Machine Learning for Ionic Liquid Toxicity Prediction

Wang, Zihao; Song, Zhen; Zhou, Teng

doi:10.3390/pr9010065

Cited by 35 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where m stands for the molality solubility (mol/kg) of gases (CO2 (logEC50=3.10) [30]. In view of all these facts, [Bmim][DCA] is selected here as the absorbent for the biogas upgrading process.…”

Section: Ionic Liquids Screeningmentioning

confidence: 99%

Thermal-plasma-assisted renewable hydrogen and solid carbon production from ionic liquid-based biogas upgrading: A process intensification study

Song

Long

Qin

et al. 2022

Chemical Engineering and Processing - Process Intensification

Self Cite

View full text Add to dashboard Cite

Section: Ionic Liquids Screeningmentioning

confidence: 99%

Thermal-plasma-assisted renewable hydrogen and solid carbon production from ionic liquid-based biogas upgrading: A process intensification study

Song

Long

Qin

et al. 2022

Chemical Engineering and Processing - Process Intensification

Self Cite

View full text Add to dashboard Cite

“…To prove the performance of the proposed IL SMILES Transformer-CNN model for predicting IL properties, state-of-the-art models in recent literature [24][25][26][28][29][30]58 are chosen for comparison. For the sake of a fair comparison, this work trains all the IL SMILES Transformer-CNN models on the same IL property databases as in the corresponding references.…”

Section: Performance On Il Properties Modelingmentioning

confidence: 99%

A Transformer-Convolutional Neural Network Based Framework for Predicting Ionic Liquid Properties

Chen

Song

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Of central importance to evaluate the suitability of ionic liquids (ILs) for a process is the accurate estimation of IL properties related to target performances. In this work, a versatile deep learning method for predicting IL properties is developed. Molecular fingerprints are derived from the encoder state of a Transformer model pre-trained on the PubChem database, which allows transfer learning from large-scale unlabeled data and significantly improves generalization performance for developing models with small datasets. Employing the pre-trained molecular fingerprints, convolutional neural network (CNN) models for IL properties prediction are trained and tested on 11 databases. The obtained Transformer-CNN models present superior performance to state-of-the-art models in all cases and enable property prediction of millions of ILs shortly. The application of the proposed models is exemplified by searching CO2 absorbent from a huge database of 8,333,096 synthetically feasible ILs, which is by far the most high-throughput IL screening in literature.

show abstract

“…Unfortunately, thermodynamic models that can provide such predictions are still not available due to the high complexity of these biphasic systems. On the other hand, machine learning (ML) algorithms such as ANN and SVM have been employed to build complex nonlinear GC or QSPR models for different properties such as gas solubility, − surface tension, viscosity, toxicity, , melting point, , and the acid dissociation constants of organic compounds . Besides these, some of ML-based models have been integrated into the computer-aided design method for addressing some optimal design problems such as CO 2 capture , and cosmetic formulation .…”

Section: Optimal Design Of Il-absmentioning

confidence: 99%

Optimal Aqueous Biphasic Systems Design for the Recovery of Ionic Liquids

Chen

Meng

Cai

et al. 2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Ionic liquid-based aqueous biphasic systems (IL-ABS) have attracted much attention in both academia and industries due to their superior performance in many applications. In order to better utilize these novel biphasic liquid−liquid systems for recovering hydrophilic ILs from their dilute aqueous solutions, a machine learning (ML)-based ABS design method is proposed for such a purpose in this work. In this method, an ML-based model, i.e., artificial neural network (ANN)-group contribution (GC) model, is employed to predict the phase equilibrium behaviors of IL-ABS. Based on the integration with a computeraided design technique, the optimal IL-ABS is determined by formulating and solving an optimization-based mixed-integer nonlinear programming problem, where the structure of IL-ABS is denoted as the input vector in the ANN-GC model. As a proof of the concept, results of the recovery of 1-butyl-3methylimidazolium chloride ([C 4 mIm][Cl]) and n-butylpyridinium trifluoromethanesulfonate ([C 4 Py][TfO]) from aqueous solutions are presented. The ABS [C 4 mIm][Cl]-H 2 O-(NH 4 ) 2 SO 3 (identified in this work) gives an IL recovery efficiency of 95.0 wt % and a salting-out agent input of 2.36 kg/kg IL recovery, and for the ABS [C 4 mIm][Cl]-H 2 O-K 2 CO 3 (reported in the literature), they are 81.7 and 5.25, respectively. For the second case, our proposed ABS [C 4 Py][TfO]-H 2 O-KH 2 PO 4 gives an IL recovery efficiency of 95.6 wt % and a salting-out agent input of 1.81 kg/kg IL recovery, and for the reported ABS [C 4 Py][TfO]-H 2 O-(NH 4 ) 2 SO 4 , they are 80.6 and 3.16, respectively.

show abstract

Machine Learning for Ionic Liquid Toxicity Prediction

Cited by 35 publications

References 32 publications

Thermal-plasma-assisted renewable hydrogen and solid carbon production from ionic liquid-based biogas upgrading: A process intensification study

Thermal-plasma-assisted renewable hydrogen and solid carbon production from ionic liquid-based biogas upgrading: A process intensification study

A Transformer-Convolutional Neural Network Based Framework for Predicting Ionic Liquid Properties

Optimal Aqueous Biphasic Systems Design for the Recovery of Ionic Liquids

Contact Info

Product

Resources

About