Beware of proper validation of models for ionic Liquids!

Makarov, Dmitriy M.; Fadeeva, Yu. A.; Shmukler, L. E.; Tetko, Igor V.

doi:10.1016/j.molliq.2021.117722

Cited by 30 publications

(25 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…Previously, these methods showed a good quality of predicting the spectral properties (absorption maximum wavelengths and molar absorption coefficient) of dipyrromethene compounds including BODIPYs [47][48][49][50] and thermal properties of ionic liquids. 51,52 RFR is the most flexible and easy-to-use algorithm based on classification and regression trees (CART). 42 RFR is an ensemble learning method where decision trees are built independently on a random subset of compounds and subsequently averaged.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning

Ksenofontov

Isaev

Lukanov

et al. 2023

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Machine Learning Methodsmentioning

confidence: 99%

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning

Ksenofontov

Isaev

Lukanov

et al. 2023

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

“…Second, pressure can affect the u of ILs, which is ignored by some QSPR models. , In fact, the effects of pressure, temperature, and the interaction of anions and cations on the u should be considered in the modeling process. Most importantly, in the external validation, the traditional way of dividing the training and test sets considers only the kind of ILs and ignores the division of anions and cations, thus leading to “pseudo-high” accuracy of the validation results . The same phenomenon exists in the internal validation, as the uniqueness of the ion species in the test set is not guaranteed.…”

Section: Introductionmentioning

confidence: 99%

QSPR Model to Predict the Speed of Sound of Ionic Liquids as a Function of Variable Temperature and Pressure

Liu

Wang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In this work, a u(T,P,I)-QSPR model utilizing the norm index (I) is developed to predict the speed of sound (u) of ionic liquids (ILs) over a wide range of pressures (P) and temperatures (T). During the modeling process, preprocessing is first performed against the collected data by using the equipartition rules for temperature and pressure. Temperature and pressure effects are introduced on the basis of cation, anion, and IL descriptors. The external and internal validations are used to evaluate the predictability and robustness of the u(T,P,I)-QSPR model. The statistical results show that the u(T,P,I)-QSPR model can accurately predict the u of ILs at variable temperature and pressure with R 2 test = 0.9952, Q 2 LOCO = 0.9917, and Q 2 LOAO = 0.9903. This facilitates the acquisition of property data (e.g., density and heat capacity) associated with u and the design of functional ILs.

show abstract

“…To explore the decomposition of lignin, model compounds such as guaiacylglycerol-β-guaiacyl ether (GG), , veratrylglycerol-β-guaiacyl ether (VG), and p -coumaric acid ester (pCA) − are usually used to simplify experiments and theoretical calculations. Ionic liquids (ILs) − act as a kind of green media, consisting of organic cations and inorganic/organic anions. Taking advantage of structural diversity and strong solubility, ILs have been widely used for lignin dissolution and degradation. − Guaiacol is the main product of the β–O–4 bond cleavage, and its yield is often used to quantify the cleavage performance of ILs.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Screening of Efficient Ionic Liquids for Targeted Cleavage of the β–O–4 Bond of Lignin

et al. 2022

View full text Add to dashboard Cite

Lignin conversion into high value-added chemicals is of great significance for maximizing the use of renewable energy. Ionic liquids (ILs) have been widely used for targeted cleavage of the C–O bonds of lignin due to their high catalytic activity. Studying the cleavage activity of each IL is impossible and time-consuming, given the huge number of cations and anions. Currently, the mainstream approach to determining the cleavage activity of one IL is to calculate the activation barrier energy (E a) theoretically via transition state search, a process that involves the iterative determination of an appropriate “imaginary frequency”. Machine learning (ML) has been widely used for catalyst design and screening, enabling accurate mapping from specified descriptors to target properties. To avoid complicated E a calculations and to screen potential candidates, in this study, we selected nearly 103 ILs and guaiacylglycerol-β-guaiacyl ether (GG) as the lignin model and used the ML technology to train models that can rapidly predict the cleavage activity of ILs. Taking the easily accessible bond dissociation energy (BDE) of the β–O–4 bond in GG as the target, an ML model with r > 0.93 for predicting the catalytic activity of ILs was obtained. The change tendency of the BDE is consistent with the experimental yield of guaiacol, reflecting the reliability of the ML model. Finally, [C2MIM][Tyrosine] and [C3MIM][Tyrosine] as the optimal candidates for future applications were screened out. This is a novel strategy for predicting the catalytic activity of ILs on lignin without the need to calculate complicated reaction pathways while reducing time consumption. It is anticipated that the ML model can be utilized in future practical applications for targeted cleavage of lignin.

show abstract

Beware of proper validation of models for ionic Liquids!

Cited by 30 publications

References 53 publications

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning

QSPR Model to Predict the Speed of Sound of Ionic Liquids as a Function of Variable Temperature and Pressure

Machine Learning Screening of Efficient Ionic Liquids for Targeted Cleavage of the β–O–4 Bond of Lignin

Contact Info

Product

Resources

About

Beware of proper validation of models for ionic Liquids!

Cited by 30 publications

References 53 publications

Accurate prediction of 11B NMR chemical shift of BODIPYs via machine learning

Accurate prediction of 11B NMR chemical shift of BODIPYs via machine learning

QSPR Model to Predict the Speed of Sound of Ionic Liquids as a Function of Variable Temperature and Pressure

Machine Learning Screening of Efficient Ionic Liquids for Targeted Cleavage of the β–O–4 Bond of Lignin

Contact Info

Product

Resources

About

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning

Accurate prediction of ¹¹B NMR chemical shift of BODIPYs via machine learning