Submission Track: Papers
Submission Category: AI-Guided Design + Automated Chemical Synthesis
Keywords: Hydrolysis, DFT, GNN, pH stability, chemical design
Supplementary Material: pdf
TL;DR: In this work, we developed a predictive framework which can generate reaction products of hydrolysis and then utilize a trained graph neural network model to predict the reaction free energies (∆G).
Abstract: Hydrolysis is a fundamental chemical reaction where water facilitates the cleavage of bonds in a reactant molecule. The process is ubiquitous in biological and chemical systems, owing to water's remarkable versatility as a solvent. However, accurately predicting the feasibility of hydrolysis through computational techniques is a difficult task, as subtle changes in reactant structure like heteroatom substitutions or neighboring functional groups can influence the reaction outcome. Furthermore, hydrolysis is sensitive to the pH of the aqueous medium, and the same reaction can have different reaction properties at different pH conditions. In this work, we have combined reaction templates and high-throughput ab-initio calculations to construct a diverse dataset of hydrolysis free energies. Subsequently, we use a Graph Neural Network (GNN) to predict the free energy changes ($\Delta$G) for all hydrolytic pathways within a subset of the QM9 molecular dataset. The framework automatically identifies reaction centers, generates hydrolysis products, and utilizes a trained GNN model to predict $\Delta$G values for all potential hydrolysis reactions in a given molecule. The long-term goal of the work is to develop a data-driven, computational tool for high-throughput screening of pH-specific hydrolytic stability and the rapid prediction of reaction products, which can then be applied in a wide array of applications including chemical recycling of polymers and ion-conducting membranes for clean energy generation and storage.
Digital Discovery Special Issue: Yes
Submission Number: 28
Loading