Sign in  |  Register
Cart

CSJ Journals

▾
  • -

2020, Vol.93, No.7

841-845

Solvent Selection Scheme Using Machine Learning Based on Physicochemical Description of Solvent Molecules: Application to Cyclic Organometallic Reaction

Mikito Fujinami ,1Hiroki Maekawara ,1Ryota Isshiki ,2Junji Seino ,3,4Junichiro Yamaguchi ,2 and Hiromi Nakai *1,3,5
1Department of Chemistry and Biochemistry, School of Advanced Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan
2Department of Applied Chemistry, School of Advanced Science and Engineering, Waseda University, 3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan
3Waseda Research Institute for Science and Engineering (WISE), Waseda University, 3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan
4PRESTO, Japan Science and Technology Agency (JST), 4-1-8 Honcho, Kawaguchi, Saitama 332-0012, Japan
5Elements Strategy Initiative for Catalysts and Batteries (ESICB), Kyoto University, Katsura, Kyoto 615-8520, Japan
https://doi.org/10.1246/bcsj.20200045

Tools
PDF (1872K)
Abstract

A solvent selection scheme for optimization of reactions is proposed using machine learning, based on the numerical descriptions of solvent molecules. Twenty-eight key solvents were represented using 17 physicochemical descriptors. Clustering analysis results implied that the descriptor represents the chemical characteristics of the solvent molecules. During the assessment of an organometallic reaction system, the regression analysis indicated that learning even a small number of experimental results can be useful for identifying solvents that will produce high experimental yields. Observation of the regression coefficients, and both clustering and regression analysis, can be effective when selecting a solvent to be used for an experiment.

figure

A solvent selection scheme using machine learning for a small number of experimental data is proposed based on physicochemical description of solvent molecules. A case study of solvent selection is performed on a cyclic organometallic reaction. Both clustering and regression analysis suggest promising solvents for the reaction system.

<< Previous Impact of Enantiomeric Ligand Composition on the Photophysical Properties of Chiral Ag29 Nanoclusters Next >> Essential Role of Heterocyclic Structure of N-Alkylated 2-Pyrrolidone Derivatives for Recycling Uranium from Spent Nuclear Fuels

Select Issues

▾
  • -

Search for Articles

Advanced

Saved Search

Please login to view your saved searches.

Top Accessed Articles

Most Cited

Related Articles

  1. Machine Learning Approach for Prediction of Reaction Yield with Simulated Catalyst Parameters
  2. Virtual Reaction Condition Optimization based on Machine Learning for a Small Number of Experiments in High-dimensional Continuous and Discrete Variables
  3. Quantum Chemical Reaction Prediction Method Based on Machine Learning
  4. Developing a Support Vector Machine Based QSPR Model for Prediction of Atmospheric Lifetime of Some Halocarbons
  5. Prediction of Aqueous Solubility of Drug-Like Compounds by Using an Artificial Neural Network and Least-Squares Support Vector Machine
MANAGE YOUR ALERTS
RECOMMEND TO LIBRARY