Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials

Abstract

We present an automated data-collection pipeline involving a convolutional neural network and a large language model to extract user-specified tabular data from peer-reviewed literature. The pipeline is applied to 74 reports published between 1957 and 2014 with experimentally-measured oxidation potentials for 592 organic molecules (−0.75 to 3.58 V). After data curation (solvents, reference electrodes, and missed data points), we trained multiple supervised machine learning (ML) models reaching prediction errors similar to experimental uncertainty (∼0.2 V). For experimental measurements of identical molecules reported in multiple studies, we identified the most likely value based on out-of-sample ML predictions. Using the trained ML models, we then estimated oxidation potentials of ∼132k small organic molecules from the QM9 (quantum mechanics data for organic molecules with up to 9 atoms not counting hydrogens) data set, with predicted values spanning 0.21–3.46 V. Analysis of the QM9 predictions in terms of plausible descriptor-property trends suggests that aliphaticity increases the oxidation potential of an organic molecule on average from ∼1.5 V to ∼2 V, while an increase in number of heavy atoms lowers it systematically. The pipeline introduced offers significant reductions in human labor otherwise required for conventional manual data collection of experimental results, and exemplifies how to accelerate scientific research through automation.

Keywords

• quantum chemistry
• machine learning
• oxidation potentials
• large language model
• literature data extraction