Exploring simple, transparent, interpretable and predictive QSAR models for classification and quantitative prediction of rat toxicity of ionic liquids using OECD recommended guidelines

Das, Rudra Narayan; Roy, Kunal; Popelier, Paul L. A.

doi:10.1016/j.chemosphere.2015.06.022

Cited by 26 publications

(5 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In QSAR studies, Das et al [ 173 ] used a data set of 289 ILs experimental data, a genetic function approximation algorithm and partial least-squares regression to develop a QSAR model to predict the toxic effect of ILs on rat leukemia cell line (IPC-81). The model developed had an R 2 = 0.869.…”

Section: Effect Of Ionic Liquids On Animalsmentioning

confidence: 99%

Ionic Liquids—A Review of Their Toxicity to Living Organisms

Gonçalves

Paredes

Cristino

et al. 2021

IJMS

119

View full text Add to dashboard Cite

Ionic liquids (ILs) were initially hailed as a green alternative to traditional solvents because of their almost non-existent vapor pressure as ecological replacement of most common volatile solvents in industrial processes for their damaging effects on the environment. It is common knowledge that they are not as green as desired, and more thought must be put into the biological consequences of their industrial use. Still, compared to the amount of research studying their physicochemical properties and potential applications in different areas, there is a scarcity of scientific papers regarding how these substances interact with different organisms. The intent of this review was to compile the information published in this area since 2015 to allow the reader to better understand how, for example, bacteria, plants, fish, etc., react to the presence of this family of liquids. In general, lipophilicity is one of the main drivers of toxicity and thus the type of cation. The anion tends to play a minor (but not negligible) role, but more research is needed since, owing to the very nature of ILs, except for the most common ones (imidazolium and ammonium-based), many of them are subject to only one or two articles.

show abstract

Section: Effect Of Ionic Liquids On Animalsmentioning

confidence: 99%

Ionic Liquids—A Review of Their Toxicity to Living Organisms

Gonçalves

Paredes

Cristino

et al. 2021

IJMS

119

View full text Add to dashboard Cite

show abstract

“…In the work (Das et al, 2015b), classification and regression-based models were developed with two-dimensional topological descriptors for a dataset of 289 ILs. Linear discriminant analysis (LDA) and PLS (partial least squares regression) models of cytotoxicity (EC 50 ) values towards rat cell line IPC-81 were designed.…”

Section: Other Theoretical Molecular Descriptorsmentioning

confidence: 99%

A review of recent advances towards the development of QSAR models for toxicity assessment of ionic liquids

Abramenko

Кustov

Metelytsia

et al. 2020

Journal of Hazardous Materials

View full text Add to dashboard Cite

show abstract

“…Thus, there are considerably limited data on the toxicities of ILs tested on various organisms. In addition, the limitless opportunities and possibilities in constructing and modifying the IL structures potentially bring massive challenges in conducting a comprehensive evaluation of the risks of these ILs 6 . Therefore, there is a need to deliver a rapid and cost‐effective approach to predicting the toxicity of ILs, and one way to solve these issues is through the adoption of machine learning in predicting the ILs toxicity.…”

Section: Introductionmentioning

confidence: 99%

Prediction of ionic liquids toxicity using machine learning models for application to gas hydrate

Abdullah,

Zaini,

Lal

2024

Process Safety Progress

View full text Add to dashboard Cite

Ionic liquids (ILs) are highly favored in the oil and gas industry as gas hydrate inhibitors due to their dual functionality as thermodynamic inhibitor and kinetic hydrate inhibitor. Though known as the “green alternatives,” concerns about the effects of ILs in the environment are rising such that ILs can stabilize in water systems. Furthermore, there are insufficient data on the toxicity of ILs, limiting the use of ILs for industrial applications. Ridge, LASSO, decision tree, random forest, extra tree, gradient boost, and support vector regressions were used to develop IL toxicity predictive models. Random forest yielded the strongest predictive performance, scoring the highest R2 value of 0.86, with mean absolute error and root mean square error values of 0.32 and 0.43, respectively. Feature selections were conducted to investigate the contributions of the five molecular descriptors involved in developing regression models in this work. Descriptor MSDC was found to contribute the highest at 67% in predicting the toxicity of ILs, followed by SNarA and MAXDPC, demonstrating contributions of 15.2% and 14.1%, respectively. Further quantitative structure–activity relationship model validations were executed; the use of three descriptors resulted in a 2% increase in predictive performance for decision tree regression, whereas R2 values remained the same for random forest, extra tree, and gradient boosting.

show abstract

Exploring simple, transparent, interpretable and predictive QSAR models for classification and quantitative prediction of rat toxicity of ionic liquids using OECD recommended guidelines

Cited by 26 publications

References 59 publications

Ionic Liquids—A Review of Their Toxicity to Living Organisms

Ionic Liquids—A Review of Their Toxicity to Living Organisms

A review of recent advances towards the development of QSAR models for toxicity assessment of ionic liquids

Prediction of ionic liquids toxicity using machine learning models for application to gas hydrate

Contact Info

Product

Resources

About