Transformer-convolutional neural network for surface charge density profile prediction: Enabling high-throughput solvent screening with COSMO-SAC

Hydrocarbon Extraction with Ionic Liquids

Separation and reaction processes are key components employed in the modern chemical industry, and the former accounts for the majority of the energy consumption therein. In particular, hydrocarbon separation and purification processes, such as aromatics extraction, desulfurization, and denitrification, are challenging in petroleum refinement, an industrial cornerstone that provides raw materials for products used in human activities. The major technical shortcomings in solvent extraction are volatile solvent loss, product entrainment leading to secondary pollution, low separation efficiency, and high regeneration energy consumption due to the use of traditional organic solvents with high boiling points as extraction agents. Ionic liquids (ILs), a class of designable functional solvents or materials, have been widely used in chemical separation processes to replace conventional organic solvents after nearly 30 years of rapid development. Herein, we provide a systematic and comprehensive review of the state-of-the-art progress in ILs in the field of extractive hydrocarbon separation (i.e., aromatics extraction, desulfurization, and denitrification) including (i) molecular thermodynamic models of IL systems that enable rapid large-scale screening of IL candidates and phase equilibrium prediction of extraction processes; (ii) structure-property relationships between anionic and cationic structures of ILs and their separation performance (i.e., selectivity and distribution coefficients); (iii) IL-related extractive separation mechanisms (e.g., the magnitude, strength, and sites of intermolecular interactions depending on the separation system and IL structure); and (iv) process simulation and design of IL-related extraction at the industrial scale based on validated thermodynamic models. In short, this Review provides an easy-to-read exhaustive reference on IL-related extractive separation of hydrocarbon mixtures from the multiscale perspective of molecules, thermodynamics, and processes. It also extends to progress in IL analogs, deep eutectic solvents (DESs) in this research area, and discusses the current challenges faced by ILs in related separation fields as well as future directions and opportunities.

Computer-Aided Molecular Design of Ionic Liquids as Advanced Process Media: A Review from Fundamentals to Applications

The unique physicochemical properties, flexible structural tunability, and giant chemical space of ionic liquids (ILs) provide them a great opportunity to match different target properties to work as advanced process media. The crux of the matter is how to efficiently and reliably tailor suitable ILs toward a specific application. In this regard, the computer-aided molecular design (CAMD) approach has been widely adapted to cover this family of high-profile chemicals, that is, to perform computer-aided IL design (CAILD). This review discusses the past developments that have contributed to the state-of-the-art of CAILD and provides a perspective about how future works could pursue the acceleration of the practical application of ILs. In a broad context of CAILD, key aspects related to the forward structure-property modeling and reverse molecular design of ILs are overviewed. For the former forward task, diverse IL molecular representations, modeling algorithms, as well as representative models on physical properties, thermodynamic properties, among others of ILs are introduced. For the latter reverse task, representative works formulating different molecular design scenarios are summarized. Beyond the substantial progress made, some future perspectives to move CAILD a step forward are finally provided.

Boosting Graph Neural Networks with Molecular Mechanics: A Case Study of Sigma Profile Prediction

Sigma profiles are quantum-chemistry-derived molecular descriptors that encode the polarity of molecules. They have shown great performance when used as a feature in machine learning applications. To accelerate the development of these models and the construction of large sigma profile databases, this work proposes a graph convolutional network (GCN) architecture to predict sigma profiles from molecule structures. To do so, the usage of molecular mechanics (force field atom types) is explored as a computationally inexpensive node-level featurization technique to encode the local and global chemical environments of atoms in molecules. The GCN models developed in this work accurately predict the sigma profiles of assorted organic and inorganic compounds. The best GCN model here reported, obtained using Merck molecular force field (MMFF) atom types, displayed training and testing set coefficients of determination of 0.98 and 0.96, respectively, which are superior to previous methodologies reported in the literature. This performance boost is shown to be due to both the usage of a convolutional architecture and node-level features based on force field atom types. Finally, to demonstrate their practical applicability, we used GCN-predicted sigma profiles as the input to machine learning models previously developed in the literature that predict boiling temperatures and aqueous solubilities. Using the predicted sigma profiles as input, these models were able to compute both physicochemical properties using significantly less computational resources and displayed only a slight decrease in performance when compared with sigma profiles obtained from quantum chemistry methods.

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.

Table Tennis Track Detection Based on Temporal Feature Multiplexing Network

Recording the trajectory of table tennis balls in real-time enables the analysis of the opponent's attacking characteristics and weaknesses. The current analysis of the ball paths mainly relied on human viewing, which lacked certain theoretical data support. In order to solve the problem of the lack of objective data analysis in the research of table tennis competition, a target detection algorithm-based table tennis trajectory extraction network was proposed to record the trajectory of the table tennis movement in video. The network improved the feature reuse rate in order to achieve a lightweight network and enhance the detection accuracy. The core of the network was the "feature store & return" module, which could store the output of the current network layer and pass the features to the input of the network layer at the next moment to achieve efficient reuse of the features. In this module, the Transformer model was used to secondarily process the features, build the global association information, and enhance the feature richness of the feature map. According to the designed experiments, the detection accuracy of the network was 96.8% for table tennis and 89.1% for target localization. Moreover, the parameter size of the model was only 7.68 MB, and the detection frame rate could reach 634.19 FPS using the hardware for the tests. In summary, the network designed in this paper has the characteristics of both lightweight and high precision in table tennis detection, and the performance of the proposed model significantly outperforms that of the existing models.

A smile is all you need: predicting limiting activity coefficients from SMILES with natural language processing

The knowledge of mixtures' phase equilibria is crucial in nature and technical chemistry. Phase equilibria calculations of mixtures require activity coefficients. However, experimental data on activity coefficients are often limited due to the high cost of experiments. For an accurate and efficient prediction of activity coefficients, machine learning approaches have been recently developed. However, current machine learning approaches still extrapolate poorly for activity coefficients of unknown molecules. In this work, we introduce a SMILES-to-properties-transformer (SPT), a natural language processing network, to predict binary limiting activity coefficients from SMILES codes. To overcome the limitations of available experimental data, we initially train our network on a large dataset of synthetic data sampled from COSMO-RS (10 million data points) and then fine-tune the model on experimental data (20 870 data points). This training strategy enables the SPT to accurately predict limiting activity coefficients even for unknown molecules, cutting the mean prediction error in half compared to state-of-the-art models for activity coefficient predictions such as COSMO-RS and UNIFAC_Dortmund, and improving on recent machine learning approaches.

A Theoretical Model for the Charging Dynamics of Associating Ionic Liquids

Association between cations and anions plays an important role in the interfacial structure of room-temperature ionic liquids (ILs) and their electrochemical performance. Whereas great efforts have been devoted to investigating the association effect on the equilibrium properties of ILs, a molecular-level understanding of the charging dynamics is yet to be established. Here, we propose a theoretical procedure combining reaction kinetics and the modified Poisson-Nernst-Planck (MPNP) equations to study the influences of ionic association on the dynamics of electrical double layer (EDL) in response to an applied voltage. The ionic association introduces a new decay length λS and relaxation time scale τRC=λSL/D, where L is the system size and D is ion diffusivity, that are distinctively different those corresponding to non-associative systems. Analytical expressions have been obtained to reveal the quantitative relations between the dynamic timescales and the association strength.