This is a repository for paper "Machine Learning-Guided Yield Optimization for Palladaelectro-Catalyzed Annulation Reaction".
Electrosynthesis has become an increasingly popular platform in modern organic chemistry, possessing distinctive features and reaction parameters like applied current/potential, electrodes, electrolyte system, and cell design. While these unique features give chemists new opportunities to control reactivity and selectivity, they also increase the dimensionalities of a reaction and complicate the interactions between variables, making the optimization more challenging. Herein, we present a ML workflow that leverages physical organic descriptor-based yield prediction and orthogonal experimental design to strike a delicate balance between the need for sampling diversity and the pursuit of yield improvements, thereby efficiently identifying ideal conditions for enantioselective palladaelectro-catalyzed annulation from extensive synthetic space. This work shows the potential of synergizing organic electrochemistry and data-driven approach to tackle multi-dimensional chemical optimization problems.
In order to run Jupyter Notebook involved in this repository, several third-party python packages are required. The versions of these packages in our station are listed below.
- python==3.9.16
- ipykernel==6.21.2
- pandas==1.5.2
- numpy==1.22.3
- scikit-learn==1.0.2
- py-xgboost==1.7.3
- scipy==1.8.1
Notebook Descriptor Indepence includes processes for descriptor indepence analysis. Notebook Example includes processes for productivity optimization. Notebook Model Prediction includes processes for regression prediction compared with baseline descriptors. Notebook Find New Opt Condition includes processes for finding optimization condition in new chemical space. Folder Compare with Bayesian includes processes for comparing our optimization strategy with bayesian.
Xiaoyan Hou, Shuwen Li（Co-first authors）, Johanna Frey, Xin Hong*, Lutz Ackermann*, Machine Learning-Guided Yield Optimization for Palladaelectro-Catalyzed Annulation Reaction. Chem, 10, 1 (2024).
Email: shuwen_li@zju.edu.cn