Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction
Journal article, 2022

Computer aided synthesis planning, suggesting synthetic routes for molecules of interest, is a rapidly growing field. The machine learning methods used are often dependent on access to large datasets for training, but finite experimental budgets limit how much data can be obtained from experiments. This suggests the use of schemes for data collection such as active learning, which identifies the data points of highest impact for model accuracy, and which has been used in recent studies with success. However, little has been done to explore the robustness of the methods predicting reaction yield when used together with active learning to reduce the amount of experimental data needed for training. This study aims to investigate the influence of machine learning algorithms and the number of initial data points on reaction yield prediction for two public high-throughput experimentation datasets. Our results show that active learning based on output margin reached a pre-defined AUROC faster than random sampling on both datasets. Analysis of feature importance of the trained machine learning models suggests active learning had a larger influence on the model accuracy when only a few features were important for the model prediction.

Reaction Yield Prediction

Bayesian Matrix Factorization

Random Forest

Active Learning

Neural Networks


Simon Johansson

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

AstraZeneca AB

Hampus Gummesson Svensson

AstraZeneca AB

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Esben Jannik Bjerrum

AstraZeneca AB

Alexander Schliep

University of Gothenburg

Morteza Haghir Chehreghani

Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI

Christian Tyrchan

AstraZeneca AB

Ola Engkvist

Chalmers, Computer Science and Engineering (Chalmers)

AstraZeneca AB

Molecular Informatics

1868-1743 (ISSN) 1868-1751 (eISSN)

Vol. In Press

Subject Categories

Language Technology (Computational Linguistics)

Bioinformatics (Computational Biology)

Bioinformatics and Systems Biology





More information

Latest update