构建有机化合物斑马鱼雌激素干扰效应的二元分类模型
|
摘要
计算毒理学方法已成为辅助内分泌干扰物(EDCs)管理的决策支持工具。因此,发展内分泌干扰效应指标的(定量)结构活性关系((Q) SAR)等预测模型对于实现EDCs环境管理具有重要的意义。在雌激素受体(Q) SAR模型研究方面,目前主要针对人、牛、大鼠和小鼠等物种的雌激素受体干扰效应进行了研究,而对鱼等水生生物雌激素受体干扰效应等指标的(Q)SAR模型研究还较少。本研究采用基于欧几里德距离的K最近邻(k NN)分类算法,构建了斑马鱼雌激素受体干扰效应的二元分类模型。结果表明,2个最优模型训练集和验证集的预测准确度(Q)、敏感性(Sn)和特异性(Sp)参数均大于0.93,说明模型具有较好的预测能力。因此,能够用所建模型填补模型应用域内其他化合物缺失的斑马鱼雌激素受体干扰效应定性数据。
Computational toxicology method has been a critical decision support tool for the management of endocrine disrupting chemicals(EDCs). Thus,it is of vital importance to develop the predictive models e.g.(quantitative) structure-activity relationship((Q) SAR) for EDCs environmental management. For the available(Q) SAR models for estrogen receptor up to now,only the estrogenic activity of four species such as calf,rat,mouse,and human were modeled. While the(Q) SAR models for aquatic organisms e.g. fish were still less. Here,the binary classification models for predicting the estrogenic activity of zebrafish was attempted to construct employing the K nearest neighbor(k NN) classification algorithm based on Euclidean distance. The modeling results indicated that all of the prediction accuracy(Q),sensitivity(Sn) and specificity(Sp) of training sets and validation sets for the two optimal models are greater than 0.93,indicating that the models have good prediction ability. Therefore,the missing estrogenic activity data gap for other organic compounds within the application domain of derived models on their missing estrogenic activity data could be filled.
Computational toxicology method has been a critical decision support tool for the management of endocrine disrupting chemicals(EDCs). Thus,it is of vital importance to develop the predictive models e.g.(quantitative) structure-activity relationship((Q) SAR) for EDCs environmental management. For the available(Q) SAR models for estrogen receptor up to now,only the estrogenic activity of four species such as calf,rat,mouse,and human were modeled. While the(Q) SAR models for aquatic organisms e.g. fish were still less. Here,the binary classification models for predicting the estrogenic activity of zebrafish was attempted to construct employing the K nearest neighbor(k NN) classification algorithm based on Euclidean distance. The modeling results indicated that all of the prediction accuracy(Q),sensitivity(Sn) and specificity(Sp) of training sets and validation sets for the two optimal models are greater than 0.93,indicating that the models have good prediction ability. Therefore,the missing estrogenic activity data gap for other organic compounds within the application domain of derived models on their missing estrogenic activity data could be filled.
引文
[1] Kwiatkowski C F,Bolden A L,Liroff R A,et al. Twenty-five years of endocrine disruption science:Remembering Theo Colborn[J]. Environmental Health Perspectives,2016,124(9):A151-A154
[2] Gore A C,Chappell V A,Fenton S E,et al. EDC-2:The endocrine society’s second scientific statement on endocrine-disrupting chemicals[J]. Endocrine Reviews,2015,36(6):E1-E150
[3]杨先海，刘会会，刘济宁，等．国外环境内分泌干扰物管控现状及我国的对策[J]．生态与农村环境学报，2018,34(2):104-113Yang X H,Liu H H,Liu J N,et al. Statusquo of management of endocrine disrupting chemicals in abroad and corresponding strategies for China[J]. Journal of Ecology and Rural Environment,2018,34(2):104-113(in Chinese)
[4] U. S. Environmental Protection Agency. Addendum endocrine disruptor screening and testing advisory committee[R]. Washington DC:U. S. Environmental Protection Agency,1998
[5] European Commission. Commission delegated regulation(EU)2017/2100 of 4 September 2017 setting out scientific criteria for the determination of endocrine-disrupting properties pursuant to regulation(EU)No 528/2012 of the European Parliament and Council(Text with EEA relevance)[S]. Brussels:European Union,2017
[6] European Commission. Commission regulation(EU)2018/605 of 19 April 2018 amending annexⅡto regulation(EC)No 1107/2009 by setting out scientific criteria for the determination of endocrine disrupting properties(Text with EEA relevance)[S]. Brussels:European Union,2018
[7] Organization for Economic Co-Operation and Development(OECD). Revised guidance document 150 on standardised test guidelines for evaluating chemicals for endocrine disruption[R]. Paris:OECD,2018
[8] United Nations Environment Programme/World Health Organization. State of the science of endocrine disrupting chemicals[R]. Geneva:United Nations Environment Programme/World Health Organization(UNEP/WHO),2013
[9]中华人民共和国国务院．国务院关于印发水污染防治行动计划的通知国发[2015]17号[S]．北京:中华人民共和国国务院，2015
[10] U. S. Environmental Protection Agency. Use of high throughput assays and computational tools; endocrine disruptor screening program; notice of availability and opportunity for comment federal register[S]. Washington DC:U. S. Environmental Protection Agency,2015
[11] Chen Q C,Tan H Y,Yu H X,et al. Activation of steroid hormone receptors:Shed light on the in silico evaluation of endocrine disrupting chemicals[J]. Science of the Total Environment,2018,631-632:27-39
[12] Sakkiah S,Guo W J,Pan B H,et al. Computational prediction models for assessing endocrine disrupting potential of chemicals[J]. Journal of Environmental Science and Health. Part C,2018,36(4):192-218
[13] Yang X H,Liu H H,Kusko R. Molecular Modeling Method Applications:Probing the Mechanism of Endocrine Disruptor Action[M]//Hong H(eds). Advances in Computational Toxicology. Challenges and Advances in Computational Chemistry and Physics. Cham:Springer,2019:315-335
[14] Li F,Xie Q,Li X H,et al. Hormone activity of hydroxylated polybrominated diphenyl ethers on human thyroid receptorbeta:in vitro and in silico investigations[J].Environmental Health Perspectives,2010,118:602-606
[15] Yu H Y,Wondrousch D,Li F,et al. In silico investigation of the thyroid hormone activity of hydroxylated polybrominated diphenyl ethers[J]. Chemical Research in Toxicology,2015,28(8):1538-1545
[16] Mansouri K,Abdelaziz A,Rybacka A,et al. CERAPP:Collaborative estrogen receptor activity prediction project[J]. Environmental Health Perspectives,2016,124(7):1023-1033
[17] Ding K K,Kong X T,Wang J P,et al. Side chains of parabens modulate antiandrogenic activity:in vitro and molecular docking studies[J]. Environmental Science&Technology,2017,51(11):6452-6460
[18] Lu L,Zhan T,Ma M,et al. Thyroid disruption by bisphenol S analogues via thyroid hormone receptorβ:in vitro,in vivo,and molecular dynamics simulation study[J]. Environmental Science&Technology,2018,52(11):6617-6625
[19]陈景文，王中钰，付志强．环境计算化学与毒理学[M]．北京:科学出版社，2018:255-257
[20] He J Y,Peng T,Yang X H,et al. Development of QSAR models for predicting the binding affinity of endocrine disrupting chemicals to eight fish estrogen receptor[J]. Ecotoxicology and Environmental Safety,2018,148:211-219
[21] Lin S Y,Yang X H,Liu H H. Development of liposome/water partition coefficients predictive models for neutral and ionogenic organic chemicals[J]. Ecotoxicology and Environmental Safety,2019,179:40-49
[22] Costache A D,Pullela P K,Kasha P,et al. Homologymodeled ligand-binding domains of zebrafish estrogen receptors alpha,beta1,and beta2:From in silico to in vivo studies of estrogen interactions in Danio rerio as a model system[J]. Molecular Endocrinology,2005,19(12):2979-2990
[23] Segner H,Casanova-Nakayama A,Kase R,et al. Impact of environmental estrogens on Yfish considering the diversity of estrogen signaling[J]. General and Comparative Endocrinology,2013,191:190-201
[24] U. S. Environmental Protection Agency(US EPA). Estimation Programs Interface SuiteTMfor Microsoft Windows,v 4.10[CP]. Washington DC:US EPA,2012
[25] James J P. Stewart Computational Chemistry[CP]. Colorado Springs,CO:James Stewart,2016
[26] Talete S R L. Dragon(Software for Molecular Descriptor Calculation)Version 6.0[CP]. Milano:Talete,2012
[27] Liu H H,Yang X H,Lu R. Development of classification model and QSAR model for predicting binding affinity of endocrine disrupting chemicals to human sex hormonebinding globulin[J]. Chemosphere,2016,156:1-7
[28] Ding F,Wang Z,Yang X H,et al. Development of classification models for predicting chronic toxicity of chemicals to Daphnia magna and Pseudokirchneriella subcapitata[J]. SAR and QSAR in Environmental Research,2019,30(1):39-50
[29] Liu H H,Yang X H,Yin C,et al. Development of predictive models for predicting binding affinity of endocrine disrupting chemicals to fish sex hormone-binding globulin[J]. Ecotoxicology and Environmental Safety,2017,136:46-54
[30] Organization for Economic Co-Operation and Development(OECD). Guidance Document on the Validation of(Quantitative)Structure Activity Relationships[(Q)SAR] Models[R]. Paris:OECD,2007
[31] Tang W,Chen J W,Wang Z Y,et al. Deep learning for predicting toxicity of chemicals:A mini review[J].Journal of Environmental Science and Health. Part C,2018,36(4):252-271
[32] Sun L X,Yang H B,Cai Y C,et al. In silico prediction of endocrine disrupting chemicals using single-label and multilabel models[J]. Journal of Chemical Information and Modeling,2019,59(3):973-982
[33] Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters,2006,27:861-874
[34] Devinyak O,Havrylyuk D,Lesyk R. 3D-MoRSE descriptors explained[J]. Journal of Molecular Graphics and Modelling,2014,54:194-203
[35] Baba H,Takahara J,Mamitsuka H. In silico predictions of human skin permeability using nonlinear quantitative structure-property relationship models[J]. Pharmaceutical Research,2015,32(7):2360-2371
[36] Mansouri K,Ringsted T,Ballabio D,et al. Quantitative structure-activity relationship models for ready biodegradability of chemicals[J]. Journal of Chemical Information and Modeling,2013,53(4):867-878
[37] Consonni V,Todeschini R. Multivariate Analysis of Molecular Descriptors[M]//Dehmer M,Varmuza K,Bonchev D(eds.)Statistical Modelling of Molecular Descriptors in QSAR/QSPR. Weinheim:Wiley-VCH Verlag Gmb H&Co. KGa A,2012
[2] Gore A C,Chappell V A,Fenton S E,et al. EDC-2:The endocrine society’s second scientific statement on endocrine-disrupting chemicals[J]. Endocrine Reviews,2015,36(6):E1-E150
[3]杨先海，刘会会，刘济宁，等．国外环境内分泌干扰物管控现状及我国的对策[J]．生态与农村环境学报，2018,34(2):104-113Yang X H,Liu H H,Liu J N,et al. Statusquo of management of endocrine disrupting chemicals in abroad and corresponding strategies for China[J]. Journal of Ecology and Rural Environment,2018,34(2):104-113(in Chinese)
[4] U. S. Environmental Protection Agency. Addendum endocrine disruptor screening and testing advisory committee[R]. Washington DC:U. S. Environmental Protection Agency,1998
[5] European Commission. Commission delegated regulation(EU)2017/2100 of 4 September 2017 setting out scientific criteria for the determination of endocrine-disrupting properties pursuant to regulation(EU)No 528/2012 of the European Parliament and Council(Text with EEA relevance)[S]. Brussels:European Union,2017
[6] European Commission. Commission regulation(EU)2018/605 of 19 April 2018 amending annexⅡto regulation(EC)No 1107/2009 by setting out scientific criteria for the determination of endocrine disrupting properties(Text with EEA relevance)[S]. Brussels:European Union,2018
[7] Organization for Economic Co-Operation and Development(OECD). Revised guidance document 150 on standardised test guidelines for evaluating chemicals for endocrine disruption[R]. Paris:OECD,2018
[8] United Nations Environment Programme/World Health Organization. State of the science of endocrine disrupting chemicals[R]. Geneva:United Nations Environment Programme/World Health Organization(UNEP/WHO),2013
[9]中华人民共和国国务院．国务院关于印发水污染防治行动计划的通知国发[2015]17号[S]．北京:中华人民共和国国务院，2015
[10] U. S. Environmental Protection Agency. Use of high throughput assays and computational tools; endocrine disruptor screening program; notice of availability and opportunity for comment federal register[S]. Washington DC:U. S. Environmental Protection Agency,2015
[11] Chen Q C,Tan H Y,Yu H X,et al. Activation of steroid hormone receptors:Shed light on the in silico evaluation of endocrine disrupting chemicals[J]. Science of the Total Environment,2018,631-632:27-39
[12] Sakkiah S,Guo W J,Pan B H,et al. Computational prediction models for assessing endocrine disrupting potential of chemicals[J]. Journal of Environmental Science and Health. Part C,2018,36(4):192-218
[13] Yang X H,Liu H H,Kusko R. Molecular Modeling Method Applications:Probing the Mechanism of Endocrine Disruptor Action[M]//Hong H(eds). Advances in Computational Toxicology. Challenges and Advances in Computational Chemistry and Physics. Cham:Springer,2019:315-335
[14] Li F,Xie Q,Li X H,et al. Hormone activity of hydroxylated polybrominated diphenyl ethers on human thyroid receptorbeta:in vitro and in silico investigations[J].Environmental Health Perspectives,2010,118:602-606
[15] Yu H Y,Wondrousch D,Li F,et al. In silico investigation of the thyroid hormone activity of hydroxylated polybrominated diphenyl ethers[J]. Chemical Research in Toxicology,2015,28(8):1538-1545
[16] Mansouri K,Abdelaziz A,Rybacka A,et al. CERAPP:Collaborative estrogen receptor activity prediction project[J]. Environmental Health Perspectives,2016,124(7):1023-1033
[17] Ding K K,Kong X T,Wang J P,et al. Side chains of parabens modulate antiandrogenic activity:in vitro and molecular docking studies[J]. Environmental Science&Technology,2017,51(11):6452-6460
[18] Lu L,Zhan T,Ma M,et al. Thyroid disruption by bisphenol S analogues via thyroid hormone receptorβ:in vitro,in vivo,and molecular dynamics simulation study[J]. Environmental Science&Technology,2018,52(11):6617-6625
[19]陈景文，王中钰，付志强．环境计算化学与毒理学[M]．北京:科学出版社，2018:255-257
[20] He J Y,Peng T,Yang X H,et al. Development of QSAR models for predicting the binding affinity of endocrine disrupting chemicals to eight fish estrogen receptor[J]. Ecotoxicology and Environmental Safety,2018,148:211-219
[21] Lin S Y,Yang X H,Liu H H. Development of liposome/water partition coefficients predictive models for neutral and ionogenic organic chemicals[J]. Ecotoxicology and Environmental Safety,2019,179:40-49
[22] Costache A D,Pullela P K,Kasha P,et al. Homologymodeled ligand-binding domains of zebrafish estrogen receptors alpha,beta1,and beta2:From in silico to in vivo studies of estrogen interactions in Danio rerio as a model system[J]. Molecular Endocrinology,2005,19(12):2979-2990
[23] Segner H,Casanova-Nakayama A,Kase R,et al. Impact of environmental estrogens on Yfish considering the diversity of estrogen signaling[J]. General and Comparative Endocrinology,2013,191:190-201
[24] U. S. Environmental Protection Agency(US EPA). Estimation Programs Interface SuiteTMfor Microsoft Windows,v 4.10[CP]. Washington DC:US EPA,2012
[25] James J P. Stewart Computational Chemistry[CP]. Colorado Springs,CO:James Stewart,2016
[26] Talete S R L. Dragon(Software for Molecular Descriptor Calculation)Version 6.0[CP]. Milano:Talete,2012
[27] Liu H H,Yang X H,Lu R. Development of classification model and QSAR model for predicting binding affinity of endocrine disrupting chemicals to human sex hormonebinding globulin[J]. Chemosphere,2016,156:1-7
[28] Ding F,Wang Z,Yang X H,et al. Development of classification models for predicting chronic toxicity of chemicals to Daphnia magna and Pseudokirchneriella subcapitata[J]. SAR and QSAR in Environmental Research,2019,30(1):39-50
[29] Liu H H,Yang X H,Yin C,et al. Development of predictive models for predicting binding affinity of endocrine disrupting chemicals to fish sex hormone-binding globulin[J]. Ecotoxicology and Environmental Safety,2017,136:46-54
[30] Organization for Economic Co-Operation and Development(OECD). Guidance Document on the Validation of(Quantitative)Structure Activity Relationships[(Q)SAR] Models[R]. Paris:OECD,2007
[31] Tang W,Chen J W,Wang Z Y,et al. Deep learning for predicting toxicity of chemicals:A mini review[J].Journal of Environmental Science and Health. Part C,2018,36(4):252-271
[32] Sun L X,Yang H B,Cai Y C,et al. In silico prediction of endocrine disrupting chemicals using single-label and multilabel models[J]. Journal of Chemical Information and Modeling,2019,59(3):973-982
[33] Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters,2006,27:861-874
[34] Devinyak O,Havrylyuk D,Lesyk R. 3D-MoRSE descriptors explained[J]. Journal of Molecular Graphics and Modelling,2014,54:194-203
[35] Baba H,Takahara J,Mamitsuka H. In silico predictions of human skin permeability using nonlinear quantitative structure-property relationship models[J]. Pharmaceutical Research,2015,32(7):2360-2371
[36] Mansouri K,Ringsted T,Ballabio D,et al. Quantitative structure-activity relationship models for ready biodegradability of chemicals[J]. Journal of Chemical Information and Modeling,2013,53(4):867-878
[37] Consonni V,Todeschini R. Multivariate Analysis of Molecular Descriptors[M]//Dehmer M,Varmuza K,Bonchev D(eds.)Statistical Modelling of Molecular Descriptors in QSAR/QSPR. Weinheim:Wiley-VCH Verlag Gmb H&Co. KGa A,2012
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |