The Effect of Chemical Representation on Active Machine Learning Towards Closed-Loop Optimization

Abstract

Multivariate chemical reaction optimization involving catalytic systems is a non-trivial task due to the high number of tuneable parameters and discrete choices. Closed-loop optimization featuring active Machine Learning (ML) represents a powerful strategy for automating reaction optimization. However, the translation of chemical reaction conditions into a machine-readable format comes with the challenge of finding highly informative features which accurately capture the factors for reaction success and allow the model to learn efficiently. Herein, we compare the efficacy of different calculated chemical descriptors for a high throughput generated dataset to determine the impact on a supervised ML model when predicting reaction yield. Then, the effect of featurization and size of the initial dataset within a closed-loop reaction optimization was examined. Finally, the balance between descriptor complexity and dataset size was considered. Ultimately, tailored descriptors did not outperform simple generic representations, however, a larger initial dataset accelerated reaction optimization.

A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

“…3B) showing its robustness against the selection of the initial experiments. 46 Another important consideration in the success of an optimization is the choice of the initial conditions to start the optimization campaign. We illustrate the impact of the initialization method using the Pd-catalyzed C-H arylation dataset (see Ref.…”

Automated pH Adjustment Driven by Robotic Workflows and Active Machine Learning

“…On average, using the large feature set resulted in 3.1 ± 0.6 iterations and the small feature set in 3.2 ± 0.6. While the results of the GP performance without chemical information might seem surprising, it must be noted that additional features increase the number of model parameters that need to be learned, as shown in other previously reported active ML studies by Pomberger et al 40 The model initialization for each single system was conducted with 5% of the training data instead of a consistent number of datapoints. While the number of initialization datapoints varies, the focus is on the relative comparison of the different feature sets.…”

“…39 Previous literature has led to ambiguous outcomes on whether the addition of chemical information within low data regimes, such as the initialization of active-ML search strategies, is beneficial. 31,40 To learn more about featurization effects on this specific application, we compared two input feature sets. The large feature set contains information on the components' concentrations, component pKa values, number of protons a buffer can accept/donate and the initial pH value of the buffer mixture (prior to any acid/base addition).…”

Working at the interfaces of data science and synthetic electrochemistry

“…However, as the authors pointed out, the effectiveness of this approach was hampered by a lack of sufficient data, which could potentially be validated by comparison to baseline models. Indeed, as non-parametric algorithms are incorporated into synthetic electrochemistry, maintaining high validation metrics is essential in ensuring the robustness of predictive models [ 39 – 43 ].…”