tree restructuring. Mach. Learn. 29, 5–44 (1997).10.1023/A:1007413323501 ↗
20. Pedregosa, F. et al. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
21. Mendonca, L. F., Vieira, S. M. & Sousa, J. M. C. Decision tree search methods in fuzzy modeling and classification. Int. J. Approx. Reason. 44, 106–123 (2007).10.1016/j.ijar.2006.07.004 ↗
22. Ke, G. L. et al. LightGBM: a highly efficient gradient boosting decision tree. Adv. Neur. In. 30, 3146–3154 (2017).
23. Chen, T. Q. & Guestrin, C. XGBoost: a scalable tree boosting system. in KDD'16: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining 785–794 (2016).10.1145/2939672.2939785 ↗
24. Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).10.1023/A:1010933404324 ↗
25. Lu, S. H. et al. Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nat. Commun. 9, 3405 (2018).10.1038/s41467-018-05761-w ↗
26. Lamber, R., Wetjen, S. & Jaeger, N. I. Size dependence of the lattice parameter of small palladium particles. Phys. Rev. B Condens. Matter 51, 10968–10971 (1995).10.1103/PhysRevB.51.10968 ↗
27. Liu, Z. et al. Transferable multilevel attention neural network for accurate prediction of quantum chemistry properties via multitask learning. J. Chem. Inf. Model 61, 1066–1082 (2021).10.1021/acs.jcim.0c01224 ↗
28. Gopinath, S. & Philip, J. Preparation of metal oxide nanoparticles of different sizes and morphologies, their characterization using small angle X-ray scattering and study of thermal properties. Mater. Chem. Phys. 145, 213–221 (2014).10.1016/j.matchemphys.2014.02.005 ↗
29. Ingham, B. X-ray scattering characterisation of nanoparticles. Crystallogr. Rev. 21, 229–303 (2015).10.1080/0889311X.2015.1024114 ↗
30. Yokaichiya, F. et al. Effects of doxorubicin on the structural and morphological characterization of solid lipid nanoparticles (SLN) using small angle neutron scattering (SANS) and small angle X-ray scattering (SAXS). Phys. B 551, 191–196 (2018).10.1016/j.physb.2017.12.036 ↗
31. Dong, H. et al. A deep convolutional neural network for real-time full profile analysis of big powder diffraction data. npj Comput. Mat. 7, 1–9 (2021).10.1038/s41524-020-00473-6 ↗
32. Zhu, C. et al. The morphology of hydroxyapatite nanoparticles regulates cargo recognition in clathrin-mediated endocytosis. Front. Mol. Biosci. 8, 39 (2021).10.3389/fmolb.2021.627015 ↗
33. Villanueva, A. et al. The influence of surface functionalization on the enhanced internalization of magnetic nanoparticles in cancer cells. Nanotechnology 20, 115103 (2009).10.1088/0957-4484/20/11/115103 ↗
34. Kittel, C., McEuen, P. & McEuen, P. Introduction to Solid State Physics Vol. 8 (Wiley New York, 1996).
35. Zhu, B. E., Xu, Z., Wang, C. L. & Gao, Y. Shape evolution of metal nanoparticles in water vapor environment. Nano. Lett. 16, 2628–2632 (2016).10.1021/acs.nanolett.6b00254 ↗
36. Holec, D., Dumitraschkewitz, P., Vollath, D. & Fischer, F. D. Surface energy of Au nanoparticles depending on their size and shape. Nanomaterials 10, 484 (2020).10.3390/nano10030484 ↗
37. Cheng, X. et al. Hydroxyl migration disorders the surface structure of hydroxyapatite nanoparticles. Appl. Surf. Sci. 416, 901–910 (2017).10.1016/j.apsusc.2017.04.250 ↗
38. Wang, X., Wu, H., Cheng, X. J., Yang, M. L. & Zhang, L. Probing the surface activity of hydroxyapatite nanoparticles through their interaction with water molecules. AIP Adv 10, 065217 (2020).10.1063/5.0010750 ↗
39. Vollath, D., Fischer, F. D. & Holec, D. Surface energy of nanoparticles—influence of particle size and structure. Beilstein J. Nanotechnol. 9, 2265–2276 (2018).10.3762/bjnano.9.211 ↗
40. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).10.1038/nature14539 ↗
41. Jiang, D. J. et al. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J. Cheminformatics 13, 1–23 (2021).10.1186/s13321-020-00479-8 ↗
42. Bengio, Y., Courville, A. & Vincent, P. Representation learning: a review and new. Perspect. IEEE T. Pattern Anal. Mach. Intel. 35, 1798–1828 (2013).10.1109/TPAMI.2013.50 ↗
43. Coley, C. W. et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Chem. Sci. 10, 370–377 (2019).10.1039/C8SC04228D ↗
44. Eguchi, R. et al. Classification of alkaloids according to the starting substances of their biosynthetic pathways using graph convolutional neural networks. BMC Bioinformatics 20, 1–13 (2019).10.1186/s12859-019-2963-6 ↗
45. Gao, P., Zhang, J., Sun, Y. Z. & Yu, J. G. Toward accurate predictions of atomic properties via quantum mechanics descriptors augmented graph convolutional neural network: application of this novel approach in NMR chemical shifts predictions. J. Phys. Chem. Lett. 11, 9812–9818 (2020).10.1021/acs.jpclett.0c02654 ↗
46. Harada, S. et al. Dual graph convolutional neural network for predicting chemical networks. BMC Bioinformatics 21, 1–13 (2020).10.1186/s12859-020-3378-0 ↗
47. Hwang, D. et al. Comprehensive study on molecular supervised learning with graph neural networks. J. Chem. Inf. Model. 60, 5936–5945 (2020).10.1021/acs.jcim.0c00416 ↗
48. Karamad, M. Orbital graph convolutional neural network for material property prediction. Phys. Rev. Mater 4, 093801 (2020).10.1103/PhysRevMaterials.4.093801 ↗
49. Lee, C. K. Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers. J. Chem. Phys. 154, 024906 (2021).10.1063/5.0037863 ↗
50. Nikitin, F., Isayev, O. & Strijov, V. DRACON: disconnected graph neural network for atom mapping in chemical reactions. Phys. Chem. Chem. Phys. 22, 26478–26486 (2020).10.1039/D0CP04748A ↗
51. Park, C. W. & Wolverton, C. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. Phys. Rev. Mater. 4, 063801 (2020).10.1103/PhysRevMaterials.4.063801 ↗
52. Rathi, P. C., Ludlow, R. F. & Verdonk, M. L. Practical high-quality electrostatic potential surfaces for drug discovery using a graph-convolutional deep neural network. J. Med. Chem. 63, 8778–8790 (2020).10.1021/acs.jmedchem.9b01129 ↗
53. Ruza, J. et al. Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks. J. Chem. Phys. 153, 164501 (2020).10.1063/5.0022431 ↗
54. Tsubaki, M., Tomii, K. & Sese, J. Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics 35, 309–318 (2019).10.1093/bioinformatics/bty535 ↗
55. Wang, S. H., Govindaraj, V. V., Gorriz, J. M., Zhang, X. & Zhang, Y. D. Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Inf. Fusion 67, 208–229 (2021).10.1016/j.inffus.2020.10.004 ↗
56. Wen, M. J., Blau, S. M., Spotte-Smith, E. W. C., Dwaraknath, S. & Persson, K. A. BonDNet: a graph neural network for the prediction of bond dissociation energies for charged molecules. Chem. Sci. 12, 1858–1868 (2021).10.1039/D0SC05251E ↗
57. Xuan, P., Pan, S. X., Zhang, T. G., Liu, Y. & Sun, H. Graph convolutional network and convolutional neural network based method for predicting lncRNA-disease associations. Cells-Basel 8, 1012 (2019).10.3390/cells8091012 ↗
58. Liu, P. Y., Chen, Q. F. & Ma, J. Design of [2]rotaxane through image threshold segmentation of electrostatic potential image. J. Comput. Chem. 37, 2228–2241 (2016).10.1002/jcc.24452 ↗
59. Otsu, N. A threshold selection method from gray-level histograms. IEEE trans. sys., man, cyber 9, 62–66 (1979).10.1109/TSMC.1979.4310076 ↗