Quantitative structure—property relationship for thermal decomposition temperature of ionic liquids

A QSPR model for estimating Henry's law constant of H2S in ionic liquids by ELM algorithm

Ionic liquids (ILs) as green solvents have been studied in the application of gas sweetening. However, it is a huge challenge to obtain all the experimental values because of the high costs and generated chemical wastes. This study pioneered a quantitative structure-property relationship (QSPR) model for estimating Henry's law constant (HLC) of H₂S in ILs. A dataset consisting of the HLC data of H₂S for 22 ILs within a wide range of temperature (298.15-363.15 K) were collected from published reports. The electrostatic potential surface area (S_EP) and molecular volume of these ILs were calculated and used as input descriptors together with temperature. The extreme learning machine (ELM) algorithm was employed for nonlinear modelling. Results showed that the determination coefficient (R²) of the training set, test set and total set were 0.9996, 0.9989,0.9994, respectively, while the average absolute relative deviation (AARD%) of them were 1.3383, 2,4820 and 1.5820, respectively. The statistical parameters for the measurement of the model exhibited the great reliability, stability, and predictive power of the ELM model. The Applicability Domain (AD) of the ELM model is also investigated. It proves that the majority of ILs in the training and test sets are located in the model's AD and verifies the reliability of the model. The proposed model is potentially applicable to guide the application of ILs for gas sweetening.

Machine Learning for Ionic Liquid Toxicity Prediction

In addition to proper physicochemical properties, low toxicity is also desirable when seeking suitable ionic liquids (ILs) for specific applications. In this context, machine learning (ML) models were developed to predict the IL toxicity in leukemia rat cell line (IPC-81) based on an extended experimental dataset. Following a systematic procedure including framework construction, hyper-parameter optimization, model training, and evaluation, the feedforward neural network (FNN) and support vector machine (SVM) algorithms were adopted to predict the toxicity of ILs directly from their molecular structures. Based on the ML structures optimized by the five-fold cross validation, two ML models were established and evaluated using IL structural descriptors as inputs. It was observed that both models exhibited high predictive accuracy, with the SVM model observed to be slightly better than the FNN model. For the SVM model, the determination coefficients were 0.9289 and 0.9202 for the training and test sets, respectively. The satisfactory predictive performance and generalization ability make our models useful for the computer-aided molecular design (CAMD) of environmentally friendly ILs.

MoDoop: An Automated Computational Approach for COSMO-RS Prediction of Biopolymer Solubilities in Ionic Liquids

An automated computational framework (MoDoop) was developed to predict the biopolymer solubilities in ionic liquids (ILs) on the basis of conductor-like screening model for real solvents calculations of two thermodynamic properties: logarithmic activity coefficient (ln γ) at infinite dilution and excess enthalpy (H ^E) of mixture. The calculation was based on the optimized two-dimensional structures of biopolymer models and ILs by searching the lowest-energy conformer and optimizing molecular geometry. Three lignin models together with one IL dataset were used to evaluate the prediction ability of the developed method. The evaluation results show that ln γ is a more reliable property to predict lignin solubilities in ILs and the p-coumaryl alcohol model is considered as the best model to represent lignin molecules. The developed MoDoop approach is efficient for rapid in silico screening of suitable ionic liquids to dissolve biopolymers.

Development of Simple QSPR Models for the Prediction of the Heat of Decomposition of Organic Peroxides

Quantitative structure-property relationships represent alternative method to experiments to access the estimation of physico-chemical properties of chemicals for screening purpose at R&D level but also to gather missing data in regulatory context. In particular, such predictions were encouraged by the REACH regulation for the collection of data, provided that they are developed respecting the rigorous principles of validation proposed by OECD. In this context, a series of organic peroxides, unstable chemicals which can easily decompose and may lead to explosion, were investigated to develop simple QSPR models that can be used in a regulatory framework. Only constitutional and topological descriptors were employed to achieve QSPR models predicting the heat of decomposition, which could be used without any time consuming preliminary structure calculations at quantum chemical level. To validate the models, the original experimental dataset was divided into a training and a validation set according to two methods of partitioning, one based on the property value and the other based on the structure of the molecules by the mean of PCA. Four QSPR models were developed upon the type of descriptors and the methods of partitioning. The 2 models issuing from the PCA based method were highlighted as they presented good predictive power and they are easier to apply than our previous quantum chemical based model, since they do not need any preliminary calculations.

Alkyl substituent effect on density, viscosity and chemical behavior of 1-alkyl-3-methylimidazolium chloride

Molecular structure of the conformers of 1-C n -3-methylimidazolium chloride (n = 1 to 4) ionic liquids has been explored and the relationships with density and viscosity have been studied using COSMO related methodologies. Effects of the number of conformers, ionic character, anion-cation relative positions and the alkyl chain length of the cation on predictions of properties have been analyzed. The quality of the predictions has been tested by comparing with experimental results. Moreover, COSMO polarization charge densities, σ-profiles and σ-potentials of the conformers have been analyzed. Predictions on the chemical behavior based on the values of these properties in the conformers have been used to elucidate the affinity for electrophilic and nucleophilic reagents of ionic liquids.

Prediction of the thermal decomposition of organic peroxides by validated QSPR models

Organic peroxides are unstable chemicals which can easily decompose and may lead to explosion. Such a process can be characterized by physico-chemical parameters such as heat and temperature of decomposition, whose determination is crucial to manage related hazards. These thermal stability properties are also required within many regulatory frameworks related to chemicals in order to assess their hazardous properties. In this work, new quantitative structure-property relationships (QSPR) models were developed to predict accurately the thermal stability of organic peroxides from their molecular structure respecting the OECD guidelines for regulatory acceptability of QSPRs. Based on the acquisition of 38 reference experimental data using DSC (differential scanning calorimetry) apparatus in homogenous experimental conditions, multi-linear models were derived for the prediction of the decomposition heat and the onset temperature using different types of molecular descriptors. Models were tested by internal and external validation tests and their applicability domains were defined and analyzed. Being rigorously validated, they presented the best performances in terms of fitting, robustness and predictive power and the descriptors used in these models were linked to the peroxide bond whose breaking represents the main decomposition mechanism of organic peroxides.