1
|
Fan D, Xue K, Zhang R, Zhu W, Zhang H, Qi J, Zhu Z, Wang Y, Cui P. Application of interpretable machine learning models to improve the prediction performance of ionic liquids toxicity. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 908:168168. [PMID: 37918734 DOI: 10.1016/j.scitotenv.2023.168168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/30/2023] [Revised: 10/23/2023] [Accepted: 10/26/2023] [Indexed: 11/04/2023]
Abstract
With the wide application prospect of ionic liquids (ILs) as solvent in the future industry, in order to promote green and sustainable chemical engineering, the toxicity problem of common concern has been systematically modeled. Machine learning has promoted the development of chemical property prediction model with its powerful data processing ability. Two typical ensemble learning models, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), were used to model the toxicity of ILs to Vibrio fischeri in this work. The model's hyperparameters were fine-tuned using Bayesian optimization, and its robustness was enhanced through the 5-fold cross validation. The results of the model comparison showed that the XGBoost model exhibited good generalization ability. In addition, the SHapley Additive exPlanations (SHAP) method was used to explain the model in more detail and the XGBoost model was used to supplement the toxicity value matrix of 1590 ILs.
Collapse
Affiliation(s)
- Dingchao Fan
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Ke Xue
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Runqi Zhang
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Wenguang Zhu
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Hongru Zhang
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Jianguang Qi
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Zhaoyou Zhu
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| | - Yinglong Wang
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China.
| | - Peizhe Cui
- College of Chemical Engineering, Qingdao University of Science and Technology, 53Zhengzhou Road, Qingdao 266042, People's Republic of China
| |
Collapse
|
2
|
Role of Fungi in Biodegradation of Imidazolium Ionic Liquids by Activated Sewage Sludge. Molecules 2023; 28:molecules28031268. [PMID: 36770935 PMCID: PMC9919375 DOI: 10.3390/molecules28031268] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 01/07/2023] [Accepted: 01/12/2023] [Indexed: 02/03/2023] Open
Abstract
Ionic liquids (ILs), due to their specific properties, can play the role of persistent water contaminants. Fungi manifest the ability to decompose hardy degradable compounds, showing potential in the biodegradation of ILs, which has been studied extensively on sewage sludge; however, attention was drawn mainly to bacterial and not fungal species. The aim of the research was to determine the significance of fungi in ILs' biodegradation to extend the knowledge and possibly point out ways of increasing their role in this process. The research included: the isolation and genetic identification of fungal strains potentially capable of [OMIM][Cl], [BMIM][Cl], [OMIM][Tf2N], and [BMIM][Tf2N] degradation, adjustment of the ILs concentration for biodegradability test by MICs determination and choosing strains with the highest biological robustness; inoculum adaptation tests, and finally primary biodegradation by OECD 301F test. The study, conducted for 2 mM [OMIM][Cl] as a tested substance and consortium of microorganisms as inoculum, resulted in an average 64.93% biodegradation rate within a 28-day testing period. For the individual fungal strain (Candida tropicalis), the maximum of only 4.89% biodegradation rate was reached in 10 days, then inhibited. Insight into the role of fungi in the biodegradation of ILs was obtained, enabling the creation of a complex overview of ILs toxicity and the possibilities of its biological use. However, only an inoculum consisting of a consortium of microorganisms enriched with a selected strain of fungi was able to decompose the IL, in contrast to that consisting only of an individual fungal strain.
Collapse
|
3
|
Makarov D, Fadeeva Y, Safonova E, Shmukler L. Predictive modeling of antibacterial activity of ionic liquids by machine learning methods. Comput Biol Chem 2022; 101:107775. [DOI: 10.1016/j.compbiolchem.2022.107775] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Revised: 09/24/2022] [Accepted: 10/03/2022] [Indexed: 11/03/2022]
|
4
|
Application of atomic electrostatic potential descriptors for predicting the eco-toxicity of ionic liquids towards leukemia rat cell line. Chem Eng Sci 2022. [DOI: 10.1016/j.ces.2022.117941] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
5
|
Deep Probabilistic Learning Model for Prediction of Ionic Liquids Toxicity. Int J Mol Sci 2022; 23:ijms23095258. [PMID: 35563648 PMCID: PMC9104997 DOI: 10.3390/ijms23095258] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2022] [Revised: 05/06/2022] [Accepted: 05/06/2022] [Indexed: 12/10/2022] Open
Abstract
Identification of ionic liquids with low toxicity is paramount for applications in various domains. Traditional approaches used for determining the toxicity of ionic liquids are often expensive, and can be labor intensive and time consuming. In order to mitigate these limitations, researchers have resorted to using computational models. This work presents a probabilistic model built from deep kernel learning with the aim of predicting the toxicity of ionic liquids in the leukemia rat cell line (IPC-81). Only open source tools, namely, RDKit and Mol2vec, are required to generate predictors for this model; as such, its predictions are solely based on chemical structure of the ionic liquids and no manual extraction of features is needed. The model recorded an RMSE of 0.228 and R2 of 0.943. These results indicate that the model is both reliable and accurate. Furthermore, this model provides an accompanying uncertainty level for every prediction it makes. This is important because discrepancies in experimental measurements that generated the dataset used herein are inevitable, and ought to be modeled. A user-friendly web server was developed as well, enabling researchers and practitioners ti make predictions using this model.
Collapse
|
6
|
Parajó JJ, Vallet P, Varela LM, Villanueva M, Salgado J. Ecotoxicity of binary mixtures of ILs and inorganic salts of electrochemical interest. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2022; 29:24983-24994. [PMID: 34839439 PMCID: PMC8986726 DOI: 10.1007/s11356-021-17515-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Accepted: 11/09/2021] [Indexed: 06/13/2023]
Abstract
The applicability of ionic liquids (ILs) has increased over the last years, and even new opportunities are becoming a reality, i.e. mixtures of pure IL and inorganic salt as electrolytes for smart electrochemical devices, yet the effects on the environment are almost unknown. In this work, the ecotoxicity of two pure protic ILs (Ethylammonium nitrate and Ethylimidazolium nitrate) and two pure aprotic ILs (butylmethylpyrrolidinium bis(trifluoromethylsulfonyl)imide and butyldimethylimidazolium bis(trifluoromethylsulfonyl)imide) and that of their binary mixtures with inorganic salts with common cation was tested towards changes in the bioluminescence of the bacteria Aliivibrio fischeri, using the Microtox® standard toxicity test. EC50 of these mixtures was determined over three standard periods of time and compared with the corresponding values to pure ILs. Results indicate that the aprotic ILs are more toxic than protic and that aromatic are more toxic than non-aromatic. The addition of inorganic mono (LiNO3), di (Ca(NO3)2·4H2O, Mg(NO3)2·6H2O) and trivalent (Al(NO3)3·9H2O) salts in binary mixtures with EAN was analysed first. The latter was found to induce an important increase in toxicity. Finally, mixtures of IL-inorganic lithium salt (LiNO3, for the protic ILs and LiTFSI for the aprotic ILs) toxicity was also studied, which showed toxicity levels strongly dependent on the IL of the mixture.
Collapse
Affiliation(s)
- Juan José Parajó
- NAFOMAT Group, Departamentos de Física Aplicada y Física de Partículas, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain
- Departamento de Química e Bioquímica, CIQUP - Centro de Investigação em Química da Universidade do Porto, Universidade do Porto, P-4169-007, Porto, Portugal
| | - Pablo Vallet
- NAFOMAT Group, Departamentos de Física Aplicada y Física de Partículas, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain
| | - Luis Miguel Varela
- NAFOMAT Group, Departamentos de Física Aplicada y Física de Partículas, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain
| | - María Villanueva
- NAFOMAT Group, Departamentos de Física Aplicada y Física de Partículas, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain
| | - Josefa Salgado
- NAFOMAT Group, Departamentos de Física Aplicada y Física de Partículas, Universidade de Santiago de Compostela, 15782, Santiago de Compostela, Spain.
| |
Collapse
|
7
|
Yan J, Yan X, Hu S, Zhu H, Yan B. Comprehensive Interrogation on Acetylcholinesterase Inhibition by Ionic Liquids Using Machine Learning and Molecular Modeling. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2021; 55:14720-14731. [PMID: 34636548 DOI: 10.1021/acs.est.1c02960] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Quantitative structure-activity relationship (QSAR) modeling can be used to predict the toxicity of ionic liquids (ILs), but most QSAR models have been constructed by arbitrarily selecting one machine learning method and ignored the overall interactions between ILs and biological systems, such as proteins. In order to obtain more reliable and interpretable QSAR models and reveal the related molecular mechanism, we performed a systematic analysis of acetylcholinesterase (AChE) inhibition by 153 ILs using machine learning and molecular modeling. Our results showed that more reliable and stable QSAR models (R2 > 0.85 for both cross-validation and external validation) were obtained by combining the results from multiple machine learning approaches. In addition, molecular docking results revealed that the cations and organic anions of ILs bound to specific amino acid residues of AChE through noncovalent interactions such as π interactions and hydrogen bonds. The calculation results of binding free energy showed that an electrostatic interaction (ΔEele < -285 kJ/mol) was the main driving force for the binding of ILs to AChE. The overall findings from this investigation demonstrate that a systematic approach is much more convincing. Future research in this direction will help design the next generation of biosafe ILs.
Collapse
Affiliation(s)
- Jiachen Yan
- Institute of Environmental Research at Greater Bay Area, Key Laboratory for Water Quality and Conservation of the Pearl River Delta, Ministry of Education, Guangzhou University, Guangzhou 510006, People's Republic of China
| | - Xiliang Yan
- Institute of Environmental Research at Greater Bay Area, Key Laboratory for Water Quality and Conservation of the Pearl River Delta, Ministry of Education, Guangzhou University, Guangzhou 510006, People's Republic of China
| | - Song Hu
- School of Environmental Science and Engineering, Shandong University, Qingdao 266237, People's Republic of China
| | - Hao Zhu
- The Rutgers Center for Computational and Integrative Biology, Camden, New Jersey 08102, United States
| | - Bing Yan
- Institute of Environmental Research at Greater Bay Area, Key Laboratory for Water Quality and Conservation of the Pearl River Delta, Ministry of Education, Guangzhou University, Guangzhou 510006, People's Republic of China
- School of Environmental Science and Engineering, Shandong University, Qingdao 266237, People's Republic of China
| |
Collapse
|
8
|
Cho CW, Pham TPT, Zhao Y, Stolte S, Yun YS. Review of the toxic effects of ionic liquids. THE SCIENCE OF THE TOTAL ENVIRONMENT 2021; 786:147309. [PMID: 33975102 DOI: 10.1016/j.scitotenv.2021.147309] [Citation(s) in RCA: 85] [Impact Index Per Article: 28.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/26/2021] [Revised: 04/15/2021] [Accepted: 04/18/2021] [Indexed: 05/11/2023]
Abstract
Interest in ionic liquids (ILs), called green or designer solvents, has been increasing because of their excellent properties such as thermal stability and low vapor pressure; thus, they can replace harmful organic chemicals and help several industrial fields e.g., energy-storage materials production and biomaterial pretreatment. However, the claim that ILs are green solvents should be carefully considered from an environmental perspective. ILs, given their minimal vapor pressure, may not directly cause atmospheric pollution. However, they have the potential to cause adverse effects if leaked into the environment, for instance if they are spilled due to human mistakes or technical errors. To estimate the risks of ILs, numerous ILs have had their toxicity assessed toward several micro- and macro-organisms over the past few decades. Since the toxic effects of ILs depend on the method of estimating toxicity, it is necessary to briefly summarize and comprehensively discuss the biological effects of ILs according to their structure and toxicity testing levels. This can help simplify our understanding of the toxicity of ILs. Therefore, in this review, we discuss the key findings of toxicological information of ILs, collect some toxicity data of ILs to different species, and explain the influence of IL structure on their toxic properties. In the discussion, we estimated two different sensitivity values of toxicity testing levels depending on the experiment condition, which are theoretical magnitudes of the inherent sensitivity of toxicity testing levels in various conditions and their changes in biological response according to the change in IL structure. Finally, some perspectives, future research directions, and limitations to toxicological research of ILs, presented so far, are discussed.
Collapse
Affiliation(s)
- Chul-Woong Cho
- Department of Bioenergy Science and Technology, Chonnam National University, Gwangju, South Korea.
| | - Thi Phuong Thuy Pham
- Faculty of Biotechnology, HoChiMihn University of Food Industry, Ho Chi Minh City, Viet Nam
| | - Yufeng Zhao
- College of Resource and Environmental Science, South-Central University for Nationalities, Wuhan 430074, Hubei Province, China
| | - Stefan Stolte
- Technische Universität Dresden, Faculty of Environmental Sciences, Department of Hydrosciences, Institute of Water Chemistry, Bergstraße 66, 01062 Dresden, Germany
| | - Yeoung-Sang Yun
- School of Chemical Engineering, Chonbuk National University, 567 Beakje-dearo, Deokjin-gu, Jeonju, Jeonbuk 561-756, South Korea.
| |
Collapse
|
9
|
Khan MI, Mubashir M, Zaini D, Mahnashi MH, Alyami BA, Alqarni AO, Show PL. Cumulative impact assessment of hazardous ionic liquids towards aquatic species using risk assessment methods. JOURNAL OF HAZARDOUS MATERIALS 2021; 415:125364. [PMID: 33740721 DOI: 10.1016/j.jhazmat.2021.125364] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/31/2020] [Revised: 01/18/2021] [Accepted: 02/05/2021] [Indexed: 06/12/2023]
Abstract
In the present research work, a comprehensive tool for cumulative ecotoxicological impact assessment of ionic liquids (ILs) to aquatic life has been constructed. Using the probabilistic tool, impact of individual ILs to a group of aquatic species is assessed by chemical toxicity distributions (CTDs). The impact of group of ILs to individual aquatic species is assessed by species sensitivity distributions (SSDs). Acute toxicity data of imidazolium ILs with chloride (Cl-), bromide (Br-), tetrafluoroborate (BF4-), and hexafluorophosphate (PF6-) anions are used in CTD and SSD. Allowable concentrations for a group of Imidazolium ILs with the same mode of action (SMOA) to five aquatic species; Daphnia magna, Vibrio fischeri, Algae, Zebrafish, and Escherichia coli are estimated by CTDs. It has been concluded that 1-Butyl-3-methylimidazolium chloride (BMIMCl) possess the lowest risk at an acceptable risk value of 750 × 10-5 mmol/L which is 12% less than that of OMIMCl. Furthermore, the sensitivities towards the aquatic species reveal that from the studied ILs, BMIMBF4 with an acceptable risk value of 3200 × 10-5 mmol/L is the most suitable IL towards the selected aquatic species. Hence, current work provides cumulative allowable concentrations and acceptable risk values for ILs which release to aquatic compartment of ecosystem.
Collapse
Affiliation(s)
- Muhammad Ishaq Khan
- Centre of Advanced Process Safety (CAPS), Department of Chemical Engineering, Universiti Teknologi PETRONAS (UTP), 32610 Seri Iskandar, Perak, Malaysia
| | - Muhammad Mubashir
- Department of Petroleum Engineering, School of Engineering, Asia Pacific University of Technology and Innovation, 57000 Kuala Lumpur, Malaysia
| | - Dzulkarnain Zaini
- Centre of Advanced Process Safety (CAPS), Department of Chemical Engineering, Universiti Teknologi PETRONAS (UTP), 32610 Seri Iskandar, Perak, Malaysia
| | - Mater H Mahnashi
- Department of Pharmaceutical Chemistry, College of Pharmacy, Najran University, Najran, Saudi Arabia
| | - Bandar A Alyami
- Department of Pharmaceutical Chemistry, College of Pharmacy, Najran University, Najran, Saudi Arabia
| | - Ali O Alqarni
- Department of Pharmaceutical Chemistry, College of Pharmacy, Najran University, Najran, Saudi Arabia
| | - Pau Loke Show
- Department of Chemical and Environmental Engineering, University of Nottingham, Malaysia, 43500 Semenyih, Selangor Darul Ehsan, Malaysia.
| |
Collapse
|
10
|
Koutsoukos S, Philippi F, Malaret F, Welton T. A review on machine learning algorithms for the ionic liquid chemical space. Chem Sci 2021; 12:6820-6843. [PMID: 34123314 PMCID: PMC8153233 DOI: 10.1039/d1sc01000j] [Citation(s) in RCA: 46] [Impact Index Per Article: 15.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2021] [Accepted: 04/28/2021] [Indexed: 01/05/2023] Open
Abstract
There are thousands of papers published every year investigating the properties and possible applications of ionic liquids. Industrial use of these exceptional fluids requires adequate understanding of their physical properties, in order to create the ionic liquid that will optimally suit the application. Computational property prediction arose from the urgent need to minimise the time and cost that would be required to experimentally test different combinations of ions. This review discusses the use of machine learning algorithms as property prediction tools for ionic liquids (either as standalone methods or in conjunction with molecular dynamics simulations), presents common problems of training datasets and proposes ways that could lead to more accurate and efficient models.
Collapse
Affiliation(s)
- Spyridon Koutsoukos
- Department of Chemistry, Molecular Sciences Research Hub, Imperial College London White City Campus London W12 0BZ UK
| | - Frederik Philippi
- Department of Chemistry, Molecular Sciences Research Hub, Imperial College London White City Campus London W12 0BZ UK
| | - Francisco Malaret
- Department of Chemical Engineering, Imperial College London South Kensington Campus London SW7 2AZ UK
| | - Tom Welton
- Department of Chemistry, Molecular Sciences Research Hub, Imperial College London White City Campus London W12 0BZ UK
| |
Collapse
|
11
|
Shu C, Liu X, Xie W, Cai S, Li W, Wang M. Reductive desulfurization of aromatic sulfides with nickel boride in deep eutectic solvents. NEW J CHEM 2021. [DOI: 10.1039/d0nj05951j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Deep eutectic solvents were first used as the solvents in the reductive desulfurization process with nickel boride, and the desulfurization performance of nickel boride was greatly improved.
Collapse
Affiliation(s)
- Chenhua Shu
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| | - Xunzheng Liu
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| | - Wenjing Xie
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| | - Shuiping Cai
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| | - Wenting Li
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| | - Mengjiao Wang
- School of Chemistry and Environmental Science
- Shangrao Normal University
- Shangrao 334001
- P. R. China
| |
Collapse
|
12
|
Discovering Low Toxicity Ionic Liquids for Saccharomyces cerevisiae by Using the Agar Well Diffusion Test. Processes (Basel) 2020. [DOI: 10.3390/pr8091163] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023] Open
Abstract
Ionic liquids (ILs) are new solvents widely used in many technologies due to their unique and advantageous physicochemical properties. In biotechnological applications, ILs can be used along with microorganisms such as Saccharomyces cerevisiae. Due to the enormous number of ILs that can be synthesized through the combination of different anions and cations, it is necessary to have an easy and quick tool for the preliminary screening of their biocompatibility for being used in biotechnological applications. In this work, the agar well diffusion test was successfully applied as a rapid method to identify toxic/nontoxic ILs toward S. cerevisiae. Sixty-three ILs containing a diverse set of cations and anions were used. Through this methodology, nine fully biocompatible ILs toward S. cerevisiae were identified, including: [Bmim+] [NO3−], [HOPmim+] [NO3−], [Bmim+] [NTf2−], [N8,8,8,1+] [NTf2−], [S2,2,2+] [NTf2−], [EMPyr+] [NTf2−], [BMPi+] [NTf2−], [Moxa+] [MeSO4−] and [Chol+] [H2PO4−]. The analysis of the results also provides preliminary rules to enable the design of biocompatible ILs with S. cerevisiae. In this context, the toxicity was mainly determined by the cation nature although some anions can also display a strong influence on the IL biocompatibility as the bistriflimide anion. Besides, it was observed that an increase in the alkyl chain length of cations, such as imidazolium or pyridinium, involves an increase in the IL toxicity.
Collapse
|