Comparisons of Molecular Structure Generation Methods Based on Fragment Assemblies and Genetic Graphs

Prediction of critical micelle concentration for per- and polyfluoroalkyl substances

In this study, we focus on the development of Quantitative Structure-Property Relationship (QSPR) models to predict the critical micelle concentration (CMC) for per- and polyfluoroalkyl substances (PFASs). Experimental CMC values for both fluorinated and non-fluorinated compounds were meticulously compiled from existing literature sources. Our approach involved constructing two distinct types of models based on Support Vector Machine (SVM) algorithms applied to the dataset. Type (I) models were trained exclusively on CMC values for fluorinated compounds, while Type (II) models were developed utilizing the entire dataset, incorporating both fluorinated and non-fluorinated compounds. Comparative analyses were conducted against reference data, as well as between the two model types. Encouragingly, both types of models exhibited robust predictive capabilities and demonstrated high reliability. Subsequently, the model having the broadest applicability domain was selected to complement the existing experimental data, thereby enhancing our understanding of PFAS behaviour.

Modelling enzyme inhibition toxicity of ionic liquid from molecular structure via convolutional neural network model

Deep learning (DL) methods further promote the development of quantitative structure-activity/property relationship (QSAR/QSPR) models by dealing with complex relationships between data. An acetylcholinesterase inhibitory toxicity model of ionic liquids (ILs) was established using a convolution neural network (CNN) combined with support vector machine (SVM), random forest (RF) and multilayer perceptron (MLP). A CNN model was proposed for feature self-learning and extraction of ILs. By comparing with the model results through feature engineering (FE), the model regression results based on the CNN model for feature extraction have been substantially improved. The results showed that all six models (FE-SVM, FE-RF, FE-MLP, CNN-SVM, CNN-RF, and CNN-MLP) had good prediction accuracy, but the results based on the CNN model were better. The hyperparameters of six models were optimized by grid search and the 10-fold cross validation. Compared with the existing models in the literature, the model performance has been further improved. The model could be used as an intelligent tool to guide the design or screening of low-toxicity ILs.

Machine learning-based models for accessing thermal conductivity of liquids at different temperature conditions

Combating global warming-related climate change demands prompt actions to reduce greenhouse gas emissions, particularly carbon dioxide. Biomass-based biofuels represent a promising alternative fossil energy source. To convert biomass into energy, numerous conversion processes are performed at high pressure and temperature conditions, and the design and dimensioning of such processes requires thermophysical property data, particularly thermal conductivity, which are not always available in the literature. In this paper, we proposed the application of Chemoinformatics methodologies to investigate the prediction of thermal conductivity for hydrocarbons and oxygenated compounds. A compilation of experimental data followed by a careful data curation were performed to establish a database. The support vector machine algorithm has been applied to the database leading to models with good predictive abilities. The support vector regression (SVR) model has then been applied to an external set of compounds, i.e. not considered during the training of models. It showed that our SVR model can be used for the prediction of thermal conductivity values for temperatures and/or compounds that are not covered experimentally in the literature.