基于机器学习的纳米材料生物效应研究的科学问题

胡献刚; 李佳薇; 李佳蔷; 靳红叶; 于福波

doi:10.13205/j.hjgc.202206022

基于机器学习的纳米材料生物效应研究的科学问题

doi: 10.13205/j.hjgc.202206022

1. 南开大学环境科学与工程学院环境污染过程与基准教育部重点实验室, 天津 300350;
2. 南开大学生命科学学院, 天津 300072

基金项目:

国家重点研发计划(2019YFC1804603)

详细信息

作者简介:
胡献刚(1983-),男,教授,主要研究方向为机器学习与环境健康交叉。huxiangang@nankai.edu.cn

通讯作者:
胡献刚(1983-),男,教授,主要研究方向为机器学习与环境健康交叉。huxiangang@nankai.edu.cn

计量
- 文章访问数: 180
- HTML全文浏览量: 19
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2021-12-16
- 网络出版日期: 2022-09-01
- 刊出日期: 2022-09-01

SCIENTIFIC QUESTIONS ON THE BIOLOGICAL EFFECTS OF NANOMATERIALS BASED ON MACHINE LEARNING

1. Key Laboratory of Pollution Processes and Environmental Criteria, Ministry of Education, College of Environmental Science and Engineering, Nankai University, Tianjin 300350, China;
2. College of Life Sciences, Nankai University, Tianjin 300072, China

摘要

摘要: 纳米材料(nanomaterials,NM)作为一类新型的化学品,认识、控制其引起的不良环境健康风险是推广应用的重要前提。近些年,机器学习(machine learning,ML)作为一种数据驱动的研究方法,在环境、化学和材料等领域引起了广泛关注。从NM引起的细胞毒性、个体效应、蛋白冠与生态冠预测等几方面,介绍了ML的应用,并分析了应用过程中,数据集、描述符、ML方法、模型可解释性等方面存在的问题和解决方法。文章提出,数据提取与挖掘方法、新描述符、新模型、模型解释方法的创新与发展将能够促进ML在NM生物效应领域的应用。同时,随着ML的发展,ML有望能够预测新型的NM和复杂的效应,并揭示了相关原理。以梳理讨论ML在NM生物效应预测中面临的重要科学问题为重点,有助于后续研究者理清思路,解决该领域的难题,促进纳米产业健康可持续发展。
- 纳米材料 /
- 生物效应 /
- 机器学习 /
- 大数据 /
- 人工智能
Abstract: Nanomaterials (NM),as a new class of chemicals,recognizing and controlling their adverse environmental health risks are important for their applications.In recent years,machine learning (ML),as a data-driven approach,has attracted extensive attention in various fields,such as environment,chemistry,and materials.The review introduces the applications of ML from the aspects of NM-induced cytotoxicity,individual effects,protein corona and ecological corona predictions,and analyzes the problems and solutions during the application process from the aspects of data sets,descriptors,machine learning models,and model interpretability.The review also points out that the innovation and development of data extraction and mining methods,new descriptors,new models,and model interpretation methods will promote the application of ML in the biological effects of NM.With the development of ML,new types of NM and complex effects are expected to be predicted and their principles can be revealed.This review focuses on the discussion on the important scientific issues faced in the prediction of NM biological effects using ML,which will help the following researchers clarify the ideas,solve the problems in this field,and promote the healthy and sustainable development of the nano-industry.
- nanomaterial /
- biological effect /
- machine learning /
- big data /
- artificial intelligence

HTML全文

参考文献(72)

[1]	WINKLER D A, BURDEN F R, YAN B, et al. Modelling and predicting the biological effects of nanomaterials[J]. Sar and Qsar in Environmental Research, 2014, 25(1/2/3):161-172.
[2]	WINKLER D A. Role of artificial intelligence and machine learning in nanosafety[J]. Small, 2020, 16(36).
[3]	谢翼飞,李旭东,李福德.生物硫铁纳米材料特性分析及其处理高浓度含铬废水研究[J].环境科学, 2009, 30(4):1060-1065.
[4]	XU P, ZENG G M, HUANG D L, et al. Use of iron oxide nanomaterials in wastewater treatment:a review[J]. Science of the Total Environment, 2012, 424:1-10.
[5]	MAUTER M S, ZUCKER I, PERREAULT F, et al. The role of nanotechnology in tackling global water challenges[J]. Nature Sustainability, 2018, 1(4):166-175.
[6]	HOU X, MU L, CHEN F, et al. Emerging investigator series:design of hydrogel nanocomposites for the detection and removal of pollutants:from nanosheets, network structures, and biocompatibility to machine-learning-assisted design[J]. Environmental Science:Nano, 2018, 5(10):2216-2240.
[7]	张业.纳米材料的电化学制备及其应用[J].环境工程, 2011, 29(3):128-130 ,90.
[8]	LIU S, MA C, MA M G, et al. Recent advances in carbon nanomaterials derived from biomass[J]. Science of Advanced Materials, 2019, 11(1):5-17.
[9]	KIM S, KIM K H, BARK C W. Two-dimensional nanomaterials:their structures, synthesis, and applications[J]. Science of Advanced Materials, 2017, 9(9):1441-1457.
[10]	FAN Z X, HUANG X, CHEN Y, et al. Facile synthesis of gold nanomaterials with unusual crystal structures[J]. Nature Protocols, 2017, 12(11):2367-2376.
[11]	韩伟,于艳军,李宁涛,等.纳米复合材料在食品包装中的应用及其安全评价[J].科学通报, 2011, 56(3):198-209.
[12]	郑明彬,赵鹏飞,罗震宇,等.纳米技术在癌症诊疗一体化中的应用[J].科学通报, 2014, 59(31):3009-3024.
[13]	POON W, KINGSTON B R, OUYANG B, et al. A framework for designing delivery systems[J]. Nature Nanotechnology, 2020, 15(10):819-829.
[14]	BENFENATI F, LANZANI G. Clinical translation of nanoparticles for neural stimulation[J]. Nature Reviews Materials, 2021, 6(1):1-4.
[15]	闻雷,宋仁升,石颖,等.炭材料在锂离子电池中的应用及前景[J].科学通报, 2013, 58(31):3157-3171.
[16]	KAH M, TUFENKJI N, WHITE J C. Nano-enabled strategies to enhance crop nutrition and protection[J]. Nature Nanotechnology, 2019, 14(6):532-540.
[17]	GILBERTSON L M, POURZAHEDI L, LAUGHTON S, et al. Guiding the design space for nanotechnology to advance sustainable crop production[J]. Nature Nanotechnology, 2020, 15(9):801-,.
[18]	YANAMALA N, ORANDLE M S, KODALI V K, et al. Supervised machine learning approaches predict and characterize nanomaterial exposures:MWCNT markers in lung lavage fluid[C]//Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics (ACM-BCB), Boston, MA, F 2017.
[19]	张学治,孙红文,张稚妍.鲤鱼对纳米二氧化钛的生物富集[J].环境科学, 2006,27(8):1631-1635.
[20]	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):14.
[21]	DEV A, SRIVASTAVA A K, KARMAKAR S. Nanomaterial toxicity for plants[J]. Environmental Chemistry Letters, 2018, 16(1):85-100.
[22]	LUAN F, TANG L L, ZHANG L H, et al. A further development of the QNAR model to predict the cellular uptake of nanoparticles by pancreatic cancer cells[J]. Food and Chemical Toxicology, 2018, 112:571-580.
[23]	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.
[24]	YU H J, ZHAO Z L, CHENG F. Predicting and investigating cytotoxicity of nanoparticles by translucent machine learning[J]. Chemosphere, 2021, 276:130164.
[25]	FURXHI I, MURPHY F, MULLINS M, et al. Nanotoxicology data for in silico tools:a literature review[J]. Nanotoxicology, 2020, 14(5):612-637.
[26]	WANG M, WANG T, CAI P Q, et al. Nanomaterials discovery and design through machine learning[J]. Small Methods, 2019, 3(5).
[27]	TO K T, TRUONG L, EDWARDS S, et al. Multivariate modeling of engineered nanomaterial features associated with developmental toxicity[J]. Nanoimpact, 2019, 16:100185.
[28]	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.
[29]	MARCHWIANY M E, BIROWSKA M, POPIELSKI M, et al. Surface-related features responsible for cytotoxic behavior of mXenes layered materials predicted with machine learning approach[J]. Materials, 2020, 13(14).
[30]	KOTZABASAKI M I, SOTIROPOULOS I, SARIMVEIS H. QSAR modeling of the toxicity classification of superparamagnetic iron oxide nanoparticles (SPIONs) in stem-cell monitoring applications:an integrated study from data curation to model development[J]. RSC Advances, 2020, 10(9):5385-5391.
[31]	HAN Z W, SALAWU O A, ZENOBIO J E, et al. Emerging investigator series:immobilization of arsenic in soil by nanoscale zerovalent iron:role of sulfidation and application of machine learning[J]. Environmental Science-Nano, 2021, 8(3):619-633.
[32]	GUL G, YILDIRIM R, ILERI-ERCAN N. Cytotoxicity analysis of nanoparticles by association rule mining[J]. Environmental Science:Nano, 2021, 8(4):937-949.
[33]	VARSOU D D, ELLIS L J A, AFANTITIS A, et al. Ecotoxicological read-across models for predicting acute toxicity of freshly dispersed versus medium-aged NMs to Daphnia magna[J]. Chemosphere, 2021, 285:131452.
[34]	SUBRAMANIAN N A, PALANIAPPAN A. NanoTox:development of a parsimonious in silico model for toxicity assessment of metal-oxide nanoparticles using physicochemical features[J]. ACS Omega, 2021, 6(17):11729-11739.
[35]	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.
[36]	SIZOCHENKO N, MIKOLAJCZYK A, JAGIELLO K, et al. How the toxicity of nanomaterials towards different species could be simultaneously evaluated:a novel multi-nano-read-across approach[J]. Nanoscale, 2018, 10(2):582-591.
[37]	SINGH A V, MAHARJAN R-S, KANASE A, et al. Machine-learning-based approach to decode the influence of nanomaterial properties on their interaction with cells[J]. Acs Applied Materials&Interfaces, 2021, 13(1):1943-1955.
[38]	PAPADIAMANTIS A G, JANES J, VOYIATZIS E, et al. Predicting cytotoxicity of metal oxide nanoparticles using isalos analytics platform[J]. Nanomaterials, 2020, 10(10):2017.
[39]	KOTZABASAKI M, SOTIROPOULOS I, CHARITIDIS C, et al. Machine learning methods for multi-walled carbon nanotubes (MWCNT) genotoxicity prediction[J]. Nanoscale Advances, 2021, 3(11):3167-3176.
[40]	KAR S, PATHAKOTI K, TCHOUNWOU P B, et al. Evaluating the cytotoxicity of a large pool of metal oxide nanoparticles to Escherichia coli:mechanistic understanding through In Vitro and In Silico studies[J]. Chemosphere, 2021, 264:128428.
[41]	HALDER A K, MELO A, CORDEIRO M N D S. A unified in silico model based on perturbation theory for assessing the genotoxicity of metal oxide nanoparticles[J]. Chemosphere, 2020, 244:125489.
[42]	FURXHI I, MURPHY F, MULLINS M, et al. Machine learning prediction of nanoparticle in vitro toxicity:a comparative study of classifiers and ensemble-classifiers using the Copeland Index[J]. Toxicology Letters, 2019, 312:157-166.
[43]	CHOI J S, TRINH T X, YOON T H, et al. Quasi-QSAR for predicting the cell viability of human lung and skin cells exposed to different metal oxide nanomaterials[J]. Chemosphere, 2019, 217:243-249.
[44]	CHAU Y T, YAP C W. Quantitative Nanostructure-Activity Relationship modelling of nanoparticles[J]. Rsc Advances, 2012, 2(22):8489-8496.
[45]	CONCU R, KLEANDROVA V V, SPECK-PLANCHE A, et al. Probing the toxicity of nanoparticles:a unified in silico machine learning model based on perturbation theory[J]. Nanotoxicology, 2017, 11(7):891-906.
[46]	FINDLAY M R, FREITAS D N, MOBED-MIREMADI M, et al. Machine learning provides predictive analysis into silver nanoparticle protein corona formation from physicochemical properties[J]. Environmental Science:Nano, 2018, 5(1):64-71.
[47]	LIM G P, SOON C F, MA N L, et al. Cytotoxicity of MXene-based nanomaterials for biomedical applications:a mini review[J]. Environmental Research, 2021, 201:111592.
[48]	SIMEONE F C, COSTA A L. Assessment of cytotoxicity of metal oxide nanoparticles on the basis of fundamental physical-chemical parameters:a robust approach to grouping[J]. Environmental Science:Nano, 2019, 6(10):3102-3112.
[49]	CHEN G C, VIJVER M G, XIAO Y L, et al. A review of recent advances towards the development of (quantitative) structure-activity relationships for metallic nanomaterials[J]. Materials, 2017, 10(9):1013.
[50]	SASON H, SHAMAY Y. Nanoinformatics in drug delivery[J]. Israel Journal of Chemistry, 2020, 60(12):1108-1117.
[51]	MA Y, WANG J L, WU J Y, et al. Meta-analysis of cellular toxicity for graphene via data-mining the literature and machine learning[J]. Science of the Total Environment, 2021, 793:148532.
[52]	HAYAT H, NUKALA A, NYAMIRA A, et al. A concise review:the synergy between artificial intelligence and biomedical nanomaterials that empowers nanomedicine[J]. Biomedical Materials, 2021, 16(5).
[53]	SHEEHAN B, MURPHY F, MULLINS M, et al. Hazard screening methods for nanomaterials:a comparative study[J]. International Journal of Molecular Sciences, 2018, 19(3):649.
[54]	KARATZAS P, MELAGRAKI G, ELLIS L J 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).
[55]	GOMES S I L, AMORIM M J B, POKHREL S, et al. Machine learning and materials modelling interpretation of in vivo toxicological response to TiO₂ nanoparticles library (UV and non-UV exposure)[J]. Nanoscale, 2021, 13(35):14666-14678.
[56]	GOUSIADOU C, ROBINSON R L M, KOTZABASAKI M, et al. Machine learning predictions of concentration-specific aggregate hazard scores of inorganic nanomaterials in embryonic zebrafish[J]. Nanotoxicology, 2021, 15(4):446-476.
[57]	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.
[58]	YANAMALA N, DESAI I C, MILLER W, et al. Grouping of carbonaceous nanomaterials based on association of patterns of inflammatory markers in BAL fluid with adverse outcomes in lungs[J]. Nanotoxicology, 2019, 13(8):1102-1016.
[59]	PAPA E, DOUCET J P, SANGION A, et al. Investigation of the influence of protein corona composition on gold nanoparticle bioactivity using machine learning approaches[J]. Sar and Qsar in Environmental Research, 2016, 27(7):521-538.
[60]	HELMA C, RAUTENBERG M, GEBELE D. Nano-Lazar:read across predictions for nanoparticle toxicities with calculated and measured properties[J]. Frontiers in Pharmacology, 2017, 8.
[61]	WEI L F, ZHANG Q, HOU X W, et al. Species-dependent eco-corona dictates the aggregation of black phosphorus nanosheets:the role of protein and calcium[J]. Environmental Science:Nano, 2021, 8(11):3098-30109.
[62]	CHAKRABORTY D, ETHIRAJ K R, CHANDRASEKARAN N, et al. Mitigating the toxic effects of CdSe quantum dots towards freshwater alga Scenedesmus obliquus:role of eco-corona[J]. Environmental Pollution, 2021, 270:116049.
[63]	FADARE O O, WAN B, LIU K Y, et al. Eco-corona vs protein corona:effects of humic substances on corona formation and nanoplastic particle toxicity in Daphnia magna[J]. Environmental Science&Technology, 2020, 54(13):8001-8019.
[64]	JIA Y Y, HOU X, WANG Z W, et al. Machine learning boosts the design and discovery of nanomaterials[J]. ACS Sustainable Chemistry&Engineering, 2021, 9(18):6130-6147.
[65]	TAO H C, WU T Y, ALDEGHI M, et al. Nanoparticle synthesis assisted by machine learning[J]. Nature Reviews Materials, 2021, 6(8):701-716.
[66]	KARAKUS C O, WINKLER D A. Overcoming roadblocks in computational roadmaps to the future for safe nanotechnology[J]. Nano Futures, 2021, 5(2).
[67]	LI Y, PU Q, LI S, et al. Machine learning methods for research highlight prediction in biomedical effects of nanomaterial application[J]. Pattern Recognition Letters, 2019, 117:111-118.
[68]	BASEI G, HRISTOZOV D, LAMON L, et al. Making use of available and emerging data to predict the hazards of engineered nanomaterials by means of in silico tools:a critical review[J]. Nanoimpact, 2019, 13:76-99.
[69]	YAN X, 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.
[70]	TO K T, TRUONG L, EDWARDS S, et al. Multivariate modeling of engineered nanomaterial features associated with developmental toxicity (vol 16C, 100185, 2019)[J]. Nanoimpact, 2021, 21.
[71]	YAN X L, SEDYKH A, WANG W Y, et al. Construction of a web-based nanomaterial database by big data curation and modeling friendly nanostructure annotations[J]. Nature Communications, 2020, 11(1):2519.
[72]	SUN S, DENG P, MU L, et al. Bionanoscale recognition underlies cell fate and therapy[J]. Advanced Healthcare Materials, 2021, 10(22).