Predicting the ecotoxicity of ionic liquids towards Vibrio fischeri using genetic function approximation and least squares support vector machine

Ma, Shuying; Lv, Min; Deng, Fangfang; Zhang, Xiaoyun; Zhai, Hong Lin; Lv, Wenjuan

doi:10.1016/j.jhazmat.2014.10.011

Cited by 65 publications

(29 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…16,17,20,[22][23][24][25][26][27][28][29][30][31][32][33][34][35][36] Table S1 of the ESI. † While the other descriptors were obtained without the need of any geometry optimization process, the QTMS parameters were derived from the ab initio based optimized geometry at the HF/6-31G(d) level of theory, and were limited to only cations.…”

Section: The Dataset and Descriptorsmentioning

confidence: 99%

“…15 There have been a few reports in the literature on modelling the toxicity of ILs towards V. fischeri. [16][17][18][19][20][21][22] In the present work, we have developed QSAR models for V. fischeri toxicity using the largest available set of ionic liquids with the experimental toxicity data using Microtox®. We have also applied these models for prediction of toxicity of a recently available set of ionic liquids for a true external validation of the developed models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of predictive QSAR models for Vibrio fischeri toxicity of ionic liquids and their true external and experimental validation tests

et al. 2016

View full text Add to dashboard Cite

Despite possessing an interesting chemical nature and tuneable physicochemical properties, ionic liquids (ILs) must have their ecotoxicity tested in order to be commercialized. The water solubility of ILs allows their easy access to the aquatic compartment of the ecosystem creating a potential hazard to aquatic organisms. Hence, it is relevant to design ionic liquids with lower toxicity while keeping the desired properties of interest. Considering the possibility of an enormous number of combinations of different cations and anions, a rational guidance for the structural design of ionic liquids is essential in order to prioritize the synthesis as well as testing of selected molecules only. Predictive in silico models, such as quantitative structure-activity relationship (QSAR) models, can play a pivotal role in exploring the important chemical attributes contributing to the response activity. These models may then lead to the design of novel ionic liquids. The present study aims at developing predictive QSAR models for the ecotoxicity of ionic liquids using the bacteria Vibrio fischeri as an indicator response species. Instead of a single model, here we have used multiple models to capture more complete structural information of ionic liquids for toxicity towards Vibrio fischeri. The derived chemical attributes have been implemented in designing new analogues, some of which have been synthesized and had their ecotoxicity tested for the same model organism. The predictive QSAR models reported here can be used for ecotoxicity prediction of new IL chemicals and for data-gap filling. Moreover, the synthesized low-toxic ILs could be considered for evaluation as well as for application in suitable processes serving the purpose of industry and academia.

show abstract

Section: The Dataset and Descriptorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of predictive QSAR models for Vibrio fischeri toxicity of ionic liquids and their true external and experimental validation tests

et al. 2016

View full text Add to dashboard Cite

show abstract

“…adrenoceptors [469], Human protein tyrosine phosphatase 1B inhibitors [470], potent human protein tyrosine phosphatase inhibitors [471], some thiourea derivatives as influenza virus neuraminidase inhibitors [472] and also predicting the ecotoxicity of ionic liquids [473]. The potential of GFA makes this algorithm as an interesting option of utilization in a lot of QSAR/QSPR reports during these years [74,469,.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…They compared their utilized approach with multilayer perceptron neural network to discriminate active and nonactive molecules and it was shown that SVM was the more efficient in this case [509]. [473,510,511,. In addition, application of SVM in QSAR/QSPR and drug design has been reviewed in some review articles [533,550] …”

mentioning

confidence: 99%

Chemometrics tools in QSAR/QSPR studies: A historical perspective

Yousefinejad

Hemmateenejad

2015

Chemometrics and Intelligent Laboratory Systems

122

View full text Add to dashboard Cite

“…In addition, the models were not able to fully account for the intrinsically non-linear and complex nature of experimental datasets. This presented large errors in the model predictions [17,18]. This created huge gabs in fire parameter predictions that needed to be solved.…”

Section: Introductionmentioning

confidence: 99%

Novel Approaches to Modelling Flammability Characteristics of Polymethyl Methacrylate (PMMA) via Multivariate Adaptive Regression Splines and Random Forest Methods

Alhassan

Jiang

Mensah

et al. 2020

AJRCoS

View full text Add to dashboard Cite

Soft-computing techniques for fire safety parameter predictions in flammability studies are essential for describing a material fire behaviour. This study proposed, two novel Artificial Intelligence developed models, Multivariate Adaptive Regression Splines (MARS) and Random Forest (RF) methods, to model and predict peak heat release rate (pHRR) of Polymethyl methacrylate (PMMA) from Microscale Combustion Calorimetry (MCC) experiment. From the statistical analysis, MARS presented the highest coefficient of determination (R 2 ) values of (0.9998) and (0.9996) for training and testing respectively, with low MAD, MAPE and RMSE values. Comparatively, MARS Alhassan et al.; AJRCOS, 4(4): 1-14, 2019; Article no.AJRCOS.53584 2 outperformed RF in the predictions of pHRR, through its model algorithms that generated optimized equations for pHRR predictions, covering all non-linearity points of the experimental data. Amongst the input variables (sample mass, THR, HRC, pTemp and pTime), heating rate (β), highly influenced pHRR outcome predictions from MARS and RF models. However, to validate the performance and applicability of the proposed models. Results of MARS and RF were benchmarked with that from Artificial Neural Network (ANN) methods. The MARS and RF models observed the least error deviation when compared with pHRR results for PMMA from the ANN models. This study therefore, recommends the adoption of MARS and RF in the predictions of flammability characteristics of polymeric materials. Original Research Article

show abstract

Predicting the ecotoxicity of ionic liquids towards Vibrio fischeri using genetic function approximation and least squares support vector machine

Cited by 65 publications

References 51 publications

Development of predictive QSAR models for Vibrio fischeri toxicity of ionic liquids and their true external and experimental validation tests

Development of predictive QSAR models for Vibrio fischeri toxicity of ionic liquids and their true external and experimental validation tests

Chemometrics tools in QSAR/QSPR studies: A historical perspective

Novel Approaches to Modelling Flammability Characteristics of Polymethyl Methacrylate (PMMA) via Multivariate Adaptive Regression Splines and Random Forest Methods

Contact Info

Product

Resources

About