REPOSITORY ABOUT GUIDELINES CITING BLOG

Toots, K. M.; Sild, S.; Leis, J.; Acree Jr., W. E.; Maran, U. Machine learning Quantitative Structure-Property Relationships as a function of ionic liquid cations for the gas-ionic liquid partition coefficient of hydrocarbons. IJMS 2022.

QsarDB Repository

Toots, K. M.; Sild, S.; Leis, J.; Acree Jr., W. E.; Maran, U. Machine learning Quantitative Structure-Property Relationships as a function of ionic liquid cations for the gas-ionic liquid partition coefficient of hydrocarbons. IJMS 2022.

QDB archive DOI: 10.15152/QDB.256   DOWNLOAD

QsarDB content

Property logKh: Gas-ionic liquid partition coefficient of hexane in [Tf2N]- ionic liquids

SVRh: Support Vector Regression model for logK of hexane in [Tf2N]- ionic liquids

Support vector machine (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 57 0.970 0.071
MLRh-Eq23: Multiple Linear Regression model for logK of hexane in [Tf2N]- ionic liquids

Regression model (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 57 0.943 0.094

Property logKc: Gas-ionic liquid partition coefficient of cyclohexane in [Tf2N]- ionic liquids

MLRc-Eq24: Multiple Linear Regression model for logK of cyclohexane in [Tf2N]- ionic liquids

Regression model (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 60 0.914 0.103
SVRc: Support Vector Regression model for logK of cyclohexane in [Tf2N]- ionic liquids

Support vector machine (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 60 0.946 0.082

Property logKb: Gas-ionic liquid partition coefficient of benzene in [Tf2N]- ionic liquids

MLRb-Eq25: Multiple Linear Regression model for logK of benzene in [Tf2N]- ionic liquids

Regression model (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 60 0.790 0.069
SVRb: Support Vector Regression model for logK of benzene in [Tf2N]- ionic liquids

Support vector machine (regression)

Open in:QDB Explorer QDB Predictor

Name Type n

R2

σ

Training set training 60 0.973 0.025

Citing

When using this QDB archive, please cite (see details) it together with the original article:

  • Toots, K. M.; Sild, S.; Leis, J.; Acree Jr., W. E.; Maran, U. Data for: Machine learning Quantitative Structure-Property Relationships as a function of ionic liquid cations for the gas-ionic liquid partition coefficient of hydrocarbons. QsarDB repository, QDB.256. 2022. http://dx.doi.org/10.15152/QDB.256

  • Toots, K. M.; Sild, S.; Leis, J.; Acree Jr., W. E.; Maran, U. Machine learning Quantitative Structure-Property Relationships as a function of ionic liquid cations for the gas-ionic liquid partition coefficient of hydrocarbons. IJMS 2022.

Metadata

Show full item record

Title: Toots, K. M.; Sild, S.; Leis, J.; Acree Jr., W. E.; Maran, U. Machine learning Quantitative Structure-Property Relationships as a function of ionic liquid cations for the gas-ionic liquid partition coefficient of hydrocarbons. IJMS 2022.
Abstract: Ionic liquids (ILs) are known for their unique characteristics as solvents and electrolytes. Therefore new ILs are being developed and adapted as innovative chemical environments for different applications where their properties need to be understood on a molecular level. Computational data driven methods provide means for understanding of properties at molecular level and quantitative structure-property relationships (QSPRs) gives framework for this. This framework is commonly used to study the properties of molecules in ILs as an environment. The opposite situation where the property is considered as a function of the ionic liquid does not exist. The aim of the present study was to supplement this perspective with new knowledge and to develop QSPRs that would allow the understanding of molecular interactions in ionic liquids based on the structure of the cationic moiety. A wide range of applications in electrochemistry, separation and extraction chemistry depend on the partitioning of solutes between the ionic liquid and the surrounding environment that is characterized by the gas-ionic liquid partition coefficient. To model this property as a function of the structure of cationic counterpart the series of ionic liquids were selected with a common bis-(trifluoromethylsulfonyl)-imide anion, [Tf2N]-, for benzene, hexane and cyclohexane. MLR, SVR and GPR machine learning approaches were used to derive data driven models and their performance was compared. The cross-validation coefficients of determination in the range 0.71–0.93 along with other performance statistics indicated strong accuracy of models for all data series and machine learning methods. The analysis and interpretation of descriptors revealed that generally higher lipophilicity and dispersion interaction capability, and lower polarity in the cations induces a higher partition coefficient for benzene, hexane, cyclohexane and hydrocarbons in general. Applicability domain analysis of models concluded no highly influential outliers and the models are applicable to a wide selection of cation families with variable size, polarity, and aliphatic or aromatic nature.
URI: http://hdl.handle.net/10967/256
http://dx.doi.org/10.15152/QDB.256
Date: 2022-06-22


Files in this item

Name Description Format Size View
article2_qsardb.zip Article_2 application/zip 59.33Kb View/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show full item record