Intelligent Chemical Purification Technique Based on Machine Learning

TL;DR

This work tackles inefficiencies in column chromatography by building an automated data-collection platform and applying a geometry-enhanced graph neural network, QGeoGNN, to predict key separation parameters for multiple column specifications. Transfer learning is leveraged to adapt the model from a 4g baseline to 8g, 25g, and 40g columns, with significant improvements over direct training. A novel separation probability metric, $S_p$, quantifies the likelihood of successful separation using elution-volume quantiles, and experimental validation with a Claisen rearrangement demonstrates practical guidance for separations. The study advances AI-assisted chemical purification by delivering scalable data-driven predictions and a framework for cross-specification applicability, while outlining avenues for broader eluents and larger chemical spaces.

Abstract

We present an innovative of artificial intelligence with column chromatography, aiming to resolve inefficiencies and standardize data collection in chemical separation and purification domain. By developing an automated platform for precise data acquisition and employing advanced machine learning algorithms, we constructed predictive models to forecast key separation parameters, thereby enhancing the efficiency and quality of chromatographic processes. The application of transfer learning allows the model to adapt across various column specifications, broadening its utility. A novel metric, separation probability ($S_p$), quantifies the likelihood of effective compound separation, validated through experimental verification. This study signifies a significant step forward int the application of AI in chemical research, offering a scalable solution to traditional chromatography challenges and providing a foundation for future technological advancements in chemical analysis and purification.

Figures (5)

• Figure 1: Schematic diagram of main parts. (a) Research pipeline. (b) Schematic of automation platform. (c) Separation process schematic (CC, column chromatography).
• Figure 2: Dataset distribution and feature engineering. (a) Column specifications for number distribution. (b) Distribution of the amount of data according to the proportion of eluents. (c) Feature engineering for ANN and LGB. (d) The schematic instruction of atom-bond Graph G and bond-angle Graph H. (e) Schematic diagram of QGeoGNN hierarchy.
• Figure 3: The training results of the basic model. (a) Training outcomes of different machine learning algorithms based on 4g-dataset. (b) Relationship between mean absolute error (MAE) and compound similarity. (c) Impact of the training set proportion on $R^{2}$. (d) Influence of Gaussian noise ratio on $R^{2}$.
• Figure 4: Transfer learning and training results. (a) Transfer learning process; (b, c, d) Training results from the application of transfer learning to the 8g, 25g, and 40g column datasets using the QGeoGNN model initially developed for the 4g.
• Figure 5: Application of $S_p$ in CC predictive model. (a) Schematic diagram of $S_p$ calculation. (b) The classic Claisen rearrangement reaction. (c, d) Wet laboratory validation based on model prediction results.