Machine learning enabling prediction of the bond dissociation enthalpy of hypervalent iodine from SMILES

Masaya Nakajima,Tetsuhiro Nemoto

doi:10.1038/s41598-021-99369-8

Masaya Nakajima, Tetsuhiro Nemoto

Open Access

https://doi.org/10.1038/s41598-021-99369-8

Copy DOI

Journal: Scientific Reports	Publication Date: Oct 12, 2021
Citations: 15	License type: open-access

Affiliation: Chiba University

Abstract

Machine learning to create models on the basis of big data enables predictions from new input data. Many tasks formerly performed by humans can now be achieved by machine learning algorithms in various fields, including scientific areas. Hypervalent iodine compounds (HVIs) have long been applied as useful reactive molecules. The bond dissociation enthalpy (BDE) value is an important indicator of reactivity and stability. Experimentally measuring the BDE value of HVIs is difficult, however, and the value has been estimated by quantum calculations, especially density functional theory (DFT) calculations. Although DFT calculations can access the BDE value with high accuracy, the process is highly time-consuming. Thus, we aimed to reduce the time for predicting the BDE by applying machine learning. We calculated the BDE of more than 1000 HVIs using DFT calculations, and performed machine learning. Converting SMILES strings to Avalon fingerprints and learning using a traditional Elastic Net made it possible to predict the BDE value with high accuracy. Furthermore, an applicability domain search revealed that the learning model could accurately predict the BDE even for uncovered inputs that were not completely included in the training data.

Highlights

Machine learning to create models on the basis of big data enables predictions from new input data
Hypervalent iodine (HVI), which bears over eight valence electrons on iodine, is a reactive molecule used as an oxidant or an alkylating agent in organic s ynthesis[8,9,10,11,12,13,14,15]
In addition to the bond dissociation enthalpy (BDE) data of 206 HVIs, which we reported previously, we newly calculated 510 HVIs by density functional theory (DFT) calculations (Fig. 2)

Summary

Introduction

Machine learning to create models on the basis of big data enables predictions from new input data. In the field of organic chemistry, machine learning is applied for predicting synthetic pathways and reactivity, and optimising reaction conditions[20,21,22,23,24,25,26]. Yu and co-workers reported the prediction model of BDE of carbonyl groups with machine learning in 202027 Their important model accurately predicts the BDE value of the C=O bond on the basis of the bond length and bond angle of the relevant site as inputs. We considered that an ideal and highly useful method of BDE prediction for chemists should not require quantum computations to prepare the input data. We decided to use only structural formula information, such as SMILES strings, to predict the BDE value of HVIs by machine learning (Fig. 1)

Objectives

Methods

Results

Conclusion