1
|
Xiao Z, Zhu M, Chen J, You Z. Integrated Transfer Learning and Multitask Learning Strategies to Construct Graph Neural Network Models for Predicting Bioaccumulation Parameters of Chemicals. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2024; 58:15650-15660. [PMID: 39051472 DOI: 10.1021/acs.est.4c02421] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/27/2024]
Abstract
Accurate prediction of parameters related to the environmental exposure of chemicals is crucial for the sound management of chemicals. However, the lack of large data sets for training models may result in poor prediction accuracy and robustness. Herein, integrated transfer learning (TL) and multitask learning (MTL) was proposed for constructing a graph neural network (GNN) model (abbreviated as TL-MTL-GNN model) using n-octanol/water partition coefficients as a source domain. The TL-MTL-GNN model was trained to predict three bioaccumulation parameters based on enlarged data sets that cover 2496 compounds with at least one bioaccumulation parameter. Results show that the TL-MTL-GNN model outperformed single-task GNN models with and without the TL, as well as conventional machine learning models trained with molecular descriptors or fingerprints. Applicability domains were characterized by a state-of-the-art structure-activity landscape-based (abbreviated as ADSAL) methodology. The TL-MTL-GNN model coupled with the optimal ADSAL was employed to predict bioaccumulation parameters for around 60,000 chemicals, with more than 13,000 compounds identified as bioaccumulative chemicals. The high predictive accuracy and robustness of the TL-MTL-GNN model demonstrate the feasibility of integrating the TL and MTL strategy in modeling small-sized data sets. The strategy holds significant potential for addressing small data challenges in modeling environmental chemicals.
Collapse
Affiliation(s)
- Zijun Xiao
- Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education), Dalian Key Laboratory on Chemicals Risk Control and Pollution Prevention Technology, School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China
| | - Minghua Zhu
- Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education), Dalian Key Laboratory on Chemicals Risk Control and Pollution Prevention Technology, School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China
- Key Laboratory of Integrated Regulation and Resources Development of Shallow Lakes of Ministry of Education, College of Environment, Hohai University, Nanjing 210098, China
| | - Jingwen Chen
- Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education), Dalian Key Laboratory on Chemicals Risk Control and Pollution Prevention Technology, School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China
| | - Zecang You
- Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education), Dalian Key Laboratory on Chemicals Risk Control and Pollution Prevention Technology, School of Environmental Science and Technology, Dalian University of Technology, Dalian 116024, China
| |
Collapse
|
2
|
Di S, Liu R, Chen L, Diao J, Zhou Z. Selective bioaccumulation, biomagnification, and dissipation of hexachlorocyclohexane isomers in a freshwater food chain. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2018; 25:18752-18761. [PMID: 29713971 DOI: 10.1007/s11356-018-2044-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/12/2017] [Accepted: 04/16/2018] [Indexed: 06/08/2023]
Abstract
Hexachlorocyclohexane isomers (HCHs) are persistent organic pollutants (POPs), having potential risks to humans and ecosystem. This work evaluated the propensity of organisms to accumulate, eliminate, and transfer HCHs along the food chain (Tubifex tubifex and common carp (Cyprinus carpio)). The accumulation of HCHs from water by worms and carp was observed, and the concentrations increased with exposure time. After 8 days, the HCH concentrations in organisms remained stable. The accumulation factor (AF) values of HCHs in T. tubifex were higher than those in carp, indicating that the bioaccumulation abilities of HCHs in T. tubifex were higher than those in carp. The contaminated worms as a dietary source in the food chain led to significantly higher bioaccumulation in carp. The biomagnification factor (BMF) values of HCH isomers were all greater than 1. In the dissipation experiments, the elimination was fast and the half-lives were shorter than 2.5 days. The enantioselective accumulation and dissipation of α-HCH enantiomers were observed in worms and carp (food chain), and the enantiomeric differences should be taken into consideration in the study of contaminants risk assessment. The results on trophic transfer of HCHs in a freshwater food chain should be helpful for better understanding the fate, transport, and transfer of HCHs in freshwater environments.
Collapse
Affiliation(s)
- Shanshan Di
- Institute of Quality and Standard of Agro-Products, Zhejiang Academy of Agricultural Sciences, Hangzhou, 310021, China
- Agricultural Ministry Key Laboratory for Pesticide Residue Detection, Hangzhou, 310021, China
- Key Laboratory of Detection for Pesticide Residues and Control of Zhejiang, Hangzhou, 310021, China
| | - Ruiquan Liu
- Department of Applied Chemistry, China Agricultural University, Yuanmingyuan West Road 2, Beijing, 100193, China
| | - Li Chen
- Department of Applied Chemistry, China Agricultural University, Yuanmingyuan West Road 2, Beijing, 100193, China
- Beijing Advanced Innovation Center for Food Nutrition and Human Health, Department of Applied Chemistry, China Agricultural University, Yuanmingyuan west road 2, Beijing, 100193, People's Republic of China
| | - Jinling Diao
- Department of Applied Chemistry, China Agricultural University, Yuanmingyuan West Road 2, Beijing, 100193, China
| | - Zhiqiang Zhou
- Department of Applied Chemistry, China Agricultural University, Yuanmingyuan West Road 2, Beijing, 100193, China.
- Beijing Advanced Innovation Center for Food Nutrition and Human Health, Department of Applied Chemistry, China Agricultural University, Yuanmingyuan west road 2, Beijing, 100193, People's Republic of China.
| |
Collapse
|
3
|
de Solla SR. Exposure, Bioaccumulation, Metabolism and Monitoring of Persistent Organic Pollutants in Terrestrial Wildlife. THE HANDBOOK OF ENVIRONMENTAL CHEMISTRY 2015. [DOI: 10.1007/698_2015_450] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/19/2023]
|
4
|
Dearden JC, Rowe PH. Use of artificial neural networks in the QSAR prediction of physicochemical properties and toxicities for REACH legislation. Methods Mol Biol 2015; 1260:65-88. [PMID: 25502376 DOI: 10.1007/978-1-4939-2239-0_5] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
With the introduction of the REACH legislation in the European Union, there is a requirement for property and toxicity data on chemicals produced in or imported into the EU at levels of 1 tonne/year or more. This has meant an increase in the in silico prediction of such data. One of the chief predictive approaches is QSAR (quantitative structure-activity relationships), which is widely used in many fields. A QSAR approach that is increasingly being used is that of artificial neural networks (ANNs), and this chapter discusses its application to the range of physicochemical properties and toxicities required by REACH. ANNs generally outperform the main QSAR approach of multiple linear regression (MLR), although other approaches such as support vector machines sometimes outperform ANNs. Most ANN QSARs reported to date comply with only two of the five OECD Guidelines for the Validation of (Q)SARs.
Collapse
Affiliation(s)
- John C Dearden
- School of Pharmacy & Biomolecular Sciences, Liverpool John Moores University, Byrom Street, Liverpool, L3 3AF, UK,
| | | |
Collapse
|
5
|
Poole CF, Ariyasena TC, Lenca N. Estimation of the environmental properties of compounds from chromatographic measurements and the solvation parameter model. J Chromatogr A 2013; 1317:85-104. [DOI: 10.1016/j.chroma.2013.05.045] [Citation(s) in RCA: 122] [Impact Index Per Article: 11.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2013] [Revised: 04/15/2013] [Accepted: 05/20/2013] [Indexed: 11/29/2022]
|
6
|
Abstract
Structure-activity relationship (SAR) and quantitative structure-activity relationship (QSAR) models are increasingly used in toxicology, ecotoxicology, and pharmacology for predicting the activity of the molecules from their physicochemical properties and/or their structural characteristics. However, the design of such models has many traps for unwary practitioners. Consequently, the purpose of this chapter is to give a practical guide for the computation of SAR and QSAR models, point out problems that may be encountered, and suggest ways of solving them. Attempts are also made to see how these models can be validated and interpreted.
Collapse
|
7
|
Jalali-Heravi M, Mani-Varnosfaderani A. QSAR modelling of integrin antagonists using enhanced Bayesian regularised genetic neural networks. SAR AND QSAR IN ENVIRONMENTAL RESEARCH 2011; 22:293-314. [PMID: 21598195 DOI: 10.1080/1062936x.2011.569758] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/30/2023]
Abstract
Bayesian regularised genetic neural network (BRGNN) has been used for modelling the inhibition activity of 141 biphenylalanine derivatives as integrin antagonists. Three local pattern search (PS) methods, simulated annealing and threshold acceptance were combined with BRGNN in the form of a hybrid genetic algorithm (HGA). The results obtained revealed that PS is a suitable method for improving the ability of BRGNN to break out from the local minima. The proposed HGA technique is able to retrieve important variables from complex systems and nonlinear search spaces for optimisation. Two models with 8-3-1 artificial neural network (ANN) architectures were developed for describing α₄β₇ and α₄β₁ modulatory activities of integrin antagonists. Monte Carlo cross-validation was performed to validate the models and Q₂ values of 0.75 and 0.74 were obtained for α₄β₇ and α₄β₁ inhibitory activities, respectively. The scrambling technique was used for sensitivity analysis of descriptors appearing in ANN models. Frequencies of repetition and sensitivity analysis of molecular descriptors revealed that 3D-Morse descriptors are influential factors for describing α₄β₇ inhibitory activity, while in the case of α₄β₁ inhibitory activity, the Randic shape index, the lowest eigenvalue of the Burden matrix and the number of rotatable bonds are important parameters.
Collapse
Affiliation(s)
- M Jalali-Heravi
- Department of Chemistry, Sharif University of Technology, Tehran, Iran.
| | | |
Collapse
|