Evaluating ionic liquid toxicity with machine learning and structural similarity methods DOI Creative Commons

Rongli Shan,

Runqi Zhang, Ying Gao

et al.

Green Chemical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Ionic liquids (ILs) have garnered significant interest owing to their distinct physicochemical traits. Nonetheless, extensive application is curtailed by ecotoxicity concerns. This study aimed develop a quantitative structure-activity relationship (QSAR) model for predicting the toxicity of ILs in biological cells. Toxicity data on leukemia rat cell line IPC-81, Escherichia coli (E. coli), and Acetylcholinesterase (AChE) were collected from open-source databases, two integrated models, random forest (RF) gradient boosted decision tree (GBDT), used train data. The molecular structures represented three different methods, namely descriptor (MD), fingerprint (MF), identifier (MI), respectively. Tanimoto similarity coefficients indicate that MD has stronger ability recognize structural similarity. Statistical metrics performance showed models (MD-RF MD-GBDT) with as an input feature performed better datasets. SHapley Additive exPlanations (SHAP) method explains importance features. specifically, increasing carbon chain length number fluorine atoms structure can effectively reduce toxic effects employs machine learning grasp how relates inhibiting biotoxicity, offering insights crafting safer, eco-friendly IL designs.

Language: Английский

Combined Machine Learning and High-Throughput Calculations Predict Heyd–Scuseria–Ernzerhof Band Gap of 2D Materials and Potential MoSi2N4 Heterostructures DOI
Weibin Zhang,

Jie Guo,

Xiankui Lv

et al.

The Journal of Physical Chemistry Letters, Journal Year: 2024, Volume and Issue: 15(20), P. 5413 - 5419

Published: May 14, 2024

We present a novel target-driven methodology devised to predict the Heyd–Scuseria–Ernzerhof (HSE) band gap of two-dimensional (2D) materials leveraging comprehensive C2DB database. This innovative approach integrates machine learning and density functional theory (DFT) calculations HSE gap, conduction minimum (CBM), valence maximum (VBM) 2176 types 2D materials. Subsequently, we collected data set comprising 3539 materials, each characterized by its gaps, CBM, VBM. Considering lattice disparities between MoSi2N4 (MSN) our analysis predicted 766 potential MSN/2D heterostructures. These heterostructures are further categorized into four distinct based on relative positions their CBM VBM: Type I encompasses 230 variants, II comprises 244 configurations, III consists 284 permutations, 0 8 types.

Language: Английский

Citations

17
Fluorine Domains Induced Ultrahigh Nitrogen Solubility in Ionic Liquids DOI
Kun Li, Yanlei Wang, Chenlu Wang

et al.

Journal of the American Chemical Society, Journal Year: 2024, Volume and Issue: 146(37), P. 25569 - 25577

Published: Aug. 2, 2024

Fluorinated ionic liquids (ILs) are well-known as electrolytes in the nitrogen (N2) electroreduction reaction due to their exceptional gas solubility. However, influence of fluorinated functional group on N2 solvation and solubility enhancement remains unclear. Massive molecular dynamics simulations free energy perturbation methods conducted investigate 11 traditional 9 ILs. It shows that IL 1-Ethyl-3-methylimidazolium tris(pentafluoroethyl) trifluorophosphate ([Emim]FAP) exhibits ultrahigh solubility, 4.844 × 10–3, approximately 118 times higher than nitrate ([Emim]NO3). Moreover, ILs with more 10 C–F bonds possess others show an exothermic nature during solvation. As number decreases, decreases significantly displays opposite endothermic behavior. To understand ILs, we propose a concept fluorine densification (FDE), referring average strength interaction between atoms per unit volume domains, demonstrating linear relationship bonds. Physically, lower FDE results N2–anion pair dissociation volume, finally enhancing Consequently, medium long alkyl tails within polar environment defines distinct domain, emphasizing FDE's role Overall, these quantitative will not only deepen understanding but may also shed light rational design IL-based high-performance capture conversion technologies.

Language: Английский

Citations

7
Prediction of the solubility of fluorinated gases in ionic liquids by machine learning with COSMO-RS-based descriptors DOI
Yuxuan Fu,

Wenbo Mu,

Xuefeng Bai

et al.

Separation and Purification Technology, Journal Year: 2025, Volume and Issue: unknown, P. 132413 - 132413

Published: March 1, 2025

Language: Английский

Citations

0
Predictive modeling of CO2 solubility in piperazine aqueous solutions using boosting algorithms for carbon capture goals DOI Creative Commons
Mohammadreza Mohammadi, Aydin Larestani,

Mahin Schaffie

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 27, 2024

Language: Английский

Citations

3
Prediction of acetylene solubility by a mechanism-data hybrid-driven machine learning model constructed based on COSMO-RS theory DOI

Yao Mu,

Tianying Dai,

Jiahe Fan

et al.

Journal of Molecular Liquids, Journal Year: 2024, Volume and Issue: 414, P. 126194 - 126194

Published: Oct. 5, 2024

Language: Английский

Citations

3
Recent progress and prospects in electroreduction of nitrogen to ammonia in non-aqueous electrolytes DOI
Muhammad Yasir, Zhiliang Zhao, Min Zeng

et al.

Current Opinion in Electrochemistry, Journal Year: 2024, Volume and Issue: 45, P. 101487 - 101487

Published: March 15, 2024

Language: Английский

Citations

1
Predicting the solubility of CO2 and N2 in ionic liquids based on COSMO-RS and machine learning DOI Creative Commons
Hongling Qin, Ke Wang,

Xifei Ma

et al.

Frontiers in Chemistry, Journal Year: 2024, Volume and Issue: 12

Published: Oct. 31, 2024

As ionic liquids (ILs) continue to be prepared, there is a growing need develop theoretical methods for predicting the properties of ILs, such as gas solubility. In this work, different strategies were employed obtain solubility CO

Language: Английский

Citations

1
Insights into the pore structure effect on the mass transfer of fuel cell catalyst layer via combining Machine learning and multiphysics simulation DOI

Lai-Ming Luo,

Xinrui Liu, Jujia Zhang

et al.

Chemical Engineering Science, Journal Year: 2024, Volume and Issue: unknown, P. 120830 - 120830

Published: Oct. 1, 2024

Language: Английский

Citations

1
Machine learning models coupled with Ionic Fragment σ-profiles to predict ammonia solubility in ionic liquids DOI Creative Commons
Kaikai Li,

Yuesong Zhu,

Sensen Shi

et al.

Green Chemical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Language: Английский

Citations

0
Evaluating ionic liquid toxicity with machine learning and structural similarity methods DOI Creative Commons

Rongli Shan,

Runqi Zhang, Ying Gao

et al.

Green Chemical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Ionic liquids (ILs) have garnered significant interest owing to their distinct physicochemical traits. Nonetheless, extensive application is curtailed by ecotoxicity concerns. This study aimed develop a quantitative structure-activity relationship (QSAR) model for predicting the toxicity of ILs in biological cells. Toxicity data on leukemia rat cell line IPC-81, Escherichia coli (E. coli), and Acetylcholinesterase (AChE) were collected from open-source databases, two integrated models, random forest (RF) gradient boosted decision tree (GBDT), used train data. The molecular structures represented three different methods, namely descriptor (MD), fingerprint (MF), identifier (MI), respectively. Tanimoto similarity coefficients indicate that MD has stronger ability recognize structural similarity. Statistical metrics performance showed models (MD-RF MD-GBDT) with as an input feature performed better datasets. SHapley Additive exPlanations (SHAP) method explains importance features. specifically, increasing carbon chain length number fluorine atoms structure can effectively reduce toxic effects employs machine learning grasp how relates inhibiting biotoxicity, offering insights crafting safer, eco-friendly IL designs.

Language: Английский

Citations

0