دورية أكاديمية
Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials
| العنوان: | Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials |
|---|---|
| المؤلفون: | Siwoo Lee, Stefan Heinen, Danish Khan, O Anatole von Lilienfeld |
| المصدر: | Machine Learning: Science and Technology, Vol 5, Iss 1, p 015052 (2024) |
| بيانات النشر: | IOP Publishing, 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Computer engineering. Computer hardware LCC:Electronic computers. Computer science |
| مصطلحات موضوعية: | quantum chemistry, machine learning, oxidation potentials, large language model, literature data extraction, Computer engineering. Computer hardware, TK7885-7895, Electronic computers. Computer science, QA75.5-76.95 |
| الوصف: | 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. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2632-2153 |
| Relation: | https://doaj.org/toc/2632-2153 |
| DOI: | 10.1088/2632-2153/ad2f52 |
| URL الوصول: | https://doaj.org/article/95be18147f884c3e90f822b66fe4feae |
| رقم الأكسشن: | edsdoj.95be18147f884c3e90f822b66fe4feae |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 26322153 |
|---|---|
| DOI: | 10.1088/2632-2153/ad2f52 |