簡易檢索 / 詳目顯示
| 研究生： |
顏伯宇 Yen, Po-Yu |
|---|---|
| 論文名稱： |
比較多種基於機器學習的定量結構活性關係模型於預測水生急毒性之研究 A Study on the Comparison of Multiple Machine Learning-based Quantitative Structure-Activity Relationship Models in the Prediction of Acute Aquatic Toxicity |
| 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： | 2024 |
| 畢業學年度： | 112 |
| 語文別： | 英文 |
| 論文頁數： | 124 |
| 中文關鍵詞： | 生態毒理學 、新測試方法學 、定量結構活性關係 、機器學習 |
| 外文關鍵詞： | Ecotoxicology, New approach methodologies, QSAR, Machine learning |
| 相關次數： | 點閱：75 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 |
近年來，大量化學物質被製造及使用，因此化學物質管理及登錄受到大量關注，化學物質標準登錄需要繳交毒理和生態毒理資料，傳統毒理學和生態毒理學領域依賴動物試驗以獲取所需的評估數據。然而動物試驗通常耗費大量時間及金錢成本，且大規模的動物試驗也可能觸犯動物倫理，因此近年來全球對於3R原則(取代、減量、精緻化)的關注逐漸增加，在這種情況下新方法學(New Approach Methodologies、 NAMs)成為毒理學領域的一大亮點，其中定量活性結構關係(Quantitative Structure-Activity Relationships、QSARs)能快速填補數據空缺及操作簡單的優勢，已成為國際和台灣化學品監管以及毒性評估的重要工具。
本研究開發基於機器學習演算法的QSAR模型用於預測水生急毒性，並與文獻和國際認證公開的既有QSAR模型進行比較與探討，以及將本研究模型與既有QSAR模型用於預測國內106種重要既有化學物質，針對準確性進行評估，準確性評估是以模型預測值與實驗值之相關係數(rext2)以及是否落在相同Globally Harmonized System (GHS)水生急毒性分級(即正確分級率)進行判定。結果顯示，本研究QSAR模型之rext2與正確分級率在水蚤(0.58-0.61 和53.7%-66.7%)和藻類急毒性(0.51-0.58和60.0%-71.1%)相較既有QSAR模型有良好的表現，而魚類的正確分級率為69.6%，與正確分級率最高的既有QSAR模型(70.0%)表現相當。除此之外，為了更公平的比較本研究模型與既有模型之機器學習演算法的能力，我們利用既有QSAR建模數據進行本研究模型訓練，比較在相同建模數據下各演算法的預測表現。結果顯示，本研究的QSAR模型使用非線性演算法，其模型表現和預測表現與使用線性演算法的既有QSAR模型相比，並沒有顯著差異，說明模型表現並非只取決於演算法的能力，還包括建模數據數量、特徵的篩選以及適用範圍的界定。
The increasing focus on chemical management and registration has highlighted the need for toxicological data, traditionally obtained through costly and ethically problematic animal testing. This has driven global interest in the 3R principles (Replacement, Reduction, Refinement) and the adoption of New Approach Methodologies (NAMs), such as Quantitative Structure-Activity Relationships (QSARs), which offer efficient and ethical toxicity assessment solutions.
This study presents QSAR models developed in our lab using machine learning algorithms including eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) to predict acute fish, daphnia, and algae toxicity. Their performances were compared with those of publically available ones and from the literature. The national priority chemicals in Taiwan were further used as external chemicals to test model performances using standard statistic review based on the correlation coefficient (rext2) between predicted and experimental toxicity of external chemicals and corresponding toxicity classification rates (CRs). The results showed that our QSAR models demonstrated best performance with rext2 = 0.58-0.61 and CR = 53.7%-66.7% for daphnia EC50, and rext2 = 0.51-0.58 and CR = 60.0%-71.1% for algae EC50, compared to existing QSAR models with rext2 = 0.17-0.78 and CR = 15.4%-65.0% for daphnia EC50, and rext2 = 0.19-0.59 and CR = 32.2%-53.3% for algae EC50. CR = 69.6% of our fish toxicity prediction was comparable to 70.0% of the best existing QSAR model. Our models generally have wider applicability domains as shown by more predictable chemicals. Additionally, we also trained and compared models based on identical training set chemicals to examine the role of algorithms in the model performance. The result indicated that non-linear regression models using XGBoost, RF, and SVM do not necessarily perform better than linear regression or clustering ones. Our results suggest that while our QSAR models developed using non-linear regression ML algorithms showed overall improved acute aquatic toxicity predictions, the algorithms per se may not be the only factor.
(1) Singh, K. P.; Gupta, S.; Kumar, A.; Mohan, D. Multispecies QSAR Modeling for Predicting the Aquatic Toxicity of Diverse Organic Chemicals for Regulatory Toxicology. Chem. Res. Toxicol. 2014, 27 (5), 741–753. https://doi.org/10.1021/tx400371w.
(2) ECHA. Guidance on Information Requirements and Chemical Safety Assessment Chapter R.7b: Endpoint Specific Guidance, 2023.
(3) Russell, W. M. S.; Burch, R. L. The Principles of Humane Experimental Technique; Methuen, 1959.
(4) Toxicity Testing in the 21st Century: A Vision and a Strategy; National Academies Press: Washington, D.C., 2007. https://doi.org/10.17226/11970.
(5) Hartung, T.; Hoffmann, S. Food for Thought ... on in Silico Methods in Toxicology. ALTEX - Alternatives to animal experimentation 2009, 26 (3), 155–166. https://doi.org/10.14573/altex.2009.3.155.
(6) Mondou, M.; Hickey, G. M.; Rahman, H. T.; Maguire, S.; Pain, G.; Crump, D.; Hecker, M.; Basu, N. Factors Affecting the Perception of New Approach Methodologies (NAMs) in the Ecotoxicology Community. Integrated Environmental Assessment and Management 2020, 16 (2), 269–281. https://doi.org/10.1002/ieam.4244.
(7) Benfenati, E.; Roncaglioni, A.; Petoumenou, M. I.; Cappelli, C. I.; Gini, G. Integrating QSAR and Read-across for Environmental Assessment. SAR and QSAR in Environmental Research 2015, 26 (7–9), 605–618. https://doi.org/10.1080/1062936X.2015.1078408.
(8) 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 2022-05-10).
(9) US EPA, O. Toxicity Estimation Software Tool (TEST). https://www.epa.gov/chemical-research/toxicity-estimation-software-tool-test (accessed 2022-05-10).
(10) VEGA QSAR – VEGA HUB. https://www.vegahub.eu/portfolio-item/vega-qsar/ (accessed 2022-05-10).
(11) Danish QSAR Database. https://qsardb.food.dtu.dk/db/index.html (accessed 2022-05-09).
(12) European Chemicals Agency. How to Use and Report (Q)SARs.Practical Guide 5 .; Publications Office: LU, 2016.
(13) Moore, D. R. J.; Breton, R. L.; MacDonald, D. B. A Comparison of Model Performance for Six Quantitative Structure-Activity Relationship Packages That Predict Acute Toxicity to Fish. Environmental Toxicology and Chemistry 2003, 22 (8), 1799–1809. https://doi.org/10.1897/00-361.
(14) Reuschenbach, P.; Silvani, M.; Dammann, M.; Warnecke, D.; Knacker, T. ECOSAR Model Performance with a Large Test Set of Industrial Chemicals. Chemosphere 2008, 71 (10), 1986–1995. https://doi.org/10.1016/j.chemosphere.2007.12.006.
(15) Golbamaki, A.; Cassano, A.; Lombardo, A.; Moggio, Y.; Colafranceschi, M.; Benfenati, E. Comparison of in Silico Models for Prediction of Daphnia Magna Acute Toxicity. SAR and QSAR in Environmental Research 2014, 25 (8), 673–694. https://doi.org/10.1080/1062936X.2014.923041.
(16) Barros, R. P. C.; Sousa, N. F.; Scotti, L.; Scotti, M. T. Use of Machine Learning and Classical QSAR Methods in Computational Ecotoxicology. In Ecotoxicological QSARs; Roy, K., Ed.; Springer US: New York, NY, 2020; pp 151–175. https://doi.org/10.1007/978-1-0716-0150-1_7.
(17) Jeong, J.; Choi, J. Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications. Environ. Sci. Technol. 2022, 56 (12), 7532–7543. https://doi.org/10.1021/acs.est.1c07413.
(18) Lunghini, F.; Marcou, G.; Azam, P.; Enrici, M. H.; Van Miert, E.; Varnek, A. Consensus QSAR Models Estimating Acute Toxicity to Aquatic Organisms from Different Trophic Levels: Algae, Daphnia and Fish. SAR and QSAR in Environmental Research 2020, 31 (9), 655–675. https://doi.org/10.1080/1062936X.2020.1797872.
(19) Sheffield, T. Y.; Judson, R. S. Ensemble QSAR Modeling to Predict Multispecies Fish Toxicity Lethal Concentrations and Points of Departure. Environ. Sci. Technol. 2019, 53 (21), 12793–12802. https://doi.org/10.1021/acs.est.9b03957.
(20) Wu, Z.; Zhu, M.; Kang, Y.; Leung, E. L.-H.; Lei, T.; Shen, C.; Jiang, D.; Wang, Z.; Cao, D.; Hou, T. Do We Need Different Machine Learning Algorithms for QSAR Modeling? A Comprehensive Assessment of 16 Machine Learning Algorithms on 14 QSAR Data Sets. Briefings in Bioinformatics 2021, 22 (4), bbaa321. https://doi.org/10.1093/bib/bbaa321.
(21) ECHA. Registration, Evaluation, Authorisation and Restriction of Chemicals (REACH). https://osha.europa.eu/en/legislation/directives/regulation-ec-no-1907-2006-of-the-european-parliament-and-of-the-council (accessed 2022-05-01).
(22) 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.
(23) Taiwan EPA. 新化學物質及既有化學物質第一階段登錄資料撰寫指引 第一版. 2024.
(24) Westmoreland, C.; Bender, H. J.; Doe, J. E.; Jacobs, M. N.; Kass, G. E. N.; Madia, F.; Mahony, C.; Manou, I.; Maxwell, G.; Prieto, P.; Roggeband, R.; Sobanski, T.; Schütte, K.; Worth, A. P.; Zvonar, Z.; Cronin, M. T. D. Use of New Approach Methodologies (NAMs) in Regulatory Decisions for Chemical Safety: Report from an EPAA Deep Dive Workshop. Regulatory Toxicology and Pharmacology 2022, 135, 105261. https://doi.org/10.1016/j.yrtph.2022.105261.
(25) Törnqvist, E.; Annas, A.; Granath, B.; Jalkesten, E.; Cotgreave, I.; Öberg, M. Strategic Focus on 3R Principles Reveals Major Reductions in the Use of Animals in Pharmaceutical Toxicity Testing. PloS one 2014, 9 (7), e101638.
(26) Klüver, N.; König, M.; Ortmann, J.; Massei, R.; Paschke, A.; Kühne, R.; Scholz, S. Fish Embryo Toxicity Test: Identification of Compounds with Weak Toxicity and Analysis of Behavioral Effects To Improve Prediction of Acute Toxicity for Neurotoxic Compounds. Environ. Sci. Technol. 2015, 49 (11), 7002–7011. https://doi.org/10.1021/acs.est.5b01910.
(27) Braunbeck, T.; Kais, B.; Lammer, E.; Otte, J.; Schneider, K.; Stengel, D.; Strecker, R. The Fish Embryo Test (FET): Origin, Applications, and Future. Environ Sci Pollut Res 2015, 22 (21), 16247–16261. https://doi.org/10.1007/s11356-014-3814-7.
(28) Kusko, R.; Hong, H. Machine Learning and Deep Learning Promote Computational Toxicology for Risk Assessment of Chemicals. In Machine Learning and Deep Learning in Computational Toxicology; Hong, H., Ed.; Springer International Publishing: Cham, 2023; pp 1–17. https://doi.org/10.1007/978-3-031-20730-3_1.
(29) FJODOROVA, N.; NOVICH, M.; VRACHKO, M.; SMIRNOV, V.; KHARCHEVNIKOVA, N.; ZHOLDAKOVA, Z.; NOVIKOV, S.; SKVORTSOVA, N.; FILIMONOV, D.; POROIKOV, V.; BENFENATI, E. Directions in QSAR Modeling for Regulatory Uses in OECD Member Countries, EU and in Russia. Journal of Environmental Science and Health, Part C 2008, 26 (2), 201–236. https://doi.org/10.1080/10590500802135578.
(30) Roy, K.; Kar, S.; Das, R. N. A Primer on QSAR/QSPR Modeling: Fundamental Concepts; Springer, 2015.
(31) Pavan, M.; Netzeva, T. I.; Worth, A. P. Validation of a QSAR Model for Acute Toxicity. SAR and QSAR in Environmental Research 2006, 17 (2), 147–171. https://doi.org/10.1080/10659360600636253.
(32) Cronin, M. T. D. Quantitative Structure–Activity Relationships (QSARs) – Applications and Methodology. In Recent Advances in QSAR Studies: Methods and Applications; Puzyn, T., Leszczynski, J., Cronin, M. T., Eds.; Challenges and Advances in Computational Chemistry and Physics; Springer Netherlands: Dordrecht, 2010; pp 3–11. https://doi.org/10.1007/978-1-4020-9783-6_1.
(33) Romesburg, H. C. Cluster Analysis for Researchers (Belmont, CA: Lifetime Learning Publications. RomesburgCluster Analysis for Researchers1984 1984.
(34) Martin, T. M. User’s Guide for T.E.S.T. (Toxicity Estimation Software Tool). 63.
(35) Enterprise, L. Leadscope Inc. Columbus, OH 2007.
(36) 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.
(37) Helm, J. M.; Swiergosz, A. M.; Haeberle, H. S.; Karnuta, J. M.; Schaffer, J. L.; Krebs, V. E.; Spitzer, A. I.; Ramkumar, P. N. Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions. Curr Rev Musculoskelet Med 2020, 13 (1), 69–76. https://doi.org/10.1007/s12178-020-09600-8.
(38) Emerging Artificial Intelligence Applications in Computer Engineering.
(39) Sen, P. C.; Hajra, M.; Ghosh, M. Supervised Classification Algorithms in Machine Learning: A Survey and Review. In Emerging Technology in Modelling and Graphics; Mandal, J. K., Bhattacharya, D., Eds.; Springer: Singapore, 2020; pp 99–111. https://doi.org/10.1007/978-981-13-7403-6_11.
(40) N. Muratov, E.; Bajorath, J.; P. Sheridan, R.; V. Tetko, I.; Filimonov, D.; Poroikov, V.; I. Oprea, T.; I. Baskin, I.; Varnek, A.; Roitberg, A.; Isayev, O.; Curtalolo, S.; Fourches, D.; Cohen, Y.; Aspuru-Guzik, A.; A. Winkler, D.; Agrafiotis, D.; Cherkasov, A.; Tropsha, A. QSAR without Borders. Chemical Society Reviews 2020, 49 (11), 3525–3564. https://doi.org/10.1039/D0CS00098A.
(41) Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; KDD ’16; Association for Computing Machinery: New York, NY, USA, 2016; pp 785–794. https://doi.org/10.1145/2939672.2939785.
(42) Tunkel, J.; Mayo, K.; Austin, C.; Hickerson, A.; Howard, P. Practical Considerations on the Use of Predictive Models for Regulatory Purposes. Environ. Sci. Technol. 2005, 39 (7), 2188–2199. https://doi.org/10.1021/es049220t.
(43) Cappelli, C. I.; Cassano, A.; Golbamaki, A.; Moggio, Y.; Lombardo, A.; Colafranceschi, M.; Benfenati, E. Assessment of in Silico Models for Acute Aquatic Toxicity towards Fish under REACH Regulation. SAR and QSAR in Environmental Research 2015, 26 (12), 977–999. https://doi.org/10.1080/1062936X.2015.1104519.
(44) Chen, X.; Dang, L.; Yang, H.; Huang, X.; Yu, X. Machine Learning-Based Prediction of Toxicity of Organic Compounds towards Fathead Minnow. RSC Advances 2020, 10 (59), 36174–36180. https://doi.org/10.1039/D0RA05906D.
(45) Tinkov, O.; Polishchuk, P.; Matveieva, M.; Grigorev, V.; Grigoreva, L.; Porozov, Y. The Influence of Structural Patterns on Acute Aquatic Toxicity of Organic Compounds. Molecular Informatics 2021, 40 (9), 2000209. https://doi.org/10.1002/minf.202000209.
(46) Marzo, M.; Lavado, G. J.; Como, F.; Toropova, A. P.; Toropov, A. A.; Baderna, D.; Cappelli, C.; Lombardo, A.; Toma, C.; Blázquez, M.; Benfenati, E. QSAR Models for Biocides: The Example of the Prediction of Daphnia Magna Acute Toxicity. SAR and QSAR in Environmental Research 2020, 31 (3), 227–243. https://doi.org/10.1080/1062936X.2019.1709221.
(47) Ghsc14.Pdf. https://webapps.ilo.org/static/english/protection/safework/ghs/ghsfinal/ghsc14.pdf (accessed 2024-07-09).
(48) Guo, C. A. 精進機器學習為基礎之水生急毒性定量活性結構關係並應用於評估國內重要化學物質之研究. 2022.
(49) Patterson, E. A.; Whelan, M. P.; Worth, A. P. The Role of Validation in Establishing the Scientific Credibility of Predictive Toxicology Approaches Intended for Regulatory Application. Computational Toxicology 2021, 17, 100144. https://doi.org/10.1016/j.comtox.2020.100144.
(50) ECOTOX | Home. https://cfpub.epa.gov/ecotox/ (accessed 2020-06-27).
(51) Registered substances - ECHA. https://echa.europa.eu/information-on-chemicals/registered-substances (accessed 2024-06-26).
(52) Results of Eco-Toxicity Tests of Chemicals Conducted by Ministry of the Environment in Japan (- March 2015). 2000, 31.
(53) Aruoja, V.; Sihtmäe, M.; Dubourguier, H.-C.; Kahru, A. Toxicity of 58 Substituted Anilines and Phenols to Algae Pseudokirchneriella Subcapitata and Bacteria Vibrio Fischeri: Comparison with Published Data and QSARs. Chemosphere 2011, 84 (10), 1310–1320. https://doi.org/10.1016/j.chemosphere.2011.05.023.
(54) Aruoja, V.; Moosus, M.; Kahru, A.; Sihtmäe, M.; Maran, U. Measurement of Baseline Toxicity and QSAR Analysis of 50 Non-Polar and 58 Polar Narcotic Chemicals for the Alga Pseudokirchneriella Subcapitata. Chemosphere 2014, 96, 23–32. https://doi.org/10.1016/j.chemosphere.2013.06.088.
(55) CompTox Chemicals Dashboard. https://comptox.epa.gov/dashboard/ (accessed 2024-06-26).
(56) Russom, C. L.; Breton, R. L.; Walker, J. D.; Bradbury, S. P. An Overview of the Use of Quantitative Structure-Activity Relationships for Ranking and Prioritizing Large Chemical Inventories for Environmental Risk Assessments. Environmental Toxicology and Chemistry 2003, 22 (8), 1810–1821. https://doi.org/10.1897/01-194.
(57) Re-Evaluation of Animal Numbers and Costs for In Vivo Tests to Accomplish REACH Legislation Requirements for Chemicals : a Report by the Transatlantic Think Tank for Toxicology (t(4)). https://kops.uni-konstanz.de/entities/publication/6060d571-cb5d-46d2-b780-2a9a2adebf73 (accessed 2024-07-05).
(58) Braunbeck, T.; Kais, B.; Lammer, E.; Otte, J.; Schneider, K.; Stengel, D.; Strecker, R. The Fish Embryo Test (FET): Origin, Applications, and Future. Environmental Science and Pollution Research 2015, 22 (21), 16247–16261.
(59) Cappelli, C. I.; Benfenati, E.; Cester, J. Evaluation of QSAR Models for Predicting the Partition Coefficient (logP) of Chemicals under the REACH Regulation. Environmental Research 2015, 143, 26–32. https://doi.org/10.1016/j.envres.2015.09.025.
(60) Song, R.; Li, D.; Chang, A.; Tao, M.; Qin, Y.; Keller, A. A.; Suh, S. Accelerating the Pace of Ecotoxicological Assessment Using Artificial Intelligence. Ambio 2022, 51 (3), 598–610. https://doi.org/10.1007/s13280-021-01598-8.
(61) Su, L. M.; Liu, X.; Wang, Y.; Li, J. J.; Wang, X. H.; Sheng, L. X.; Zhao, Y. H. The Discrimination of Excess Toxicity from Baseline Effect: Effect of Bioconcentration. Science of The Total Environment 2014, 484, 137–145. https://doi.org/10.1016/j.scitotenv.2014.03.040.
(62) Cassotti, M.; Ballabio, D.; Todeschini, R.; Consonni, V. A Similarity-Based QSAR Model for Predicting Acute Toxicity towards the Fathead Minnow (Pimephales Promelas). SAR and QSAR in Environmental Research 2015, 26 (3), 217–243.
(63) Austin, T.; Denoyelle, M.; Chaudry, A.; Stradling, S.; Eadsforth, C. European Chemicals Agency Dossier Submissions as an Experimental Data Source: Refinement of a Fish Toxicity Model for Predicting Acute LC50 Values. Environmental Toxicology and Chemistry 2015, 34 (2), 369–378. https://doi.org/10.1002/etc.2817.
(64) Menze, B. H.; Kelm, B. M.; Masuch, R.; Himmelreich, U.; Bachert, P.; Petrich, W.; Hamprecht, F. A. A Comparison of Random Forest and Its Gini Importance with Standard Chemometric Methods for the Feature Selection and Classification of Spectral Data. BMC Bioinformatics 2009, 10 (1), 213. https://doi.org/10.1186/1471-2105-10-213.
(65) The Proportion for Splitting Data into Training and Test Set for the Bootstrap in Classification Problems | Business Systems Research : International journal of the Society for Advancing Innovation and Research in Economy. https://hrcak.srce.hr/ojs/index.php/bsr/article/view/17347 (accessed 2024-07-05).
(66) Lerman, P. M. Fitting Segmented Regression Models by Grid Search. Journal of the Royal Statistical Society Series C: Applied Statistics 1980, 29 (1), 77–84. https://doi.org/10.2307/2346413.
(67) Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models. OECD. https://www.oecd.org/en/publications/2014/09/guidance-document-on-the-validation-of-quantitative-structure-activity-relationship-q-sar-models_g1ghcc68.html (accessed 2024-07-29).
(68) Roy, K.; Kar, S.; Ambure, P. On a Simple Approach for Determining Applicability Domain of QSAR Models. Chemometrics and Intelligent Laboratory Systems 2015, 145, 22–29. https://doi.org/10.1016/j.chemolab.2015.04.013.
(69) Snedecor, G. W. Statistical Methods. Soil Science 1941, 51 (2), 172.
(70) Tropsha, A.; Gramatica, P.; Gombar, V. K. The Importance of Being Earnest: Validation Is the Absolute Essential for Successful Application and Interpretation of QSPR Models. QSAR & Combinatorial Science 2003, 22 (1), 69–77. https://doi.org/10.1002/qsar.200390007.
(71) European Chemicals Agency. - 2016 - How to Use and Report (Q)SARs.Practical Guide 5 ..Pdf. https://echa.europa.eu/documents/10162/13655/pg_report_qsars_en.pdf/407dff11-aa4a-4eef-a1ce-9300f8460099 (accessed 2024-07-09).
(72) Nagelkerke, N. J. A Note on a General Definition of the Coefficient of Determination. Biometrika 1991, 78 (3), 691–692.
(73) Veerasamy, R.; Rajak, H.; Jain, A.; Sivadasan, S.; Christapher, P. V.; Agrawal, R. Validation of QSAR Models - Strategies and Importance. Int J Drug Design and Discov 2011, 2, 511–519.
(74) 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.
(75) 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.
(76) Dearden, J. C.; Cronin, M. T. D.; Kaiser, K. L. E. How Not to Develop a Quantitative Structure–Activity or Structure–Property Relationship (QSAR/QSPR). SAR and QSAR in Environmental Research 2009, 20 (3–4), 241–266. https://doi.org/10.1080/10629360902949567.
(77) 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.
(78) Guide to Fish Acute Toxicity Read-Across Version 1.0.0.Pdf.
(79) Guide to Fish Acute Toxicity (LC50) Model for Biocides Version 1.0.0 Table.Pdf.
(80) Guide to 48 Hour Daphnia Magna LC50 Model (Demetra) Version 1.0.4.Pdf.
(81) Guide to Daphnia Magna Acute Toxicity (EC50) Model for Biocides Version 1.0.0.Pdf.
(82) Guide to Algae EC50 (72h) Model for Biocides Version 1.0.0.Pdf.
(83) Leonard, J. T.; Roy, K. On Selection of Training and Test Sets for the Development of Predictive QSAR Models. QSAR & Combinatorial Science 2006, 25 (3), 235–251. https://doi.org/10.1002/qsar.200510161.
(84) Golbraikh, A.; Shen, M.; Xiao, Z.; Xiao, Y.-D.; Lee, K.-H.; Tropsha, A. Rational Selection of Training and Test Sets for the Development of Validated QSAR Models. J Comput Aided Mol Des 2003, 17 (2), 241–253. https://doi.org/10.1023/A:1025386326946.
(85) Biau, G.; Scornet, E. A Random Forest Guided Tour. TEST 2016, 25 (2), 197–227. https://doi.org/10.1007/s11749-016-0481-7.
(86) Hsu, C.-W.; Chang, C.-C.; Lin, C.-J. A Practical Guide to Support Vector Classification. 16.
(87) Demir, S.; Şahin, E. K. Liquefaction Prediction with Robust Machine Learning Algorithms (SVM, RF, and XGBoost) Supported by Genetic Algorithm-Based Feature Selection and Parameter Optimization from the Perspective of Data Processing. Environmental Earth Sciences 2022, 81 (18). https://doi.org/10.1007/s12665-022-10578-4.
(88) Huang, J.-C.; Tsai, Y.-C.; Wu, P.-Y.; Lien, Y.-H.; Chien, C.-Y.; Kuo, C.-F.; Hung, J.-F.; Chen, S.-C.; Kuo, C.-H. Predictive Modeling of Blood Pressure during Hemodialysis: A Comparison of Linear Model, Random Forest, Support Vector Regression, XGBoost, LASSO Regression and Ensemble Method. Computer Methods and Programs in Biomedicine 2020, 195, 105536. https://doi.org/10.1016/j.cmpb.2020.105536.
(89) Shebl, A.; Abriha, D.; Fahil, A. S.; El-Dokouny, H. A.; Elrasheed, A. A.; Csámer, Á. PRISMA Hyperspectral Data for Lithological Mapping in the Egyptian Eastern Desert: Evaluating the Support Vector Machine, Random Forest, and XG Boost Machine Learning Algorithms. Ore Geology Reviews 2023, 161, 105652. https://doi.org/10.1016/j.oregeorev.2023.105652.
(90) Wolpert, D. H.; Macready, W. G. No Free Lunch Theorems for Optimization. IEEE Transactions on Evolutionary Computation 1997, 1 (1), 67–82. https://doi.org/10.1109/4235.585893.
(91) James, G.; Witten, D.; Hastie, T.; Tibshirani, R.; Taylor, J. Linear Regression. In An Introduction to Statistical Learning; Springer Texts in Statistics; Springer International Publishing: Cham, 2023; pp 69–134. https://doi.org/10.1007/978-3-031-38747-0_3.
(92) Martin, T. M.; Harten, P.; Young, D. M.; Muratov, E. N.; Golbraikh, A.; Zhu, H.; Tropsha, A. Does Rational Selection of Training and Test Sets Improve the Outcome of QSAR Modeling? J. Chem. Inf. Model. 2012, 52 (10), 2570–2578. https://doi.org/10.1021/ci300338w.
(93) Wang, Y.; Chen, X. A Joint Optimization QSAR Model of Fathead Minnow Acute Toxicity Based on a Radial Basis Function Neural Network and Its Consensus Modeling. RSC Advances 2020, 10 (36), 21292–21308. https://doi.org/10.1039/D0RA02701D.
(94) Yu, X. Support Vector Machine-Based Model for Toxicity of Organic Compounds against Fish. Regulatory Toxicology and Pharmacology 2021, 123, 104942. https://doi.org/10.1016/j.yrtph.2021.104942.
(95) Gajewicz-Skretna, A.; Furuhama, A.; Yamamoto, H.; Suzuki, N. Generating Accurate in Silico Predictions of Acute Aquatic Toxicity for a Range of Organic Chemicals: Towards Similarity-Based Machine Learning Methods. Chemosphere 2021, 280, 130681. https://doi.org/10.1016/j.chemosphere.2021.130681.
(96) Blázquez, M.; Andreu-Sánchez, O.; Ballesteros, A.; Fernández-Cruz, M. L.; Fito, C.; Gómez-Ganau, S.; Gozalbes, R.; Hernández-Moreno, D.; de Julián-Ortiz, J. V.; Lombardo, A.; Marzo, M.; Ranero, I.; Ruiz-Costa, N.; Tarazona-Díez, J. V.; Benfenati, E. Computational Tools for the Assessment and Substitution of Biocidal Active Substances of Ecotoxicological Concern. In Chemometrics and Cheminformatics in Aquatic Toxicology; John Wiley & Sons, Ltd, 2021; pp 527–546. https://doi.org/10.1002/9781119681397.ch27.
(97) Sahigara, F.; Mansouri, K.; Ballabio, D.; Mauri, A.; Consonni, V.; Todeschini, R. Comparison of Different Approaches to Define the Applicability Domain of QSAR Models. Molecules 2012, 17 (5), 4791–4810. https://doi.org/10.3390/molecules17054791.
(98) Gómez-Ganau, S.; Marzo, M.; Gozalbes, R.; Benfenati, E. Computational Approaches to Evaluate Ecotoxicity of Biocides: Cases from the Project COMBASE. In Ecotoxicological QSARs; Roy, K., Ed.; Springer US: New York, NY, 2020; pp 387–404. https://doi.org/10.1007/978-1-0716-0150-1_17.
(99) Esteki, M.; Khayamian, T. Mechanistic-Based Descriptors for QSAR Study of Psychotropic Drug Toxicity. Chemical Biology & Drug Design 2008, 72 (5), 409–435. https://doi.org/10.1111/j.1747-0285.2008.00718.x.
(100) Steinbeck, C.; Han, Y.; Kuhn, S.; Horlacher, O.; Luttmann, E.; Willighagen, E. The Chemistry Development Kit (CDK): An Open-Source Java Library for Chemo- and Bioinformatics. J. Chem. Inf. Comput. Sci. 2003, 43 (2), 493–500. https://doi.org/10.1021/ci025584y.
(101) Gajewicz-Skretna, A.; Gromelski, M.; Wyrzykowska, E.; Furuhama, A.; Yamamoto, H.; Suzuki, N. Aquatic Toxicity (Pre)Screening Strategy for Structurally Diverse Chemicals: Global or Local Classification Tree Models? Ecotoxicology and Environmental Safety 2021, 208, 111738. https://doi.org/10.1016/j.ecoenv.2020.111738.
(102) Kaiser, K. L. E.; Esterby, S. R. Regression and Cluster Analysis of the Acute Toxicity of 267 Chemicals to Six Species of Biota and the Octanol/Water Partition Coefficient. Science of The Total Environment 1991, 109–110, 499–514. https://doi.org/10.1016/0048-9697(91)90204-R.
(103) Schreier, S.; Malheiros, S. V. P.; de Paula, E. Surface Active Drugs: Self-Association and Interaction with Membranes and Surfactants. Physicochemical and Biological Aspects. Biochimica et Biophysica Acta (BBA) - Biomembranes 2000, 1508 (1), 210–234. https://doi.org/10.1016/S0304-4157(00)00012-5.
(104) Kaiser, K. L. E.; Niculescu, S. P. Modeling Acute Toxicity of Chemicals to Daphnia Magna: A Probabilistic Neural Network Approach. Environmental Toxicology and Chemistry 2001, 20 (2), 420–431. https://doi.org/10.1002/etc.5620200225.
(105) Furuhama, A.; Toida, T.; Nishikawa, N.; Aoki, Y.; Yoshioka, Y.; Shiraishi, H. Development of an Ecotoxicity QSAR Model for the KAshinhou Tool for Ecotoxicity (KATE) System, March 2009 Version. SAR and QSAR in Environmental Research 2010, 21 (5–6), 403–413. https://doi.org/10.1080/1062936X.2010.501815.
(106) Cassotti, M.; Ballabio, D.; Consonni, V.; Mauri, A.; Tetko, I. V.; Todeschini, R. Prediction of Acute Aquatic Toxicity toward Daphnia Magna by Using the GA-kNN Method. Altern Lab Anim 2014, 42 (1), 31–41. https://doi.org/10.1177/026119291404200106.
(107) Burden, N.; Maynard, S. K.; Weltje, L.; Wheeler, J. R. The Utility of QSARs in Predicting Acute Fish Toxicity of Pesticide Metabolites: A Retrospective Validation Approach. Regulatory Toxicology and Pharmacology 2016, 80, 241–246. https://doi.org/10.1016/j.yrtph.2016.05.032.
(108) Khan, K.; Baderna, D.; Cappelli, C.; Toma, C.; Lombardo, A.; Roy, K.; Benfenati, E. Ecotoxicological QSAR Modeling of Organic Compounds against Fish: Application of Fragment Based Descriptors in Feature Analysis. Aquatic Toxicology 2019, 212, 162–174. https://doi.org/10.1016/j.aquatox.2019.05.011.
(109) Samanipour, S.; O’Brien, J. W.; Reid, M. J.; Thomas, K. V.; Praetorius, A. From Molecular Descriptors to Intrinsic Fish Toxicity of Chemicals: An Alternative Approach to Chemical Prioritization. Environ. Sci. Technol. 2023, 57 (46), 17950–17958. https://doi.org/10.1021/acs.est.2c07353.
(110) Chen, S.; Sun, G.; Fan, T.; Li, F.; Xu, Y.; Zhang, N.; Zhao, L.; Zhong, R. Ecotoxicological QSAR Study of Fused/Non-Fused Polycyclic Aromatic Hydrocarbons (FNFPAHs): Assessment and Priority Ranking of the Acute Toxicity to Pimephales Promelas by QSAR and Consensus Modeling Methods. Science of The Total Environment 2023, 876, 162736. https://doi.org/10.1016/j.scitotenv.2023.162736.
校內：2029-08-08公開校外：2029-08-08公開