MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails

TL;DR

MetaRF is a novel differentiable random forest model that leverages meta-learning and dimension-reduction sampling to accurately predict chemical reaction yields with minimal experimental data, aiding chemists in efficient reaction selection.

Contribution

The paper introduces MetaRF, a new attention-based differentiable random forest model optimized for few-shot reaction yield prediction using meta-learning and sampling strategies.

Findings

MetaRF achieves high accuracy in few-shot yield prediction across three datasets.

The model's top predictions closely match ideal high-yield reactions in high-throughput experiments.

MetaRF adapts quickly to new reagents with minimal additional data.

Abstract

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield prediction problem, which assists chemists in selecting high-yield reactions in a new chemical space only with a few experimental trials. To attack this challenge, we first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction, where the attention weight of a random forest is automatically optimized by the meta-learning framework and can be quickly adapted to predict the performance of new reagents while given a few additional samples. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method to determine valuable samples to be experimentally tested and then learned. Our methodology is evaluated on three different datasets and acquires satisfactory performance on few-shot prediction. In high-throughput experimentation (HTE) datasets, the average yield of our methodology's top 10 high-yield reactions is relatively close to the results of ideal yield selection.