Exploration of automatic learning to establish relationships between the molecular structure of chiral ionic liquids and the specific optical rotation

Chen, Mengyao; Xiao, Kaixia; Zhao, Tanfeng; Zhou, Yanmei; Zhang, Qingyou; Aires-de-Sousa, João

doi:10.1016/j.molliq.2018.01.086

Cited by 6 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20] The form of codification is important in the context of finding relevant features in an IL-based system, providing predictive and interpretation abilities. [9,21] The Molecular Maps of Atom-level Properties (MOLMAPs), previously developed and tested, permit such approach by mapping structural features of a system in a fixed-dimension's Kohonen network, according to its property's profile. This characteristic permit to compare, in a straightforward form, systems of different nature/number of components.…”

Section: Introductionmentioning

confidence: 99%

The Solubility of Gases in Ionic Liquids: A Chemoinformatic Predictive and Interpretable Approach

et al. 2021

View full text Add to dashboard Cite

This work comprises the study of solubilities of gases in ionic liquids (ILs) using a chemoinformatic approach. It is based on the codification, of the atomic inter-component interactions, cation/gas and anion/gas, which are used to obtain a pattern of activation in a Kohonen Neural Network (MOLMAP descriptors). A robust predictive model has been obtained with the Random Forest algorithm and used the maximum proximity as a confidence measure of a given chemical system compared to the training set. The encoding method has been validated with molecular dynamics. This encoding approach is a valuable estimator of attractive/repulsive interactions of a generical chemical system IL + gas. This method has been used as a fast/ visual form of identification of the reasons behind the differences observed between the solubility of CO 2 and O 2 in 1-butyl-3-methylimidazolium hexafluorophosphate (BMIM PF 6 ) at identical temperature and pressure (TP) conditions, The effect of variable cation and anion effect has been evaluated.

show abstract

Section: Introductionmentioning

confidence: 99%

The Solubility of Gases in Ionic Liquids: A Chemoinformatic Predictive and Interpretable Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[6][7][8][9][10][11][12] Such as the imidazole ionic liquids were analyzed with QSPR techniques and melting temperature were estimated with clustering methods; [13] the melting point of 126 structurally diverse pyridinium bromides was predicted by QSPR models with the CODESSA program; [14] the viscosity of ILs was predicted using group contribution method with artificial neural network; [15] and the signs of specific optical rotations of chiral ILs were qualitatively predicted to assign absolute configuration, as well as their values were quantitatively predicted by several of the authors. [16] The quantitative structural-activity relationship studies (QSAR) have been used to predict the toxicity of ILs. [17][18] Maciej Barycki et al used descriptors calculated by Dragon software to build a series of QSAR models for predicting the toxicity against human HeLa and MCF-7 cancer cell lines of ILs, and then developed a quantitative toxicity-toxicity relationship (QTTR) model.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Ionic Liquids Toxicity against Leukemia Rat Cell Line IPC‐81 based on the Empirical‐like Models using Intuitive and Explainable Fingerprint Descriptors

Chen

et al. 2020

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

Ionic liquids as green solvents have been paid extensive attention in recent years. However, mostly it is cost and time-consuming to measure their properties. Thus, theorical methods, especially ultrafast chemoinformatics methods were introduced into these studies. Instead of abstract and complex models in some QSPR studies, in this study, the 2D structural features related to the toxicity of ionic liquids were discussed at first, and then the corresponding intuitive and meaningful descriptors were suggested to construct quantitative chemoinformatics models, finally a multiple linear regression (MLR) based on the empirical-like models were applied to the estimation of toxicities of 304 ionic liquids. For the test sets, the relationship coefficients reached up to R = 0.90. An external test set of 11 ionic liquids collected from other literatures was submitted to the achieved MLR equations, and the satisfactory result (R = 0.94) was obtained.

show abstract

“…Our research groups have contributed to the development of conformation-independent and conformation-dependent chirality codes, physicochemical atomic stereo descriptors (PAS), and simplified derivatives. − These have been applied to chiral structure–property relationships concerning the assignment of absolute configurations from NMR data, the prediction of enantiospecific or enantioselective reactions, the virtual screening of chiral catalysts for asymmetric reactions, the prediction of the elution order in chiral separations, and the estimation of specific optical rotation in small data sets. , …”

Section: Introductionmentioning

confidence: 99%

“…Successful ML models can be applied to curate the databases of published experimental values or to trigger alert for suspicious experimental values before their disclosure. QSPR has been applied to predict optical rotations using small data sets of congeneric series. ,, …”

Section: Introductionmentioning

confidence: 99%

Machine Learning Classification of One-Chiral-Center Organic Molecules According to Optical Rotation

Mamede

de-Almeida

Chen

et al. 2020

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

In this study, machine learning algorithms were investigated for the classification of organic molecules with one carbon chiral center according to the sign of optical rotation. Diverse heterogeneous data sets comprising up to 13,080 compounds and their corresponding optical rotation were retrieved from Reaxys and processed independently for three solvents: dichloromethane, chloroform, and methanol. The molecular structures were represented by chiral descriptors based on the physicochemical and topological properties of ligands attached to the chiral center. The sign of optical rotation was predicted by random forests (RF) and artificial neural networks for independent test sets with an accuracy of up to 75% for dichloromethane, 82% for chloroform, and 82% for methanol. RF probabilities and the availability of structures in the training set with the same spheres of atom types around the chiral center defined applicability domains in which the accuracy is higher.

show abstract

Exploration of automatic learning to establish relationships between the molecular structure of chiral ionic liquids and the specific optical rotation

Cited by 6 publications

References 20 publications

The Solubility of Gases in Ionic Liquids: A Chemoinformatic Predictive and Interpretable Approach

The Solubility of Gases in Ionic Liquids: A Chemoinformatic Predictive and Interpretable Approach

Estimation of Ionic Liquids Toxicity against Leukemia Rat Cell Line IPC‐81 based on the Empirical‐like Models using Intuitive and Explainable Fingerprint Descriptors

Machine Learning Classification of One-Chiral-Center Organic Molecules According to Optical Rotation

Contact Info

Product

Resources

About