Prediction of Optimal Conditions of Hydrogenation Reaction Using the Likelihood Ranking Approach.

Valentina A Afonina,Maxim D Shevelev,Albina Nurmukhametova,Dina A Khasanova,Alexandre Varnek,Daniyar A Mazitov,Timur I Madzhidov,Ramil I Nugmanov,Vladimir A Burilov

doi:10.3390/ijms23010248

Abstract

The selection of experimental conditions leading to a reasonable yield is an important and essential element for the automated development of a synthesis plan and the subsequent synthesis of the target compound. The classical QSPR approach, requiring one-to-one correspondence between chemical structure and a target property, can be used for optimal reaction conditions prediction only on a limited scale when only one condition component (e.g., catalyst or solvent) is considered. However, a particular reaction can proceed under several different conditions. In this paper, we describe the Likelihood Ranking Model representing an artificial neural network that outputs a list of different conditions ranked according to their suitability to a given chemical transformation. Benchmarking calculations demonstrated that our model outperformed some popular approaches to the theoretical assessment of reaction conditions, such as k Nearest Neighbors, and a recurrent artificial neural network performance prediction of condition components (reagents, solvents, catalysts, and temperature). The ability of the Likelihood Ranking model trained on a hydrogenation reactions dataset, (~42,000 reactions) from Reaxys® database, to propose conditions that led to the desired product was validated experimentally on a set of three reactions with rich selectivity issues.

Highlights

Nowadays, an interest in automation is growing every year, in the field of chemistry where the creation of a fully automatized robochemist has become realistic [1,2,3,4,5]
Reaction condition prediction is quite a challenging task due to several reasons: (i) a particular reaction may proceed under several different conditions; (ii) all conditions leading to a particular product are never explored experimentally; and (iii) negative data are usually absent
We demonstrate that consideration of reaction condition prediction as a ranking problem solves all aforementioned problems

Summary

Introduction

An interest in automation is growing every year, in the field of chemistry where the creation of a fully automatized robochemist has become realistic [1,2,3,4,5]. One of the problems of the automated development of a synthesis plan of the target compound is the selection of experimental conditions leading to a reasonable yield. Various theoretical approaches, ranging from quantum chemical methods [6] to an artificial neural network of complex architecture [7], were used for condition assessment. These studies were mostly focused on predictions of the role a compound as a condition component: solvent; catalyst; or reagent. Marcou et al [8]

Methods

Results

Conclusion