In this paper, the term "applicability domain" refers to the range of chemical compounds for which the statistical quantitative structure-activity relationship (QSAR) model can accurately predict their toxicity. This is a crucial concept in the development and practical use of these models. First, a multidisciplinary review is provided regarding the theory and practice of applicability domains in the context of toxicity problems using the classical QSAR model. Then, the advantages and improved performance of neural networks (NNs), which are the most promising machine learning algorithms, are reviewed. Within the domain of medicinal chemistry, nine different methods using NNs for toxicity prediction were compared utilizing 29 alternative artificial intelligence (AI) techniques. Similarly, seven NN-based toxicity prediction methodologies were compared to six other AI techniques within the realm of food safety, 11 NN-based methodologies were compared to 16 different AI approaches in the environmental sciences category and four specific NN-based toxicity prediction methodologies were compared to nine alternative AI techniques in the field of industrial hygiene. Within the reviewed approaches, given known toxic compound descriptors and behaviors, we observed a difficulty in being able to extrapolate and predict the effects with untested chemical compounds. Different methods can be used for unsupervised clustering, such as distance-based approaches and consensus-based decision methods. Additionally, the importance of model validation has been highlighted within a regulatory context according to the Organization for Economic Co-operation and Development (OECD) principles, to predict the toxicity of potential new drugs in medicinal chemistry, to determine the limits of detection for harmful substances in food to predict the toxicity limits of chemicals in the environment, and to predict the exposure limits to harmful substances in the workplace. Despite its importance, a thorough application of toxicity models is still restricted in the field of medicinal chemistry and is virtually overlooked in other scientific domains. Consequently, only a small proportion of the toxicity studies conducted in medicinal chemistry consider the applicability domain in their mathematical models, thereby limiting their predictive power to untested drugs. Conversely, the applicability of these models is crucial; however, this has not been sufficiently assessed in toxicity prediction or in other related areas such as food science, environmental science, and industrial hygiene. Thus, this review sheds light on the prevalent use of Neural Networks in toxicity prediction, thereby serving as a valuable resource for researchers and practitioners across these multifaceted domains that could be extended to other fields in future research.
Citation: Efrén Pérez-Santín, Luis de-la-Fuente-Valentín, Mariano González García, Kharla Andreina Segovia Bravo, Fernando Carlos López Hernández, José Ignacio López Sánchez. Applicability domains of neural networks for toxicity prediction[J]. AIMS Mathematics, 2023, 8(11): 27858-27900. doi: 10.3934/math.20231426
In this paper, the term "applicability domain" refers to the range of chemical compounds for which the statistical quantitative structure-activity relationship (QSAR) model can accurately predict their toxicity. This is a crucial concept in the development and practical use of these models. First, a multidisciplinary review is provided regarding the theory and practice of applicability domains in the context of toxicity problems using the classical QSAR model. Then, the advantages and improved performance of neural networks (NNs), which are the most promising machine learning algorithms, are reviewed. Within the domain of medicinal chemistry, nine different methods using NNs for toxicity prediction were compared utilizing 29 alternative artificial intelligence (AI) techniques. Similarly, seven NN-based toxicity prediction methodologies were compared to six other AI techniques within the realm of food safety, 11 NN-based methodologies were compared to 16 different AI approaches in the environmental sciences category and four specific NN-based toxicity prediction methodologies were compared to nine alternative AI techniques in the field of industrial hygiene. Within the reviewed approaches, given known toxic compound descriptors and behaviors, we observed a difficulty in being able to extrapolate and predict the effects with untested chemical compounds. Different methods can be used for unsupervised clustering, such as distance-based approaches and consensus-based decision methods. Additionally, the importance of model validation has been highlighted within a regulatory context according to the Organization for Economic Co-operation and Development (OECD) principles, to predict the toxicity of potential new drugs in medicinal chemistry, to determine the limits of detection for harmful substances in food to predict the toxicity limits of chemicals in the environment, and to predict the exposure limits to harmful substances in the workplace. Despite its importance, a thorough application of toxicity models is still restricted in the field of medicinal chemistry and is virtually overlooked in other scientific domains. Consequently, only a small proportion of the toxicity studies conducted in medicinal chemistry consider the applicability domain in their mathematical models, thereby limiting their predictive power to untested drugs. Conversely, the applicability of these models is crucial; however, this has not been sufficiently assessed in toxicity prediction or in other related areas such as food science, environmental science, and industrial hygiene. Thus, this review sheds light on the prevalent use of Neural Networks in toxicity prediction, thereby serving as a valuable resource for researchers and practitioners across these multifaceted domains that could be extended to other fields in future research.
| [1] | National Research Council, Toxicity testing in the 21st century: A vision and a strategy, in National Academies Press, 2007, 1–196. Available from: https://doi.org/10.17226/11970 |
| [2] |
H. Sun, M. Xia, C. P. Austin, R Huang, Paradigm shift in toxicity testing and modeling, AAPS J., 14 (2012), 473–480. https://doi.org/10.1208/s12248-012-9358-1 doi: 10.1208/s12248-012-9358-1
|
| [3] |
I. Fischer, C. Milton, H. Wallace, Toxicity testing is evolving! Toxicol. Res. (Camb), 9 (2020), 67–80. https://doi.org/10.1093/toxres/tfaa011 doi: 10.1093/toxres/tfaa011
|
| [4] |
S. Gibb, Toxicity testing in the 21st century: A vision and a strategy, Reprod. Toxicol., 25 (2008), 136–138. https://doi.org/10.1016/j.reprotox.2007.10.013 doi: 10.1016/j.reprotox.2007.10.013
|
| [5] |
K. A. Ford, Refinement, reduction, and replacement of animal toxicity tests by computational methods, ILAR J., 57 (2016), 226–233. https://doi.org/10.1093/ilar/ilw031 doi: 10.1093/ilar/ilw031
|
| [6] |
C. Jean-Quartier, F. Jeanquartier, I. Jurisica, A. Holzinger, In silico cancer research towards 3R, BMC Cancer, 18 (2018), 408. https://doi.org/10.1186/s12885-018-4302-0 doi: 10.1186/s12885-018-4302-0
|
| [7] |
E. Pérez Santín, R. Rodríguez Solana, M. González García, M. Del Mar García Suárez, G. David Blanco Díaz, M. Dolores Cima Cabal, et al., Toxicity prediction based on artificial intelligence: A multidisciplinary overview, Wiley Interdiscip. Rev. Comput. Mol. Sci., 11 (2021), e1516. https://doi.org/10.1002/wcms.1516 doi: 10.1002/wcms.1516
|
| [8] | G. J. Myatt, L. D. Beilke, K. P. Cross, In Silico Tools and their Application, In: Comprehensive Medicinal Chemistry III, Oxford, Elsevier, 2017,156–176. Available from: https://doi.org/10.1016/B978-0-12-409547-2.12379-0 |
| [9] | R. Todeschini, V. Consonni, P. Gramatica, 4.05-Chemometrics in QSAR, In: Comprehensive Chemometrics, Oxford, Elsevier, (2009), 129–172. https://doi.org/10.1016/B978-044452701-1.00007-7 |
| [10] | Committee 37th Joint Meeting of the Chemicals, OECD principles for the validation, for regulatory purposes, of (quantitative) structure–activity relationship models, 2019. Available from: https://www.oecd.org/chemicalsafety/risk-assessment/37849783.pdf |
| [11] | OECD (Organisation for Economic Co-operation and Development, Quantitative Structure-Activity Relationships Project [(Q)SARs], 2023. Available from: https://www.oecd.org/chemicalsafety/risk-assessment/oecdquantitativestructure-activityrelationshipsprojectqsars.htm. |
| [12] | ECHA (European Chemicals Agency), REACH: Regulation (EC) No 1907/2006. Available from: https://eur-lex.europa.eu/LexUriServ/LexUriServ.do?uri = OJ: L: 2007: 136: 0003: 0280: en: PDF |
| [13] | European Commission, JRC QSAR Model Database, Joint Research Centre (JRC), 2020. Available from: https://data.jrc.ec.europa.eu/dataset/e4ef8d13-d743-4524-a6eb-80e18b58cba4 |
| [14] | S. C. Peter, J. K. Dhanjal, V. Malik, N. Radhakrishnan, M.Jayakanthan, D. Sundar, Quantitative Structure-Activity Relationship (QSAR): Modeling Approaches to Biological Applications, In Encyclopedia of Bioinformatics and Computational Biology, Oxford, Academic Press, 2019,661–676. https://doi.org/10.1016/B978-0-12-809633-8.20197-0 |
| [15] | K. Roy, S. Kar, R. N. Das RN, QSAR/QSPR Modeling: Introduction, In: A Primer on QSAR/QSPR Modeling: Fundamental Concepts, Cham, Springer International Publishing, 2015, 1–36. https://doi.org/10.1007/978-3-319-17281-1 |
| [16] |
G. J. Hwang, H. Xie, B. W. Wah, D. Gašević, Vision, challenges, roles and research issues of Artificial Intelligence in Education, Comput. Education: Artif. Intell., 1 (2020), 100001. https://doi.org/10.1016/j.caeai.2020.100001 doi: 10.1016/j.caeai.2020.100001
|
| [17] |
S. Agatonovic-Kustrin, R. Beresford, Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research, J. Pharm. Biomed. Anal., 22 (2000), 717–727. https://doi.org/10.1016/S0731-7085(99)00272-1 doi: 10.1016/S0731-7085(99)00272-1
|
| [18] |
R. Jabbar, R. Jabbar, S. Kamoun, Recent progress in generative adversarial networks applied to inversely designing inorganic materials: A brief review, Comput. Mater. Sci., 213 (2022), 111612. https://doi.org/10.1016/j.commatsci.2022.111612 doi: 10.1016/j.commatsci.2022.111612
|
| [19] | G. Gómez-Jiménez, K. Gonzalez-Ponce, D. J. Castillo-Pazos, A. Madariaga-Mazon, J. Barroso-Flores, J. Barroso-Flores, et al., Chapter Four-The OECD Principles for (Q)SAR Models in the Context of Knowledge Discovery in Databases (KDD), In: Advances in Protein Chemistry and Structural Biology, Academic Press, 2018, 85–117. http://dx.doi.org/10.1016/bs.apcsb.2018.04.001 |
| [20] |
A. Morger, F. Svensson, S. Arvidsson McShane, N. Gauraha, U. Norinder, O. Spjuth, Assessing the calibration in toxicological in vitro models with conformal prediction, J. Cheminform., 13 (2021), 1–14. https://doi.org/10.1186/s13321-021-00511-5 doi: 10.1186/s13321-021-00511-5
|
| [21] |
U. Norinder, Traditional machine and deep learning for predicting toxicity endpoints, Molecules, 28 (2023), 217. https://doi.org/10.3390/molecules28010217 doi: 10.3390/molecules28010217
|
| [22] |
M. Nascimben, L. Rimondini, Molecular toxicity virtual screening applying a quantized computational SNN-Based framework, Molecules, 28 (2023), 1342. https://doi.org/10.3390/molecules28031342 doi: 10.3390/molecules28031342
|
| [23] |
J. Li, D. Luo, T. Wen, Q. Liu, Z. Mo, Representative feature selection of molecular descriptors in QSAR modeling, J. Mol. Struct., 1244 (2021), 131249. https://doi.org/10.1016/j.molstruc.2021.131249 doi: 10.1016/j.molstruc.2021.131249
|
| [24] | A. Tropsha, 4.07-Predictive Quantitative Structure–Activity Relationship Modeling, In: Comprehensive Medicinal Chemistry II, Oxford, Elsevier, 2007 149–165. http://dx.doi.org/10.1016/B0-08-045044-X/00248-0 |
| [25] | A. M. Davis, 3.15-Quantitative Structure-Activity Relationships, In: Comprehensive Medicinal Chemistry III, Oxford, Elsevier, 2017,379–392. |
| [26] | E. Benfenati, J. R. Chrétien, G. Gini, Chapter 6-Validation of the models, In: Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes, Amsterdam, Elsevier, 2007,185–199. https://doi.org/10.1016/B978-044452710-3/50008-2 |
| [27] |
E. Kotsampasakou, G. F. Ecker, Predicting Drug-Induced Cholestasis with the Help of Hepatic Transporters-An in Silico Modeling Approach, J. Chem. Inf. Model., 57 (2017), 608–615. https://doi.org/10.1021/acs.jcim.6b00518 doi: 10.1021/acs.jcim.6b00518
|
| [28] |
E. Minerali, D. H. Foil, K. M. Zorn, T. T. Lane, S. Ekins, Comparing machine learning algorithms for predicting Drug-Induced liver injury (DILI), Mol. Pharm., 17 (2020), 2628–2637. https://doi.org/10.1021/acs.molpharmaceut.0c00326 doi: 10.1021/acs.molpharmaceut.0c00326
|
| [29] | Collaborations Pharmaceuticals, Inc. http://tomocomd.com/apps/ptoxra, Assay Central, 2023. Available from: https://www.collaborationspharma.com/assay-central |
| [30] |
J. R. Mora, Y. Marrero-Ponce, C. R. García-Jacas, A. S. Causado, Ensemble Models Based on QuBiLS-MAS Features and Shallow Learning for the Prediction of Drug-Induced Liver Toxicity: Improving Deep Learning and Traditional Approaches, Chem. Res. Toxicol., 33 (2020), 1855–1873. https://doi.org/10.1021/acs.chemrestox.0c00030 doi: 10.1021/acs.chemrestox.0c00030
|
| [31] | ToMoCoMD framework, SiliS-PTOXRA 2023. Available from: http://tomocomd.com/apps/ptoxra |
| [32] |
Q. Wu, C. Cai, P. Guo, M. Chen, X. Wu, J. Zhou, et al., In silico Identification and mechanism exploration of hepatotoxic ingredients in traditional Chinese medicine, Front Pharmacol, 10 (2019), 1–15. https://doi.org/10.3389/fphar.2019.00458 doi: 10.3389/fphar.2019.00458
|
| [33] |
F. Hussain, S. Basu, J. J. H. Heng, L. H. Loo, D. Zink, Predicting direct hepatocyte toxicity in humans by combining high-throughput imaging of HepaRG cells and machine learning-based phenotypic profiling, Arch. Toxicol., 94 (2020), 2749–2767. https://doi.org/10.1007/s00204-020-02778-3 doi: 10.1007/s00204-020-02778-3
|
| [34] |
P. Di, Y. Yin, C. Jiang, Y. Cai, W. Li, Y. Tang, et al., Prediction of the skin sensitising potential and potency of compounds via mechanism-based binary and ternary classification models, Toxicol. Vitro, 59 (2019), 204–214. https://doi.org/10.1016/j.tiv.2019.01.004 doi: 10.1016/j.tiv.2019.01.004
|
| [35] | KNIME Open for innovation, End to End Data Science, 2023. Available from: https://www.knime.com/ |
| [36] | KNIME Open for innovation, Community Extensions, 2023. Available from: https://www.knime.com/community |
| [37] | NovaMeechanics Ltd, Cheminformatics & Nanoinformatics Excellence, 2023. Available from: https://novamechanics.com/ |
| [38] |
K. Ogura, T. Sato, H. Yuki, Y. Cai, W. Li, Y. Tang, Support Vector Machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-Ⅱ, Sci. Rep., 9 (2019), 1–7. https://doi.org/10.1038/s41598-019-47536-3 doi: 10.1038/s41598-019-47536-3
|
| [39] | Construction of Drug Discovery Informatics System by Japan Agency for Medical Research and Development, AMED Cardiotoxicity Database, 2023. Available from: https://drugdesign.riken.jp/hERGdb/. |
| [40] | N. Fjodorova, M. Vračko, M. Novič, A. Roncaglioni, E. Benfenati, New public QSAR model for carcinogenicity, Chem. Cent. J., 4 (2010), 1–15. https://doi.org/10.1186%2F1752-153X-4-S1-S3 |
| [41] |
K. P. Singh, S. Gupta, P. Rai, Predicting carcinogenicity of diverse chemicals using probabilistic neural network modeling approaches, Toxicol. Appl. Pharmacol., 27 (2013), 465–475. https://doi.org/10.1016/j.taap.2013.06.029 doi: 10.1016/j.taap.2013.06.029
|
| [42] |
L. Zhang, H. Ai, W. Chen, Z. Yin, H. Hu, J. Zhu, et al., CarcinoPred-EL: Novel models for predicting the carcinogenicity of chemicals using molecular fingerprints and ensemble learning methods, Sci. Rep., 7 (2017), 1–14. https://doi.org/10.1038/s41598-017-02365-0 doi: 10.1038/s41598-017-02365-0
|
| [43] | CarcinoPred-EL, Prediction of chemical carcinogenicity using ensemble learning methods, Available from: http://112.126.70.33/toxicity/CarcinoPred-EL/about.html |
| [44] |
D. Guan, K. Fan, I. Spence, S. Matthews, Combining machine learning models of in vitro and in vivo bioassays improves rat carcinogenicity prediction, Regul. Toxicol. Pharm., 94 (2018), 8–15. https://doi.org/10.1016/j.yrtph.2018.01.008 doi: 10.1016/j.yrtph.2018.01.008
|
| [45] |
P. Bloomingdale, D. E. Mager, Machine learning models for the prediction of chemotherapy-induced peripheral neuropathy, Pharm. Res., 36 (2019), 35. https://doi.org/10.1007/s11095-018-2562-7 doi: 10.1007/s11095-018-2562-7
|
| [46] | Team ProTox-Ⅱ, ProTox-Ⅱ-Prediction Of Toxicity Of Chemicals, 2023. Available from: https://tox-new.charite.de/protox_II/ |
| [47] |
D. R. Tonholo, V. G. Maltarollo, T. Kronenberger, I. R. Silva, P. O. Azevedo, R. B. Oliveira, et al., Preclinical toxicity of innovative molecules: In vitro, in vivo and metabolism prediction, Chem. Biol. Interact., 315 (2020), 108896. https://doi.org/10.1016/j.cbi.2019.108896 doi: 10.1016/j.cbi.2019.108896
|
| [48] |
P. Banerjee, A. O. Eckert, A. K. Schrey, R. Preissner, ProTox-Ⅱ: A webserver for the prediction of toxicity of chemicals, Nucleic. Acids. Res., 46 (2018), 257–263. https://doi.org/10.1093/nar/gky318 doi: 10.1093/nar/gky318
|
| [49] |
F. Cheng, W. Li, Y. Zhou, J. Shen, Z. Wu, G. Liu, et al., AdmetSAR: A comprehensive source and free tool for assessment of chemical ADMET properties, J. Chem. Inf. Model., 52 (2012), 3099–3105. https://doi.org/10.1021/ci300367a doi: 10.1021/ci300367a
|
| [50] |
H. Yang, C. Lou, L. Sun, J. Li, Y. Cai, Z. Wang, et al., AdmetSAR 2.0: Web-service for prediction and optimization of chemical ADMET properties, Bioinformatics, 35 (2019), 1067–1069. https://doi.org/10.1093/bioinformatics/bty707 doi: 10.1093/bioinformatics/bty707
|
| [51] | Y. Gu, C. Lou, Y. Tang, AdmetSAR-A valuable tool for assisting safety evaluation. In QSAR in Safety Evaluation and Risk Assessment, Academic Press, (2023), 187–201. https://doi.org/10.1016/B978-0-443-15339-6.00004-7- |
| [52] |
H. E. Webel, T. B. Kimber, S. Radetzki, M. Neuenschwander, M. Nazaré, A. Volkamer, Revealing cytotoxic substructures in molecules using deep learning, J. Comput. Aided. Mol. Des., 34 (2020), 731–746. https://doi.org/10.1007/s10822-020-00310-4 doi: 10.1007/s10822-020-00310-4
|
| [53] |
D. Antanasijević, J. Antanasijević, N. Trišović, G. Ušćumlić, V. Pocajt, From classification to regression multitasking QSAR modeling using a novel modular neural network: Simultaneous prediction of anticonvulsant activity and neurotoxicity of succinimides, Mol. Pharm., 14 (2017), 4476–4484. https://doi.org/10.1021/acs.molpharmaceut.7b00582 doi: 10.1021/acs.molpharmaceut.7b00582
|
| [54] |
K. Roy, S. Kar, P. Ambure, On a simple approach for determining applicability domain of QSAR models, Chemometr. Intell. Lab. Syst., 145 (2015), 22–29. https://doi.org/10.1016/j.chemolab.2015.04.013 doi: 10.1016/j.chemolab.2015.04.013
|
| [55] |
S. Zheng, J. Xiong, Y. Wang, G. Liang, Y. Xu, F. Lin, Quantitative prediction of hemolytic toxicity for small molecules and their potential hemolytic fragments by machine learning and recursive fragmentation methods, J. Chem. Inf. Model., 60 (2020), 3231–3245. https://doi.org/10.1021/acs.jcim.0c00102 doi: 10.1021/acs.jcim.0c00102
|
| [56] |
S. Zheng, Y. Wang, W. Liu, W. Chang, G. Liang, Y. Xu, et al., In Silico prediction of hemolytic toxicity on the human erythrocytes for small molecules by machine-learning and genetic algorithm, J. Med. Chem., 63 (2020), 6499–6512. https://doi.org/10.1021/acs.jmedchem.9b00853 doi: 10.1021/acs.jmedchem.9b00853
|
| [57] |
F. Plisson, O. Ramírez-Sánchez, C. Martínez-Hernández, Machine learning-guided discovery and design of non-hemolytic peptides, Sci. Rep., 10 (2020), 1–19. https://doi.org/10.1038/s41598-020-73644-6 doi: 10.1038/s41598-020-73644-6
|
| [58] |
H. Feng, L. Zhang, S. Li, L. Liu, T. Yang, P. Yang, et al., Predicting the reproductive toxicity of chemicals using ensemble learning methods and molecular fingerprints, Toxicol. Lett., 340 (2021), 4–14. https://doi.org/10.1016/j.toxlet.2021.01.002 doi: 10.1016/j.toxlet.2021.01.002
|
| [59] |
P. Zhao, Y. Peng, X. Xu, Z. Wang, Z. Wu, W. Li, et al., In silico prediction of mitochondrial toxicity of chemicals using machine learning methods, J. Appl. Toxicol., 41 (2021), 1518–1526. https://doi.org/10.1002/jat.4141 doi: 10.1002/jat.4141
|
| [60] |
Y. Yuan, S. Chang, Z. Zhang, Z. Li, S. Li, P. Xie, et al., A novel strategy for prediction of human plasma protein binding using machine learning techniques, Chemometr. Intell. Lab., 199 (2020), 103962. https://doi.org/10.1016/j.chemolab.2020.103962 doi: 10.1016/j.chemolab.2020.103962
|
| [61] |
W. C. Chou, Z. Lin, Machine learning and artificial intelligence in physiologically based pharmacokinetic modeling, Toxicol. Sci., 191 (2023), 1–14. https://doi.org/10.1093/toxsci/kfac101 doi: 10.1093/toxsci/kfac101
|
| [62] | C. Jiang, P. Zhao, W. Li, Y. Tang, G. Liu, In silico prediction of chemical neurotoxicity using machine learning, Toxicol. Res. (Camb), 9 (2020), 164–172. https://doi.org/10.1093%2Ftoxres%2Ftfaa016 |
| [63] |
X. Cui, J. Liu, J. Zhang, Q. Wu, X. Li, In silico prediction of drug-induced rhabdomyolysis with machine-learning models and structural alerts, J. Appl. Toxicol., 39 (2019), 1224–1232. https://doi.org/10.1002/jat.3808 doi: 10.1002/jat.3808
|
| [64] |
I. Sushko, S. Novotarskyi, R. Körner, A. Pandey, M. Rupp, W. Teetz, et al., Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information, J. Comput. Aided. Mol. Des., 25 (2011), 533–554. https://doi.org/10.1007/s10822-011-9440-2 doi: 10.1007/s10822-011-9440-2
|
| [65] | L. M. Lagares, N. Minovski, M. Novič, Multiclass classifier for P-glycoprotein substrates, inhibitors, and non-active compounds, Molecules, 24 (2019), 24102006. https://doi.org/10.3390%2Fmolecules24102006 |
| [66] | FAO The State of Food Insecurity in the World 2001, Rome, 2002. Available from: http://www.fao.org/3/y1500e/y1500e.pdf |
| [67] | P. A. Luning, F. Devlieghere, Safety in the agri-food chain, Wageningen Academic Pub, 2006. Available from: https://doi.org/10.3920/978-90-76998-77-0 |
| [68] |
Z. Han, J. Gao, Pixel-level aflatoxin detecting based on deep learning and hyperspectral imaging, Comput. Electron. Agric., 164 (2019), 104888. https://doi.org/10.1016/j.compag.2019.104888 doi: 10.1016/j.compag.2019.104888
|
| [69] |
F. R. Bertani, L. Businaro, L. Gambacorta, A. Mencattini, D. Brenda, D. Di Giuseppe, et al., Optical detection of aflatoxins B in grained almonds using fluorescence spectroscopy and machine learning algorithms, Food Control, 112 (2020), 107073. https://doi.org/10.1016/j.foodcont.2019.107073 doi: 10.1016/j.foodcont.2019.107073
|
| [70] |
P. Gutiérrez, S. E. Godoy, S. Torres, P. Oyarzún, I. Sanhueza, V. Díaz-García, et al., Improved antibiotic detection in raw milk using machine learning tools over the absorption spectra of a problem-specific nanobiosensor, Sensors, 16 (2020), 4552. https://doi.org/10.3390/s20164552 doi: 10.3390/s20164552
|
| [71] |
S. Qiu, J. Wang, The prediction of food additives in the fruit juice based on electronic nose with chemometrics, Food Chem., 230 (2017), 208–214. https://doi.org/10.1016/j.foodchem.2017.03.011 doi: 10.1016/j.foodchem.2017.03.011
|
| [72] |
F. Han, X. Huang, E. Teye, Novel prediction of heavy metal residues in fish using a low-cost optical electronic tongue system based on colorimetric sensors array, J. Food Process. Eng., 42 (2019), 12983. https://doi.org/10.1111/jfpe.12983 doi: 10.1111/jfpe.12983
|
| [73] | A. Tan, Y. Zhao, K. Sivashanmugan, K. Squire, A. X. Wang, Quantitative TLC-SERS detection of histamine in seafood with support vector machine analysis, Food Control, 103 (2019), 111–118. https://doi.org/10.1016%2Fj.foodcont.2019.03.032 |
| [74] |
H. Isleroglu, S. Beyhan, Prediction of baking quality using machine learning based intelligent models, Heat Mass Transfer, 56 (2020), 2045–2055. https://doi.org/10.1007/s00231-020-02837-6 doi: 10.1007/s00231-020-02837-6
|
| [75] |
H. Lu, H. Zheng, Fractal colour: A new approach for evaluation of acrylamide contents in biscuits, Food Chem., 134 (2012), 2521–2525. https://doi.org/10.1016/j.foodchem.2012.04.085 doi: 10.1016/j.foodchem.2012.04.085
|
| [76] |
A. Yadav, N. Sengar, A. Issac, M. K. Dutta, Image processing based acrylamide detection from fried potato chip images using continuous wavelet transform, Comput. Electron. Agric., 145 (2018), 349–362. https://doi.org/10.1016/j.compag.2018.01.012 doi: 10.1016/j.compag.2018.01.012
|
| [77] |
B. Jiang, J. He, S. Yang, H. Fu, T. Li, H. Song, et al., Fusion of machine vision technology and AlexNet-CNNs deep learning network for the detection of postharvest apple pesticide residues, Artif. Intell. Agricul., 1 (2019), 1–18. https://doi.org/10.1016/j.aiia.2019.02.001 doi: 10.1016/j.aiia.2019.02.001
|
| [78] |
X. Zhou, J. Sun, Y. Tian, B. Lu, Y. Hang, Q. Chen, et al., Hyperspectral technique combined with deep learning algorithm for detection of compound heavy metals in lettuce, Food Chem., 321 (2020), 126503. https://doi.org/10.1016/j.foodchem.2020.126503 doi: 10.1016/j.foodchem.2020.126503
|
| [79] |
W. Hu, S. Chen, Y. Li, Q. Wang, Z. Fang, X-ray absorption spectrum combined with deep neural network for on-line detection of beverage preservatives, Rev. Sci. Instrum., 89 (2018), 103108. https://doi.org/10.1063/1.5048281 doi: 10.1063/1.5048281
|
| [80] |
X. Sun, K. Zhu, J. Liu, J. Hu, X. Jiang, Y. Liu, Terahertz spectroscopy determination of benzoic acid additive in wheat flour by machine learning, J. Infrared Millim. Terahertz Waves, 40 (2019), 466–475. https://doi.org/10.1007/s10762-019-00579-z doi: 10.1007/s10762-019-00579-z
|
| [81] |
N. Nikolova-Jeliazkova, J. Jaworska, An approach to determining applicability domains for QSAR group contribution models: An Analysis of SRC KOWWIN, Alt-Altern. Lab. Anim., 33 (2005), 461–470. https://doi.org/10.1177/026119290503300510 doi: 10.1177/026119290503300510
|
| [82] |
X. Yu, Q. Zeng, Random forest algorithm-based classification model of pesticide aquatic toxicity to fishes, Aquatic Toxicol., 251 (2022), 106265. https://doi.org/10.1016/j.aquatox.2022.106265 doi: 10.1016/j.aquatox.2022.106265
|
| [83] |
F. Li, G. Sun, T. Fan, N. Zhang, L. Zhao, R. Zhong, et al., Ecotoxicological QSAR modelling of the acute toxicity of fused and non-fused polycyclic aromatic hydrocarbons (FNFPAHs) against two aquatic organisms: Consensus modelling and comparison with ECOSAR, Aquatic Toxicol., 255 (2023), 106393. https://doi.org/10.1016/j.aquatox.2022.106393 doi: 10.1016/j.aquatox.2022.106393
|
| [84] |
G. J. Lavado, D. Baderna, D. Gadaleta, M. Ultre, K. Roy, E. Benfenati, Ecotoxicological QSAR modeling of the acute toxicity of organic compounds to the freshwater crustacean Thamnocephalus platyurus, Chemosphere, 280 (2021), 130652. https://doi.org/10.1016/j.chemosphere.2021.130652 doi: 10.1016/j.chemosphere.2021.130652
|
| [85] |
G. Sun, Y. Zhang, L. Pei, Y. Lou, Y. Mu, J. Yun, et al., Chemometric QSAR modeling of acute oral toxicity of Polycyclic Aromatic Hydrocarbons (PAHs) to rat using simple 2D descriptors and interspecies toxicity modeling with mouse, Ecotoxicol. Environ. Safe, 222 (2021), 112525. https://doi.org/10.1016/j.ecoenv.2021.112525 doi: 10.1016/j.ecoenv.2021.112525
|
| [86] |
P. Banjare, J. Singh, P. P. Roy, Predictive classification-based QSTR models for toxicity study of diverse pesticides on multiple avian species, Environ. Sci. Pollut. Res., 28 (2021), 17992–18003. https://doi.org/10.1007/s11356-020-11713-z doi: 10.1007/s11356-020-11713-z
|
| [87] |
S. Samanipour, J. W. O'Brien, M. J. Reid, K. V. Thomas, A. Praetorius, From Molecular Descriptors to Intrinsic Fish Toxicity of Chemicals: An Alternative Approach to Chemical Prioritization, Environ. Sci. Technol., (2022), 1–9. https://doi.org/10.1021/acs.est.2c07353 doi: 10.1021/acs.est.2c07353
|
| [88] |
P. Banjare, J. Singh, E. Papa, P. P. Roy, Aquatic toxicity prediction of diverse pesticides on two algal species using QSTR modeling approach, Environ. Sci. Pollut. Res., 30 (2023), 10599–10612. https://doi.org/10.1007/s11356-022-22635-3 doi: 10.1007/s11356-022-22635-3
|
| [89] |
Y. Hao, T. Fan, G. Sun, F. Li, N. Zhang, L. Zhao, et al., Environmental toxicity risk evaluation of nitroaromatic compounds: Machine learning driven binary/multiple classification and design of safe alternatives, Food Chem. Toxicol., 170 (2022), 113461. https://doi.org/10.1016/j.fct.2022.113461 doi: 10.1016/j.fct.2022.113461
|
| [90] |
M. Xu, H. Yang, G. Liu, W. Li, In silico prediction of chemical aquatic toxicity by multiple machine learning and deep learning approaches, J. Appl. Toxicol., 42 (2022), 1766–1776. https://doi.org/10.1002/jat.4354 doi: 10.1002/jat.4354
|
| [91] |
O. V. Tinkov, V. Y. Grigorev, L. D. Grigoreva, QSAR analysis of the acute toxicity of avermectins towards Tetrahymena pyriformis, SAR QSAR Environ. Res., 32 (2021), 541–571. https://doi.org/10.1080/1062936x.2021.1932583 doi: 10.1080/1062936x.2021.1932583
|
| [92] |
T. Zhu, Y. Chen, C. Tao, Multiple machine learning algorithms assisted QSPR models for aqueous solubility: Comprehensive assessment with CRITIC-TOPSIS, Sci. Total Environ., 857 (2023), 159448. https://doi.org/10.1016/j.scitotenv.2022.159448 doi: 10.1016/j.scitotenv.2022.159448
|
| [93] |
X. Xu, P. Zhao, Z. Wang, X. Zhang, Z. Wu, W. Li, et al., In silico prediction of chemical acute contact toxicity on honey bees via machine learning methods, Toxicol. Vitro., 72 (2021), 105089. https://doi.org/10.1016/j.tiv.2021.105089 doi: 10.1016/j.tiv.2021.105089
|
| [94] |
K. P. Singh, N. Basant, S. Gupta, Support vector machines in water quality management, Anal. Chim. Acta., 703 (2011), 152–162. https://doi.org/10.1016/j.aca.2011.07.027 doi: 10.1016/j.aca.2011.07.027
|
| [95] |
P. Lauret, F. Heymes, L. Aprin, A. Johannet, Atmospheric dispersion modeling using Artificial Neural Network based cellular automata, Environ. Modell. Software, 85 (2016), 56–69. https://doi.org/10.1016/j.envsoft.2016.08.001 doi: 10.1016/j.envsoft.2016.08.001
|
| [96] |
K. P. Singh, S. Gupta, P. Rai, Predicting acute aquatic toxicity of structurally diverse chemicals in fish using artificial intelligence approaches, Ecotoxicol. Environ. Safe., 95 (2013), 221–233. https://doi.org/10.1016/j.ecoenv.2013.05.017 doi: 10.1016/j.ecoenv.2013.05.017
|
| [97] | T. H. Miller, M. D. Gallidabino, J. I. MacRae, S. F. Owen, N. R. Bury, L. P. Barron, Prediction of bioconcentration factors in fish and invertebrates using machine learning, Sci. Total. Environ., 648 (2019), 80–89. https://doi.org/10.1016%2Fj.scitotenv.2018.08.122 |
| [98] |
N. X. Tan, P. Li, H. B. Rao, Z. R. Li, X. Y. Li, Prediction of the acute toxicity of chemical compounds to the fathead minnow by machine learning approaches, Chemom. Intell. Lab. Syst., 100 (2010), 66–73. https://doi.org/10.1016/j.chemolab.2009.11.002 doi: 10.1016/j.chemolab.2009.11.002
|
| [99] |
D. Bingöl, M. Hercan, S. Elevli, E. Kılıç, Comparison of the results of response surface methodology and artificial neural network for the biosorption of lead using black cumin, Bioresour. Technol., 112 (2012), 111–115. https://doi.org/10.1016/j.biortech.2012.02.084 doi: 10.1016/j.biortech.2012.02.084
|
| [100] |
N. G. Turan, B. Mesci, O. Ozgonenel, Artificial neural network (ANN) approach for modeling Zn(Ⅱ) adsorption from leachate using a new biosorbent, Chem. Eng. J., 173 (2011), 98–105. https://doi.org/10.1016/j.cej.2011.07.042 doi: 10.1016/j.cej.2011.07.042
|
| [101] |
A. P. Sergeev, A. G. Buevich, E. M. Baglaeva, A. V. Shichkin, Combining spatial autocorrelation with machine learning increases prediction accuracy of soil heavy metals, Catena, 174 (2019), 425–435. https://doi.org/10.1016/j.catena.2018.11.037 doi: 10.1016/j.catena.2018.11.037
|
| [102] |
N. G. Turan, E. B. Gümüşel, O. Ozgonenel, Prediction of heavy metal removal by different liner materials from landfill leachate: Modeling of experimental results using artificial intelligence technique, Sci. World J., 2013 (2013), 240158. https://doi.org/10.1155/2013/240158 doi: 10.1155/2013/240158
|
| [103] |
M. González García, C. Fernández-López, A. Bueno-Crespo, R. Martínez-España, Extreme learning machine-based prediction of uptake of pharmaceuticals in reclaimed water-irrigated lettuces in the Region of Murcia, Spain, Biosyst. Eng., 177 (2019), 78–89. https://doi.org/10.1016/j.biosystemseng.2018.09.006 doi: 10.1016/j.biosystemseng.2018.09.006
|
| [104] |
Y. Kobayashi, T. Uchida, K. Yoshida, Prediction of Soil Adsorption Coefficient in Pesticides Using Physicochemical Properties and Molecular Descriptors by Machine Learning Models, Environ. Toxicol. Chem., 39 (2020), 1451–1459. https://doi.org/10.1002/etc.4724 doi: 10.1002/etc.4724
|
| [105] |
J. Sayyad Amin, H. Rajabi Kuyakhi, A. Bahadori, Prediction of formation of polycyclic aromatic hydrocarbon (PAHs) on sediment of Caspian Sea using artificial neural networks, Petrol. Sci. Technol., 37 (2019), 1987–2000. https://doi.org/10.1080/10916466.2018.1496111 doi: 10.1080/10916466.2018.1496111
|
| [106] |
R. Olawoyin, Application of backpropagation artificial neural network prediction model for the PAH bioremediation of polluted soil, Chemosphere, 161 (2016), 145–150. https://doi.org/10.1016/j.chemosphere.2016.07.003 doi: 10.1016/j.chemosphere.2016.07.003
|
| [107] |
G. Wu, C. Kechavarzi, C. Li, S. Wu, S. J. Pollard, H. Sui, et al., Machine learning models for predicting PAHs bioavailability in compost amended soils, Chem. Eng. J., 223 (2013), 747–754. https://doi.org/10.1016/j.cej.2013.02.122 doi: 10.1016/j.cej.2013.02.122
|
| [108] |
X. Li, Y. Zhang, H. Chen, H. Li, Y. Zhao, Insights into the Molecular Basis of the Acute Contact Toxicity of Diverse Organic Chemicals in the Honey Bee, J. Chem. Inf. Model., 57 (2017), 2948–2957. https://doi.org/10.1021/acs.jcim.7b00476 doi: 10.1021/acs.jcim.7b00476
|
| [109] | S. H. McArt, C. Urbanowicz, S. McCoshum, R. E. Irwin, L. S. Adler, Landscape predictors of pathogen prevalence and range contractions in US bumblebees, Proc. R. Soc. B: Biol. Sci., 284 (2017), 2017181. https://doi.org/10.1098%2Frspb.2017.2181 |
| [110] |
G. Yang, H. M. Lee, G. Lee, A hybrid deep learning model to forecast particulate matter concentration levels in Seoul, South Korea, Atmosphere, 11 (2020), 348. https://doi.org/10.3390/atmos11040348 doi: 10.3390/atmos11040348
|
| [111] |
G. Cervone, P. Franzese, Y. Ezber, Z. Boybeyi, Risk assessment of atmospheric emissions using machine learning, Nat. Hazard. Earth. Syst. Sci., 8 (2008), 991–1000. https://doi.org/10.5194/nhess-8-991-2008 doi: 10.5194/nhess-8-991-2008
|
| [112] |
S. Lopez-Aparicio, H. Grythe, M. Vogt, M. Pierce, I. Vallejo, Webcrawling and machine learning as a new approach for the spatial distribution of atmospheric emissions, PLoS One, 13 (2018), 0200650. https://doi.org/10.1371/journal.pone.0200650 doi: 10.1371/journal.pone.0200650
|
| [113] |
D. Ma, Z. Zhang, Contaminant dispersion prediction and source estimation with integrated Gaussian-machine learning network model for point source emission in atmosphere, J. Hazard. Mater., 311 (2016), 237–245. https://doi.org/10.1016/j.jhazmat.2016.03.022 doi: 10.1016/j.jhazmat.2016.03.022
|
| [114] |
Y. Zhan, Y. Luo, X. Deng, H. Chen, M. L. Grieneisen, X. Shen, et al., Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm, Atmos. Environ., 155 (2017), 129–139. https://doi.org/10.1016/j.atmosenv.2017.02.023 doi: 10.1016/j.atmosenv.2017.02.023
|
| [115] | C. Coelho, M. R. Martins, N. Lima, H. Vicente, J. Neves, An assessment to toxicological risk of pesticide exposure, In: Communications in Computer and Information Science, 2016,139–150. https://doi.org/10.1007/978-3-319-44672-1_12 |
| [116] |
K. Mansouri, A. L. Karmaus, J. Fitzpatrick, G. Patlewicz, P. Pradeep, D. Alberga, et al., CATMoS: Collaborative acute toxicity modeling suite, Environ Health Perspect, 129 (2021), 47013. https://doi.org/10.1289/EHP8495 doi: 10.1289/EHP8495
|
| [117] |
E. H. Acosta-Jiménez, L. A. Zárate-Hernández, R. L. Camacho-Mendoza, S. González-Montiel, J. Alvarado-Rodríguez, C. Z. Gómez-Castro, et al. QSTR Modeling to Find Relevant DFT Descriptors Related to the Toxicity of Carbamates, Molecules, 27 (2022), 5530. https://doi.org/10.3390/molecules27175530 doi: 10.3390/molecules27175530
|
| [118] |
M. Kotzabasaki, I. Sotiropoulos, C. Charitidis, H. Sarimveis, Machine learning methods for multi-walled carbon nanotubes (MWCNT) genotoxicity prediction, Nanoscale. Adv., 3 (2021), 3167–3176. http://dx.doi.org/10.1039/D0NA00600A doi: 10.1039/D0NA00600A
|
| [119] |
M. M. Wehr, S. S. Sarang, M. Rooseboom, P. J. Boogaard, A. Karwath, S. E. Escher, RespiraTox —Development of a QSAR model to predict human respiratory irritants, Regul. Toxicol. Pharm., 128 (2022), 105089. https://doi.org/10.1016/j.yrtph.2021.105089 doi: 10.1016/j.yrtph.2021.105089
|
| [120] |
R. Zendehdel, S. V. Shetab-Boushehri, M. R. Azari, V. Hosseini, H. Mohammadi, Chemometrics models for assessment of oxidative stress risk in chrome-electroplating workers, Drug Chem. Toxicol., 38 (2015), 174–179. https://doi.org/10.3109/01480545.2014.922096 doi: 10.3109/01480545.2014.922096
|
| [121] |
J. Black, G. Benke, K. Smith, L. Fritschi, Artificial neural networks and job-specific modules to assess occupational exposure, Ann. Occup. Hyg., 48 (2004), 595–600. https://doi.org/10.1093/annhyg/meh064 doi: 10.1093/annhyg/meh064
|
| [122] |
K. L. Johnston, M. L. Phillips, N. A. Esmen, T. A. Hall, Evaluation of an artificial intelligence program for estimating occupational exposures, Ann. Occup. Hyg., 49 (2005), 147–153. https://doi.org/10.1093/annhyg/meh072 doi: 10.1093/annhyg/meh072
|
| [123] |
Y. N. Li, F. T. Luo, Y. M. Jiang, Y. R, Lu, J. L. Huang, Z. B. Zhang, A prediction model of occupational manganese exposure based on artificial neural network, Toxicol. Mech. Method., 19 (2009), 337–345. https://doi.org/10.1080/15376510902918392 doi: 10.1080/15376510902918392
|
| [124] |
P. E. Sottas, J. Lavoué, R. Bruzzi, D. Vernez, N. Charrière, P. O. Droz, An empirical hierarchical Bayesian unification of occupational exposure assessment methods, Stat. Med., 28 (2009), 75–93. https://doi.org/10.1002/sim.3411 doi: 10.1002/sim.3411
|
| [125] |
F. A. Moayed, R. L. Shell, Developing the function of 'magnitude-of-effect' (MoE) for artificial neural networks to demonstrate the causal effect of exposure variables on outcome variable, Ann. Occup. Hyg., 55 (2011), 143–151. https://doi.org/10.1093/annhyg/meq080 doi: 10.1093/annhyg/meq080
|
| [126] |
F. A. Moayed, R. L. Shell, Application of artificial neural network models in occupational safety and health utilizing ordinal variables, Ann. Occup. Hyg., 55 (2011), 132–142. https://doi.org/10.1093/annhyg/meq079 doi: 10.1093/annhyg/meq079
|
| [127] |
J. M. Gernand, E. A. Casman, Nanoparticle characteristic interaction effects on pulmonary toxicity: A random forest modeling framework to compare risks of nanomaterial variants, ASCE-ASME J. Risk Uncertain Eng. Syst. B: Mech. Eng., 2 (2016), 021002. https://doi.org/10.1115/1.4031216 doi: 10.1115/1.4031216
|
| [128] |
R. Concu, V. V. Kleandrova, A. Speck-Planche, M. N. D. S. Cordeiro, Probing the toxicity of nanoparticles: A unified in silico machine learning model based on perturbation theory, Nanotoxicology, 11 (2017), 891–906. https://doi.org/10.1080/17435390.2017.1379567 doi: 10.1080/17435390.2017.1379567
|
| [129] |
F. Luan, V. V. Kleandrova, H. González-Díaz, J. M. Ruso, A. Melo, A. Sperck-Planceh, et al., Computer-aided nanotoxicology: Assessing cytotoxicity of nanoparticles under diverse experimental conditions by using a novel QSTR-perturbation approach, Nanoscale, 6 (2014), 10623–10630. http://dx.doi.org/10.1039/c4nr01285b doi: 10.1039/c4nr01285b
|
| [130] |
V. V. Kleandrova, F. Luan, H. González-Díaz, J. M. Ruso, A. Speck-Planche, M. N. D. Cordeiro, Computational tool for risk assessment of nanomaterials: Novel QSTR-perturbation model for simultaneous prediction of ecotoxicity and cytotoxicity of uncoated and coated nanoparticles under multiple experimental conditions, Environ. Sci. Technol., 48 (2014), 14686–14694. https://doi.org/10.1021/es503861x doi: 10.1021/es503861x
|
| [131] |
V. V. Kleandrova, F. Luan, H. González-Díaz, J. M. Ruso, A. Speck-Planche, M. N. D. Cordeiro, Computational ecotoxicology: Simultaneous prediction of ecotoxic effects of nanoparticles under different experimental conditions, Environ. Int., 73 (2014), 288–294. https://doi.org/10.1016/j.envint.2014.08.009 doi: 10.1016/j.envint.2014.08.009
|
| [132] |
V. Ramchandran, J. M. Gernand, Examining the in vivo pulmonary toxicity of engineered metal oxide nanomaterials using a genetic algorithm-based dose-response-recovery clustering model, Comput. Toxicol., 13 (2020), 100113. https://doi.org/10.1016/j.comtox.2019.100113 doi: 10.1016/j.comtox.2019.100113
|
Efrén Pérez-Santín, Luis de-la-Fuente-Valentín, Mariano González García, Kharla Andreina Segovia Bravo, Fernando Carlos López Hernández, José Ignacio López Sánchez. Applicability domains of neural networks for toxicity prediction[J]. AIMS Mathematics, 2023, 8(11): 27858-27900. doi: 10.3934/math.20231426
DownLoad: