簡易檢索 / 詳目顯示

回結果列表
研究生： 馮樂怡
Fong, Lok-I
論文名稱： 應用定量活性結構關係於評估國內重要化學物質之水生急毒性
Application of Quantitative Structure-Activity Relationships to Evaluate the Aquatic Acute Toxicity for Chemical Substance of National Importance in Taiwan
指導教授： 侯文哲
Hou, Wen-Che
學位類別： 碩士
Master
系所名稱： 工學院 - 環境工程學系
Department of Environmental Engineering
論文出版年： 2020
畢業學年度： 108
語文別： 中文
論文頁數： 132
中文關鍵詞： 定量活性結構關係 、水生急毒性 、人工智慧運算 、國內重要化學物質 、OECD驗證原則
外文關鍵詞： Quantitative Structure Activity Relationship, Aquatic Acute Toxicity, Artificial Intelligence Algorithm, Chemical Substance of National Importance, OECD validation principle
相關次數： 點閱：76  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 為了加強國內化學物質源頭管理之目的，修訂並施行「新化學物質及既有化學物質資料登錄辦法」，辦法實行至今，特別彙集到106種化學物質為國內流通較廣、潛在危害較高與資訊較缺乏之物質資料，並指定106種化學物質應完成既有化學物質標準登錄。
    目前有關登錄的相關資料都以傳統的動物實驗為主，尤其是生態毒理資訊，這不但增加了提交化學物質資料的難度，同時違背了3R原則「取代（Replace）」、「減量（Reduce）」、及實驗「精緻化（Refine）」，因此，為減少動物測試實驗與降低登錄資料繳交的難度，同時提供可以信賴的生態毒性登錄資料，建議可以提高非動物測試替代方法的定量活性結構關係（Quantitative Structure-Activity Relationships，QSARs）的使用。
    本研究目的為評估Danish QSAR Database、ECOSAR、T.E.S.T、VEGA與利用人工智慧運算自行研發的QSAR模型，在預測106種國內重要化學物質水生急毒的預測性和可靠性。其中，預測性的判別會以QSAR的預測值與實驗值的相關性與是否落在相同台灣水生急毒性級別中，而可靠性則是以經濟合作與發展組織驗證QSAR模型的原則來驗證自建的QSAR模型。
    研究結果發現ECOSAR在不同水生急毒性預測上有較好的表現，並認為人工智慧運算在定量活性結構關係模型的預測上還需要多加研究。

    In order to strengthen the source management of chemical in Taiwan, the Presidential Order promulgated a revision of the Regulations of New and Existing Chemical Substances Registration. Since its implementation, 106 chemical substances have been collected for domestic circulation, high potential harm and lack of material information. Therefore, 106 chemical substances should complete the standard registration of existing chemical substance.
    The aim of this study is to evaluate the predictability and feasibility of Danish QSAR Database, ECOSAR, T.E.S.T and VEGA, and the QSAR model developed by artificial intelligence algorithm in predicting the aquatic acute toxicity of 106 domestic important chemicals.
    The results of the study found that ECOSAR has a good performance in the prediction of different acute aquatic acute toxicity and believes that artificial intelligence needs more research on the prediction of QSAR models.

    摘要 I SUMMARY II 表目錄 IX 圖目錄 X 第一章 緒論 1 1.1 研究背景與動機 1 1.2 研究目的 2 第二章 文獻回顧 3 2.1 國際化學物質管理與登錄制度發展趨勢 3 2.2 我國化學物質管理與登錄制度概況 4 2.3 資訊繳交與替代方法 5 2.4 國際間對QSAR模型的監管認可 7 2.4.1 美國 7 2.4.2 歐盟 9 2.5 定量活性結構關係（QSAR） 11 2.5.1 QSAR的定義 12 2.5.2 QSAR在環境科學上的發展 13 2.5.3 既有QSAR模型的介紹 15 2.5.3.1 Danish QSAR Database 16 2.5.3.2 ECOSAR 18 2.5.3.3 T.E.S.T 19 2.5.3.4 VEGA 21 2.6 OECD驗證QSAR模型五大原則 23 2.6.1 明確的測試終點 23 2.6.2 明確的演算法 24 2.6.3 模型的適用範疇 24 2.6.4 模型的擬合程度、穩健性和預測性 25 2.6.5 機制的闡述 26 2.7 人工智慧運算預測毒理的發展 27 2.7.1 隨機森林（Random Forest） 27 2.7.2 支持向量機法（Support Vector Machines，SVM） 36 2.8 台灣水生急毒性的級別 40 第三章 研究方法 42 3.1 研究方法流程架構 42 3.2 實驗數據收集與整理 43 3.3 既有QSAR模型預測 44 3.3.1 Danish QSAR database 45 3.3.2 ECOSAR 45 3.3.3 T.E.S.T 46 3.3.4 VEGA 47 3.4 人工智慧運算模型建立與預測執行 48 3.4.1 隨機森林 48 3.4.2 支持向量機法 50 3.5 評估模型的預測能力 50 3.5.1 相關係數，r2 51 3.5.2 QSAR模型中可預測數、正確分級數與正確分級率 51 3.6 驗證QSAR模型 52 3.6.1 推估之測試終點（OECD 原則1） 52 3.6.2 明確的演算法（OECD 原則2） 52 3.6.3 適用範圍（OECD原則3） 52 3.6.4 模型的擬合程度、穩健性和預測性（OECD 原則4） 52 3.6.4.1 決定係數，R2 53 3.6.4.2 均方誤差，MSE 55 3.6.4.3 均方根誤差，RMSE 55 3.6.5 機制的闡述（OECD 原則5） 55 第四章 結果與討論 56 4.1 評估模型的預測能力 56 4.1.1 預測魚類水生急毒性QSAR模型 56 4.1.2 預測水蚤水生急毒性QSAR模型 60 4.1.3 預測藻類水生急毒性QSAR模型 63 4.2 驗證QSAR模型 67 4.2.1 隨機森林 67 4.2.1.1 推估之測試終點 67 4.2.1.2 明確的演算法 67 4.2.1.3 適用範圍 68 4.2.1.4 模型的擬合程度、穩健性和預測性 69 4.2.1.5 機制的闡述 69 4.2.2 支持向量機法 70 4.2.2.1 推估之測試終點 70 4.2.2.2 明確的演算法 70 4.2.2.3 適用範圍 70 4.2.2.4 模型的擬合程度、穩健性和預測性 71 4.2.2.5 機制的闡述 71 第五章 結論 72 5.1 結論 72 5.2 建議 73 參考文獻 74 附錄 81

    (1) 化學物質登錄制度的必要性 - 化學物質登錄平臺2.0 https://tcscachemreg.epa.gov.tw/Epareg/content/Introduction/Page1_1.aspx (accessed May 8, 2020).
    (2) US EPA, O. Actions under TSCA Section 5 https://www.epa.gov/reviewing-new-chemicals-under-toxic-substances-control-act-tsca/actions-under-tsca-section-5 (accessed May 8, 2020).
    (3) Williams, E. S.; Panko, J.; Paustenbach, D. J. The European Union’s REACH Regulation: A Review of Its History and Requirements. Critical Reviews in Toxicology 2009, 39 (7), 553–575. https://doi.org/10.1080/10408440903036056.
    (4) 新化學物質及既有化學物質資料登錄辦法-全國法規資料庫 https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=O0060043 (accessed May 8, 2020).
    (5) 李政憲. 107 年化學物質登錄制度精進措施專案計畫; 研究報告 TCSB-107-EM01-02-A014; 毒物及化學物質局, 2018.
    (6) 評估管理組毒物及化學物質局. 環保署預告「新化學物質及既有化學物質資料登錄辦法」修正草案 https://www.tcsb.gov.tw/cp-21-2737-ab826-1.html (accessed May 8, 2020).
    (7) ECHA, M. Guidance on Information Requirements and Chemical Safety Assessment. Chapter R 2008, 8.
    (8) US EPA, O. Toxic Substances Control Act (TSCA) and Federal Facilities https://www.epa.gov/enforcement/toxic-substances-control-act-tsca-and-federal-facilities (accessed Aug 24, 2020).
    (9) ZEEMAN, M. G. Ecotoxicity Testing and Estimation Methods Developed under Section 5 of the Toxic Substances Control Act (TSCA). Fundamentals of Aquatic Toxicology : Effects, Environmental Fate, and Risk Assessment 1995, 703–715.
    (10) Zeeman, M.; Rodier, D.; Nabholz, J. V.; Lynch, D. G.; Macek, G. J.; Sherlock, S. M.; Wright, R. Ecological Risks of New Industrial Chemicals under TSCA. Ecological risk assessment in the Federal Government 1999.
    (11) Directive, C. 79/831/EEC of 18 September 1979 Amending for the Sixth Time Directive 67/548/EEC on the Approximation of the Laws, Regulations and Administrative Provisions Relating to the Classification, Packaging and Labelling of Dangerous Substances. Official Journal L 1979, 259 (15), 10.
    (12) [annexXI] REACH - Registration, Evaluation, Authorisation and Restriction of Chemicals https://reachonline.eu/REACH/EN/REACH_EN/articleXI.html (accessed May 28, 2020).
    (13) OECD. Guidance Document on the Validation and International Acceptance of New or Updated Test Methods for Hazard Assessment. ENV/JM/MONO (2005) 14; Organisation for Economic Co-operation and Development Paris, France, 2005; Vol. 34.
    (14) QSAR models - Models for ecotoxicology and toxicology https://sites.google.com/site/modelecotoxtox/models-and-tools/qsar-qspr-model (accessed May 9, 2020).
    (15) Babbage, C. The Ninth Bridgewater Treatise: A Fragment; J. Murray, 1838.
    (16) Hansch, Corwin.; Muir, R. M.; Fujita, Toshio.; Maloney, P. P.; Geiger, Fred.; Streich, Margaret. The Correlation of Biological Activity of Plant Growth Regulators and Chloromycetin Derivatives with Hammett Constants and Partition Coefficients. J. Am. Chem. Soc. 1963, 85 (18), 2817–2824. https://doi.org/10.1021/ja00901a033.
    (17) Meylan, W. M.; Howard, P. H. Atom/Fragment Contribution Method for Estimating Octanol–Water Partition Coefficients. Journal of Pharmaceutical Sciences 1995, 84 (1), 83–92. https://doi.org/10.1002/jps.2600840120.
    (18) Hansch, C. Quantitative Approach to Biochemical Structure-Activity Relationships. Acc. Chem. Res. 1969, 2 (8), 232–239. https://doi.org/10.1021/ar50020a002.
    (19) Neely, W. B.; Branson, D. R.; Blau, G. E. Partition Coefficient to Measure Bioconcentration Potential of Organic Chemicals in Fish. Environ. Sci. Technol. 1974, 8 (13), 1113–1115. https://doi.org/10.1021/es60098a008.
    (20) Könemann, H. Quantitative Structure-Activity Relationships in Fish Toxicity Studies. Part 1: Relationship for 50 Industrial Pollutants. Toxicology 1981, 19 (3), 209–221. https://doi.org/10.1016/0300-483x(81)90130-x.
    (21) ECHA. Practical Guide: How to Use Alternatives to Animal Testing to Fulfil Your Information Requirements for REACH Registration; European Chemicals Agency Helsinki, 2016.
    (22) ECHA. Practical Guide:How to Use and Report (Q)SARs; European Chemicals Agency Helsinki, 2016.
    (23) Danish (Q)SAR Database http://qsar.food.dtu.dk/ (accessed Aug 24, 2020).
    (24) Enterprise, L. Leadscope Inc. Columbus, OH 2007.
    (25) Chakravarti, S. K.; Saiakhov, R. D.; Klopman, G. Optimizing Predictive Performance of CASE Ultra Expert System Models Using the Applicability Domains of Individual Toxicity Alerts. J. Chem. Inf. Model. 2012, 52 (10), 2609–2618. https://doi.org/10.1021/ci300111r.
    (26) US EPA, O. Ecological Structure Activity Relationships (ECOSAR) Predictive Model https://www.epa.gov/tsca-screening-tools/ecological-structure-activity-relationships-ecosar-predictive-model (accessed Aug 24, 2020).
    (27) ECOTOX | Home https://cfpub.epa.gov/ecotox/ (accessed Jun 27, 2020).
    (28) US EPA, O. Toxicity Estimation Software Tool (TEST) https://www.epa.gov/chemical-research/toxicity-estimation-software-tool-test (accessed Aug 24, 2020).
    (29) Romesburg, H. C. Cluster Analysis for Researchers (Belmont, CA: Lifetime Learning Publications. RomesburgCluster Analysis for Researchers1984 1984.
    (30) Contrera, J. F.; Matthews, E. J.; Daniel Benz, R. Predicting the Carcinogenic Potential of Pharmaceuticals in Rodents Using Molecular Structural Similarity and E-State Indices. Regulatory Toxicology and Pharmacology 2003, 38 (3), 243–259. https://doi.org/10.1016/S0273-2300(03)00071-0.
    (31) Chemistry Development Kit https://cdk.github.io/ (accessed Aug 24, 2020).
    (32) VEGA QSAR – VEGA HUB https://www.vegahub.eu/portfolio-item/vega-qsar/ (accessed Aug 24, 2020).
    (33) Benfenati, E.; Manganaro, A.; Gini, G. C. VEGA-QSAR: AI Inside a Platform for Predictive Toxicology. In PAI@ AI* IA; 2013; pp 21–28.
    (34) Lm, S.; X, L.; Y, W.; Jj, L.; Xh, W.; Lx, S.; Yh, Z. The Discrimination of Excess Toxicity from Baseline Effect: Effect of Bioconcentration. Sci Total Environ 2014, 484, 137–145. https://doi.org/10.1016/j.scitotenv.2014.03.040.
    (35) Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes - 1st Edition https://www.elsevier.com/books/quantitative-structure-activity-relationships-qsar-for-pesticide-regulatory-purposes/benfenati/978-0-444-52710-3 (accessed Jul 2, 2020).
    (36) OECD, O. Environment Health and Safety Publications Series on Testing and Assessment No. 58. Report on the Regulatory Uses and Applications in OECD Member Countries of (Quantitative) Structure-Activity Relationship ((Q) SAR) Models in the Assessment of New and Existing Chemicals 2006, 1–79.
    (37) Bopp, S. K.; Barouki, R.; Brack, W.; Dalla Costa, S.; Dorne, J.-L. C. M.; Drakvik, P. E.; Faust, M.; Karjalainen, T. K.; Kephalopoulos, S.; van Klaveren, J.; Kolossa-Gehring, M.; Kortenkamp, A.; Lebret, E.; Lettieri, T.; Nørager, S.; Rüegg, J.; Tarazona, J. V.; Trier, X.; van de Water, B.; van Gils, J.; Bergman, Å. Current EU Research Activities on Combined Exposure to Multiple Chemicals. Environment International 2018, 120, 544–562. https://doi.org/10.1016/j.envint.2018.07.037.
    (38) Lu, H.; Li, Y.; Chen, M.; Kim, H.; Serikawa, S. Brain Intelligence: Go beyond Artificial Intelligence. Mobile Netw Appl 2018, 23 (2), 368–375. https://doi.org/10.1007/s11036-017-0932-8.
    (39) Hopfield, J. J. Neural Networks and Physical Systems with Emergent Collective Computational Abilities. PNAS 1982, 79 (8), 2554–2558. https://doi.org/10.1073/pnas.79.8.2554.
    (40) Tin Kam Ho. Random Decision Forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition; 1995; Vol. 1, pp 278–282 vol.1. https://doi.org/10.1109/ICDAR.1995.598994.
    (41) Ho, T. K. The Random Subspace Method for Constructing Decision Forests. IEEE transactions on pattern analysis and machine intelligence 1998, 20 (8), 832–844.
    (42) Breiman, L. Random Forests. Machine learning 2001, 45 (1), 5–32.
    (43) Breiman, L. Statistical Modeling: The Two Cultures (with Comments and a Rejoinder by the Author). Statistical science 2001, 16 (3), 199–231.
    (44) Iverson, L. R.; Prasad, A. M.; Matthews, S. N.; Peters, M. Estimating Potential Habitat for 134 Eastern US Tree Species under Six Climate Scenarios. Forest Ecology and Management 2008, 254 (3), 390–406.
    (45) Mutanga, O.; Adam, E.; Cho, M. A. High Density Biomass Estimation for Wetland Vegetation Using WorldView-2 Imagery and Random Forest Regression Algorithm. International Journal of Applied Earth Observation and Geoinformation 2012, 18, 399–406.
    (46) Vapnik, V. N. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks 1999, 10 (5), 988–999. https://doi.org/10.1109/72.788640.
    (47) 行政院勞工委員會. 行政院勞工委員會勞工安全衛生處-配合化學品全球調和制度(GHS)之工作場所化學品管理計畫. GHS 電子報 2008, No. 8.
    (48) GHS化學品全球調和制度 https://ghs.osha.gov.tw/CHT/masterpage/index_CHT.aspx (accessed May 6, 2020).
    (49) Test No. 203: Fish, Acute Toxicity Test https://www.oecd-ilibrary.org/environment/test-no-203-fish-acute-toxicity-test_9789264069961-en (accessed May 6, 2020).
    (50) Test No. 202: Daphnia sp. Acute Immobilisation Test https://www.oecd-ilibrary.org/environment/test-no-202-daphnia-sp-acute-immobilisation-test_9789264069947-en (accessed May 6, 2020).
    (51) Test No. 201: Freshwater Alga and Cyanobacteria, Growth Inhibition Test https://www.oecd-ilibrary.org/environment/test-no-201-alga-growth-inhibition-test_9789264069923-en (accessed May 6, 2020).
    (52) Jia, Q.; Zhao, Y.; Yan, F.; Wang, Q. QSAR Model for Predicting the Toxicity of Organic Compounds to Fathead Minnow. Environ Sci Pollut Res 2018, 25 (35), 35420–35428. https://doi.org/10.1007/s11356-018-3434-8.
    (53) Strobl, C.; Boulesteix, A.-L.; Zeileis, A.; Hothorn, T. Bias in Random Forest Variable Importance Measures: Illustrations, Sources and a Solution. BMC bioinformatics 2007, 8 (1), 25.
    (54) Hothorn, T.; Hornik, K.; Zeileis, A. Unbiased Recursive Partitioning: A Conditional Inference Framework. Journal of Computational and Graphical statistics 2006, 15 (3), 651–674.
    (55) Kuncheva, L. I.; Whitaker, C. J. Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy. Machine Learning 2003, 51 (2), 181–207. https://doi.org/10.1023/A:1022859003006.
    (56) Breiman, L.; Cutler, A.; Liaw, A.; Wiener, M. RandomForest: Breiman’s Random Forest for Classification and Regression. Fortran original by Leo Breiman and Adele Cutler and R port by Andy Liaw and Matthew Wiener. R package 2003, 4–3.
    (57) Kohavi, R. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. International Joint Conference on Artificial Intelligence. Available from Internet: https://www. semanticscholar. org/search 1995.
    (58) Häne, B. G.; Jäger, K.; Drexler, H. G. The Pearson Product-Moment Correlation Coefficient Is Better Suited for Identification of DNA Fingerprint Profiles than Band Matching Algorithms. Electrophoresis 1993, 14 (1), 967–972.
    (59) Coe, A.; Janusch, R. A.; Triebe, J.; Worth, A.; European Commission; Joint Research Centre. JRC QSAR Model Database: EURL ECVAM Database Service on Alternative Methods to Animal Experimentation : To Promote the Development and Uptake of Alternative and Advanced Methods in Toxicology and Biomedical Sciences : User Support & Tutorial.; 2017.
    (60) Nagelkerke, N. J. A Note on a General Definition of the Coefficient of Determination. Biometrika 1991, 78 (3), 691–692.
    (61) Miles, J. R Squared, Adjusted R Squared. Wiley StatsRef: Statistics Reference Online 2014.
    (62) Frost, J. Multiple Regression Analysis: Use Adjusted R-Squared and Predicted R-Squared to Include the Correct Number of Variables. Minitab Blog 2013, 13 (6).
    (63) Willmott, C. J.; Matsuura, K. Advantages of the Mean Absolute Error (MAE) over the Root Mean Square Error (RMSE) in Assessing Average Model Performance. Climate research 2005, 30 (1), 79–82.
    (64) Chai, T.; Draxler, R. R. Root Mean Square Error (RMSE) or Mean Absolute Error (MAE)?–Arguments against Avoiding RMSE in the Literature. Geoscientific model development 2014, 7 (3), 1247–1250.
    (65) Zhu, H.; Tropsha, A.; Fourches, D.; Varnek, A.; Papa, E.; Gramatica, P.; Oberg, T.; Dao, P.; Cherkasov, A.; Tetko, I. V. Combinatorial QSAR Modeling of Chemical Toxicants Tested against Tetrahymena Pyriformis. J Chem Inf Model 2008, 48 (4), 766–784. https://doi.org/10.1021/ci700443v.
    (66) Akers, K. S.; Sinks, G. D.; Schultz, T. W. Structure–Toxicity Relationships for Selected Halogenated Aliphatic Chemicals. Environmental toxicology and pharmacology 1999, 7 (1), 33–39.
    (67) ChemIDplus Advanced - Chemical information with searchable synonyms, structures, and formulas https://chem.nlm.nih.gov/chemidplus/ (accessed Jun 27, 2020).
    (68) Dimitrov, S.; Dimitrova, N.; Parkerton, T.; Comber, M.; Bonnell, M.; Mekenyan, O. Base-Line Model for Identifying the Bioaccumulation Potential of Chemicals. SAR and QSAR in Environmental Research 2005, 16 (6), 531–554.
    (69) Arnot, J. A.; Gobas, F. A. A Review of Bioconcentration Factor (BCF) and Bioaccumulation Factor (BAF) Assessments for Organic Chemicals in Aquatic Organisms. Environ. Rev. 2006, 14 (4), 257–297. https://doi.org/10.1139/a06-005.
    (70) Zhao, C.; Boriani, E.; Chana, A.; Roncaglioni, A.; Benfenati, E. A New Hybrid System of QSAR Models for Predicting Bioconcentration Factors (BCF). Chemosphere 2008, 73 (11), 1701–1707. https://doi.org/10.1016/j.chemosphere.2008.09.033.
    (71) Briggs, G. G.; Freeman, R. K.; Yaffe, S. J. Metronidazole. Drugs in pregnancy and lactation, 3rd ed. The Williams & Wilkins Co., Baltimore, Md 1990, 430–433.
    (72) Shepard, T. H.; Lemire, R. J. Catalog of Teratogenic Agents; JHU Press, 2004.
    (73) Hansen, K.; Mika, S.; Schroeter, T.; Sutter, A.; Ter Laak, A.; Steger-Hartmann, T.; Heinrich, N.; Müller, K.-R. Benchmark Data Set for in Silico Prediction of Ames Mutagenicity. Journal of chemical information and modeling 2009, 49 (9), 2077–2081.
    (74) US EPA, O. Predictive Models and Tools for Assessing Chemicals under the Toxic Substances Control Act (TSCA) https://www.epa.gov/tsca-screening-tools (accessed Jun 27, 2020).
    (75) LookChem,look for chemicals all over the world. https://www.lookchem.com/ (accessed Jun 27, 2020).
    (76) Jasper, J. J. The Surface Tension of Pure Liquid Compounds. Journal of physical and chemical reference data 1972, 1 (4), 841–1010.
    (77) Viswanath, D. S.; Natavajan, G. Data Book on the Viscosity of Liquids. 1989.
    (78) Riddick, J. A.; Bunger, W. B.; Sakano, T. K. Organic Solvents: Physical Properties and Methods of Purification. 1986.
    (79) Jamieson, D. T.; Irving, J. B.; Tudhope, J. S. Liquid Thermal Conductivity: A Data Survey to 1973; HM Stationery Office, 1975.
    (80) Vargaftik, N. B.; Filippov, L. P.; Tarzimanov, A. A.; Totskii, E. E. Thermal Conductivity of Liquids and Gases. Standartov, Moscow 1978.

    無法下載圖示 校內：2025-08-28公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE