机器学习在纳米材料风险评估中的应用
Overview of Application of Machine Learning in Field of Nanomaterials Risk Assessment
-
摘要: 纳米材料的广泛应用使其排放量急剧增大，将对生态环境及人类健康造成潜在危害。因此，对纳米材料进行风险评估十分必要。纳米材料风险评估中涉及的动物实验成本高，周期长，难以满足风险评估的数据需求。为填补数据空缺，研究人员引入了计算机建模的方法对纳米材料的理化性质、毒理学效应进行预测，取得了一定的效果。机器学习作为目前计算机建模的先进方法，在纳米材料风险评估领域展现出了良好的应用价值与前景。本文首先介绍了机器学习在纳米材料风险评估领域的应用方法及建模流程，其次结合国内外研究现状，综述了机器学习在纳米材料风险评估领域的应用实例，介绍了机器学习在纳米材料性质、毒理学效应预测中的主要进展，最后根据机器学习在纳米材料风险评估领域的应用现状，指出了该领域面临的挑战与未来发展前景。Abstract: The wide application of nanomaterials has led to a sharp increase in emissions, which has potential risk to the ecological environment and human health. Therefore, risk assessment of nanomaterials is particularly important. Animal experiment involved in the risk assessment of nanomaterials is costly and time-consuming, leading to difficulties in satisfying the data requirements of risk assessment. In order to fill the data gap, computer modeling methods have been introduced to predict the physical and chemical properties and toxicological effects of nanomaterials. Machine learning (ML), as the current advanced method of computer modeling, has shown good performance and prospects in the field of nanomaterials risk assessment. This article firstly introduces the application methods and modeling process of machine learning in nanomaterials risk assessment. Secondly, based on the research status at home and abroad, the examples of machine learning applied in current issue are reviewed to exhibit the main progress of machine learning in predicting nanomaterial properties and toxicological effects. Finally, according to current studying status of machine learning in nanomaterials, the prospects and challenges in this field is summarized.
-
Key words:
- nanomaterials /
- machine learning /
- risk assessment /
- physicochemical property /
- toxicological effects
-
-
Ma L L, Zhao J F, Wang J, et al. The acute liver injury in mice caused by nano-anatase TiO2[J]. Nanoscale Research Letters, 2009, 4(11):1275-1285 Sha B Y, Gao W, Wang S Q, et al. Cytotoxicity of titanium dioxide nanoparticles differs in four liver cells from human and rat[J]. Composites Part B:Engineering, 2011, 42(8):2136-2144 Liu S J, Zhao Y, Liu Y X, et al. Pre-exposure to TiO2-NPs aggravates alcohol-related liver injury by inducing intestinal barrier damage in mice[J]. Toxicological Sciences:An Official Journal of the Society of Toxicology, 2021, 185(1):28-37 刘颖, 陈春英. 纳米材料的安全性研究及其评价[J]. 科学通报, 2011, 56(2):119-125 Liu Y, Chen C Y. Safety and risk assessment of nanomaterials[J]. Chinese Science Bulletin, 2011, 56(2):119-125(in Chinese)
国家市场监督管理总局. 纳米技术纳米材料风险评估:GB/T37129-2018[S]. 北京:中国标准出版社, 2018 Otter D W, Medina J R, Kalita J K. A survey of the usages of deep learning for natural language processing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(2):604-624 赵京胜, 宋梦雪, 高祥. 自然语言处理发展及应用综述[J]. 信息技术与信息化, 2019(7):142-145 Ker J, Wang L P, Rao J, et al. Deep learning applications in medical image analysis[J]. IEEE Access, 2018, 6:9375-9389 圣文顺, 孙艳文. 卷积神经网络在图像识别中的应用[J]. 软件工程, 2019, 22(2):13-16 Sheng W S, Sun Y W. Application of convolutional neural network in image recognition[J]. Software Engineering, 2019, 22(2):13-16(in Chinese)
Grigorescu S, Trasnea B, Cocias T, et al. A survey of deep learning techniques for autonomous driving[J]. Journal of Field Robotics, 2020, 37(3):362-386 潘峰, 鲍泓. 强化学习的自动驾驶控制技术研究进展[J]. 中国图象图形学报, 2021, 26(1):28-35 Pan F, Bao H. Research progress of automatic driving control technology based on reinforcement learning[J]. Journal of Image and Graphics, 2021, 26(1):28-35(in Chinese)
Sizochenko N, Syzochenko M, Fjodorova N, et al. Evaluating genotoxicity of metal oxide nanoparticles:Application of advanced supervised and unsupervised machine learning techniques[J]. Ecotoxicology and Environmental Safety, 2019, 185:109733 Chau Y T, Yap C W. Quantitative nanostructure-activity relationship modelling of nanoparticles[J]. RSC Advances, 2012, 2(22):8489-8496 Ghorbanzadeh M, Fatemi M H, Karimpour M. Modeling the cellular uptake of magnetofluorescent nanoparticles in pancreatic cancer cells:A quantitative structure activity relationship study[J]. Industrial & Engineering Chemistry Research, 2012, 51(32):10712-10718 Lamon L, Asturiol D, Richarz A, et al. Grouping of nanomaterials to read-across hazard endpoints:From data collection to assessment of the grouping hypothesis by application of chemoinformatic techniques[J]. Particle and Fibre Toxicology, 2018, 15:37 Aguilera P A, Fernández A, Fernández R, et al. Bayesian networks in environmental modelling[J]. Environmental Modelling & Software, 2011, 26(12):1376-1388 Loh W Y. Classification and regression trees[J]. Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery, 2011, 1(1):14-23 Burden F R, Winkler D A. Relevance vector machines:Sparse classification methods for QSAR[J]. Journal of Chemical Information and Modeling, 2015, 55(8):1529-1534 Svetnik V, Liaw A, Tong C, et al. Random forest:A classification and regression tool for compound classification and QSAR modeling[J]. Journal of Chemical Information and Computer Sciences, 2003, 43(6):1947-1958 Chen T Q, Guestrin C. XGBoost:A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA:ACM, 2016:785-794 Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn:Machine learning in Python[DB/OL].[2022-01-05]. https://arxiv.org/abs/1201.0490 LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444 Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90 Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780 Paszke A, Gross S, Massa F, et al. PyTorch:An imperative style, high-performance deep learning library[C]//Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS). Vancouver, Canada, 2019 Abadi M, Barham P, Chen J M, et al. TensorFlow:A system for large-scale machine learning[C]//Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). Savannah, GA, USA, 2016:2016 Jia Y Q, Shelhamer E, Donahue J, et al. Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, Florida, USA:ACM, 2014:675-678 Furxhi I, Murphy F, Mullins M, et al. Practices and trends of machine learning application in nanotoxicology[J]. Nanomaterials, 2020, 10(1):E116 Wyrzykowska E, Jagiello K, Rasulev B, et al. Descriptors in Nano-QSAR/QSPR Modeling[M]//Computational Nanotoxicology. Gdansk, Poland:Jenny Stanford Publishing, 2019:245-302 Gajewicz A. What if the number of nanotoxicity data is too small for developing predictive nano-QSAR models? An alternative read-across based approach for filling data gaps[J]. Nanoscale, 2017, 9(24):8435-8448 Ban Z, Zhou Q X, Sun A Q, et al. Screening priority factors determining and predicting the reproductive toxicity of various nanoparticles[J]. Environmental Science & Technology, 2018, 52(17):9666-9676 Choi J S, Ha M K, Trinh T X, et al. Towards a generalized toxicity prediction model for oxide nanomaterials using integrated data from different sources[J]. Scientific Reports, 2018, 8(1):6110 Qiao Y C, Yang X, Wu E. The research of BP neural network based on one-hot encoding and principle component analysis in determining the therapeutic effect of diabetes mellitus[C]//Proceedings of the 3rd International Workshop on Renewable Energy and Development (IWRED), Guangzhou:Taiyuan University of Technology, 2019 Peng T, Wei C H, Yu F B, et al. Predicting nanotoxicity by an integrated machine learning and metabolomics approach[J]. Environmental Pollution, 2020, 267:115434 Mu Y S, Wu F C, Zhao Q, et al. Predicting toxic potencies of metal oxide nanoparticles by means of nano-QSARs[J]. Nanotoxicology, 2016, 10(9):1207-1214 Kar S, Gajewicz A, Puzyn T, et al. Nano-quantitative structure-activity relationship modeling using easily computable and interpretable descriptors for uptake of magnetofluorescent engineered nanoparticles in pancreatic cancer cells[J]. Toxicology in Vitro:An International Journal Published in Association With BIBRA, 2014, 28(4):600-606 Ban Z, Yuan P, Yu F B, et al. Machine learning predicts the functional composition of the protein corona and the cellular recognition of nanoparticles[J]. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(19):10492-10499 Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8):861-874 Ribeiro M T, Singh S, Guestrin C. "why should I trust you?":Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA:ACM, 2016:1135-1144 Szecówka P M, Szczurek A, Mazurowski M A, et al. Neural network sensitivity analysis applied for the reduction of the sensor matrix[C]//Proceedings of the 10th International Conference on Computer Aided Systems Theory. New York:ACM, 2005:27-32 Nohara Y, Wakata Y, Nakashima N. Interpreting medical information using machine learning and individual conditional expectation[C]//Proceedings of the 15th World Congress on Health and Biomedical Informatics (MEDINFO). Sao Paulo, Brazil:International Medical Informatics Association, Brazilian Health Informatics Society, 2015:1073-1073 Gil P R, Oberdörster G, Elder A, et al. Correlating physico-chemical with toxicological properties of nanoparticles:The present and the future[J]. ACS Nano, 2010, 4(10):5527-5531 Murdock R C, Braydich-Stolle L, Schrand A M, et al. Characterization of nanomaterial dispersion in solution prior to in vitro exposure using dynamic light scattering technique[J]. Toxicological Sciences:An Official Journal of the Society of Toxicology, 2008, 101(2):239-253 Schaeublin N M, Braydich-Stolle L K, Maurer E I, et al. Does shape matter? Bioeffects of gold nanomaterials in a human skin cell model[J]. Langmuir:the ACS Journal of Surfaces and Colloids, 2012, 28(6):3248-3258 Cho W S, Duffin R, Thielbeer F, et al. Zeta potential and solubility to toxic ions as mechanisms of lung inflammation caused by metal/metal oxide nanoparticles[J]. Toxicological Sciences:An Official Journal of the Society of Toxicology, 2012, 126(2):469-477 Mikolajczyk A, Gajewicz A, Rasulev B, et al. Zeta potential for metal oxide nanoparticles:A predictive model developed by a nano-quantitative structure-property relationship approach[J]. Chemistry of Materials, 2015, 27(7):2400-2407 Sizochenko N, Mikolajczyk A, Syzochenko M, et al. Zeta potentials (ζ) of metal oxide nanoparticles:A meta-analysis of experimental data and a predictive neural networks modeling[J]. NanoImpact, 2021, 22:100317 Zhang Q B, Xiu Z M, Peretyazhko T, et al. Toxicity of silver nanoparticles:Influence of the particle shape, size, and surface coating[J]. Abstracts of Papers of the American Chemical Society, 2014, 247:403 Coquelin L, Fischer N, Feltin N, et al. Towards the use of deep generative models for the characterization in size of aggregated TiO2 nanoparticles measured by scanning electron microscopy (SEM)[J]. Materials Research Express, 2019, 6(8):085001 Berg S, Kutra D, Kroeger T, et al. Ilastik:Interactive machine learning for (bio)image analysis[J]. Nature Methods, 2019, 16(12):1226-1232 Ilett M, Wills J, Rees P, et al. Application of automated electron microscopy imaging and machine learning to characterise and quantify nanoparticle dispersion in aqueous media[J]. Journal of Microscopy, 2020, 279(3):177-184 Puzyn T, Rasulev B, Gajewicz A, et al. Using nano-QSAR to predict the cytotoxicity of metal oxide nanoparticles[J]. Nature Nanotechnology, 2011, 6(3):175-178 Karatzas P, Melagraki G, Ellis L A, et al. Development of deep learning models for predicting the effects of exposure to engineered nanomaterials on Daphnia magna[J]. Small, 2020, 16(36):e2001080 Gernand J M, Casman E A. Nanoparticle characteristic interaction effects on pulmonary toxicity:A random forest modeling framework to compare risks of nanomaterial variants[J]. Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering, 2016, 2(2):158-161 Isoda K, Tanaka A, Fuzimori C, et al. Toxicity of gold nanoparticles in mice due to nanoparticle/drug interaction induces acute kidney damage[J]. Nanoscale Research Letters, 2020, 15(1):141 Abudayyak M, Altınçekiç Gürkaynak T, Özhan G. Assessment of cellular responses in kidney cells exposed to cobalt oxide nanoparticles[J]. Marmara Pharmaceutical Journal, 2017, 21(3):537 Salazar-García S, Delgado-Buenrostro N L, Rodríguez-Escamilla J C, et al. Zinc protects the rat brain from damage induced by 24 h exposure to silver nanoparticles[J]. Journal of Nanoparticle Research, 2019, 21(8):1-13 Cheng Y P, Chen Z Z, Yang S, et al. Nanomaterials-induced toxicity on cardiac myocytes and tissues, and emerging toxicity assessment techniques[J]. The Science of the Total Environment, 2021, 800:149584 Liu L, Zhang Z L, Cao L H, et al. Cytotoxicity of phytosynthesized silver nanoparticles:A meta-analysis by machine learning algorithms[J]. Sustainable Chemistry and Pharmacy, 2021, 21:100425 Yu F B, Wei C H, Deng P, et al. Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles[J]. Science Advances, 2021, 7(22):eabf4130 Nel A E, Mädler L, Velegol D, et al. Understanding biophysicochemical interactions at the nano-bio interface[J]. Nature Materials, 2009, 8(7):543-557 Haase A, Klaessig F. EU US roadmap nanoinformatics 2030[R]. Zenodo, 2018 Kar S, Gajewicz A, Puzyn T, et al. Periodic table-based descriptors to encode cytotoxicity profile of metal oxide nanoparticles:A mechanistic QSTR approach[J]. Ecotoxicology and Environmental Safety, 2014, 107:162-169 Liu Y, Yang Q, Li Y, et al. Application of machine learning in organic chemistry[J]. Chinese Journal of Organic Chemistry, 2020, 40(11):3812-3827 Yan X L, Sedykh A, Wang W Y, et al. In silico profiling nanoparticles:Predictive nanomodeling using universal nanodescriptors and various machine learning approaches[J]. Nanoscale, 2019, 11(17):8352-8362 Yan X L, Zhang J, Russo D P, et al. Prediction of nano-bio interactions through convolutional neural network analysis of nanostructure images[J]. ACS Sustainable Chemistry & Engineering, 2020, 8(51):19096-19104 李潍, 于相毅, 史薇, 等. 欧盟健康风险评估技术概述[J]. 生态毒理学报, 2019, 14(4):43-53 Li W, Yu X Y, Shi W, et al. Overview of EU human health risk assessment technology[J]. Asian Journal of Ecotoxicology, 2019, 14(4):43-53(in Chinese)
-
点击查看大图
计量
- 文章访问数: 2834
- HTML全文浏览数: 2834
- PDF下载数: 139
- 施引文献: 0
下载:
