Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes

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 computa...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ziteng Liu, Yinghuan Shi, Hongwei Chen, Tiexin Qin, Xuejie Zhou, Jun Huo, Hao Dong, Xiao Yang, Xiangdong Zhu, Xuening Chen, Li Zhang, Mingli Yang, Yang Gao, Jing Ma
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/a7d129f801914908a22f5751d20f450f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a7d129f801914908a22f5751d20f450f
record_format	dspace
spelling	oai:doaj.org-article:a7d129f801914908a22f5751d20f450f2021-12-02T17:19:13ZMachine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes10.1038/s41524-021-00618-12057-3960https://doaj.org/article/a7d129f801914908a22f5751d20f450f2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00618-1https://doaj.org/toc/2057-3960Abstract 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.Ziteng LiuYinghuan ShiHongwei ChenTiexin QinXuejie ZhouJun HuoHao DongXiao YangXiangdong ZhuXuening ChenLi ZhangMingli YangYang GaoJing MaNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Ziteng Liu Yinghuan Shi Hongwei Chen Tiexin Qin Xuejie Zhou Jun Huo Hao Dong Xiao Yang Xiangdong Zhu Xuening Chen Li Zhang Mingli Yang Yang Gao Jing Ma Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
description	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.
format	article
author	Ziteng Liu Yinghuan Shi Hongwei Chen Tiexin Qin Xuejie Zhou Jun Huo Hao Dong Xiao Yang Xiangdong Zhu Xuening Chen Li Zhang Mingli Yang Yang Gao Jing Ma
author_facet	Ziteng Liu Yinghuan Shi Hongwei Chen Tiexin Qin Xuejie Zhou Jun Huo Hao Dong Xiao Yang Xiangdong Zhu Xuening Chen Li Zhang Mingli Yang Yang Gao Jing Ma
author_sort	Ziteng Liu
title	Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
title_short	Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
title_full	Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
title_fullStr	Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
title_full_unstemmed	Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
title_sort	machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/a7d129f801914908a22f5751d20f450f
work_keys_str_mv	AT zitengliu machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT yinghuanshi machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT hongweichen machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT tiexinqin machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT xuejiezhou machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT junhuo machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT haodong machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT xiaoyang machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT xiangdongzhu machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT xueningchen machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT lizhang machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT mingliyang machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT yanggao machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes AT jingma machinelearningonpropertiesofmultiscalemultisourcehydroxyapatitenanoparticlesdatasetswithdifferentmorphologiesandsizes
_version_	1718381102709604352

Machine learning on properties of multiscale multisource hydroxyapatite nanoparticles datasets with different morphologies and sizes

Ejemplares similares