LAPSE:2021.0759
Published Article
LAPSE:2021.0759
Machine Learning for Ionic Liquid Toxicity Prediction
Zihao Wang, Zhen Song, Teng Zhou
October 14, 2021
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.
Keywords
ionic liquid, Machine Learning, neural network, support vector machine, toxicity
Suggested Citation
Wang Z, Song Z, Zhou T. Machine Learning for Ionic Liquid Toxicity Prediction. (2021). LAPSE:2021.0759
Author Affiliations
Wang Z: Process Systems Engineering, Max Planck Institute for Dynamics of Complex Technical Systems, Sandtorstr. 1, D-39106 Magdeburg, Germany
Song Z: Process Systems Engineering, Otto-von-Guericke University Magdeburg, Universitätsplatz 2, D-39106 Magdeburg, Germany [ORCID]
Zhou T: Process Systems Engineering, Max Planck Institute for Dynamics of Complex Technical Systems, Sandtorstr. 1, D-39106 Magdeburg, Germany; Process Systems Engineering, Otto-von-Guericke University Magdeburg, Universitätsplatz 2, D-39106 Magdeburg, Germany [ORCID]
Journal Name
Processes
Volume
9
Issue
1
First Page
pr9010065
Year
2020
Publication Date
2020-12-30
Published Version
ISSN
2227-9717
Version Comments
Original Submission
Other Meta
PII: pr9010065, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2021.0759
This Record
External Link

doi:10.3390/pr9010065
Publisher Version
Download
Files
[Download 1v1.pdf] (2.6 MB)
Oct 14, 2021
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
74
Version History
[v1] (Original Submission)
Oct 14, 2021
 
Verified by curator on
Oct 14, 2021
This Version Number
v1
Citations
Most Recent
This Version
URL Here
http://psecommunity.org/LAPSE:2021.0759
 
Original Submitter
Calvin Tsay
Links to Related Works
Directly Related to This Work
Publisher Version