DES Property Prediction with Gaussian Processes

This repository contains lecture and workflow materials for generating data, introducing Gaussian processes, implementing GP models, and applying them to deep eutectic solvent (DES) property prediction.

Project Structure

• 00_data_generation.py: data generation and preprocessing steps
• 01_introduction_to_gp.py: introductory Gaussian process examples
• 02_GP_implementation.py: GP modeling implementation details
• 03_des_property_prediction.py: DES property prediction workflow
• run_pipeline.py: pipeline execution entry point

Links

• Installing uv
• Running marimo: uv run marimo edit

References

The work in this repository is related to the following publications:

@article{abranchesSigmaProfilesDeep2022a,
	title = {Sigma Profiles in Deep Learning: Towards a Universal Molecular Descriptor},
	shorttitle = {Sigma Profiles in Deep Learning},
	author = {Abranches, Dinis O. and Zhang, Yong and Maginn, Edward J. and Colón, Yamil J.},
	date = {2022-05-05},
	journaltitle = {Chemical Communications},
	shortjournal = {Chem. Commun.},
	volume = {58},
	number = {37},
	pages = {5630--5633},
	publisher = {The Royal Society of Chemistry},
	issn = {1364-548X},
	doi = {10.1039/D2CC01549H},
	url = {https://pubs.rsc.org/en/content/articlelanding/2022/cc/d2cc01549h},
	urldate = {2025-09-03},
	abstract = {This work showcases the remarkable ability of sigma profiles to function as molecular descriptors in deep learning. The sigma profiles of 1432 compounds are used to train convolutional neural networks that accurately correlate and predict a wide range of physicochemical properties. The architectures developed are then exploited to include temperature as an additional feature.},
	langid = {english},
	file = {/Users/fredericbender/Zotero/storage/BID2H43I/Abranches et al. - 2022 - Sigma profiles in deep learning towards a universal molecular descriptor.pdf;/Users/fredericbender/Zotero/storage/H85TGYCL/Abranches et al. - 2022 - Sigma profiles in deep learning towards a universal molecular descriptor.pdf}
}

@article{santosArtificialIntelligenceDiscovery2025,
	title = {Artificial {{Intelligence}} in the {{Discovery}} of {{Deep Eutectic Solvents}} with {{Lubricant Applications}}},
	author = {Santos, João P. and Sosa, Filipe H. B. and Abranches, Dinis O. and Coutinho, João A. P.},
	date = {2025-09-23},
	journaltitle = {ACS Omega},
	shortjournal = {ACS Omega},
	volume = {10},
	number = {37},
	pages = {43024--43033},
	publisher = {American Chemical Society},
	doi = {10.1021/acsomega.5c05944},
	url = {https://doi.org/10.1021/acsomega.5c05944},
	urldate = {2026-04-14},
	abstract = {Following evidence suggesting that deep eutectic solvents (DESs) can potentially replace conventional mineral-based lubricants, this study aims to leverage artificial intelligence to discover, and then experimentally prepare and characterize, novel DES-based lubricants. To do so, Gaussian processes (GPs) were employed to describe and predict relevant physicochemical properties of DESs, specifically density, viscosity, and melting temperature. This was accomplished by using a comprehensive data set encompassing nearly 400 different binary and ternary DESs and including 3985, 4197, and 2003 independent data points (different DES compositions and temperatures) for density, viscosity, and melting temperature, respectively. GPs were trained and rigorously evaluated, attaining testing set coefficients of determination of 0.98, 0.92, and 0.94, respectively. GPs were then used to predict the density, viscosity, and melting temperature of all possible binary 1:1 combinations of DES precursors available in the database, yielding more than 50,000 DESs. These DESs with precursors available in our laboratory and that were predicted to be liquid at room temperature, exhibiting either minimal density and minimal viscosity, or maximal density and maximal viscosity, were experimentally prepared and characterized. Good agreement was found between GP predictions and experimental results. Given the identification of DESs with exceptionally low viscosities, a subset of these liquids was selected for tribological evaluation. Finally, tribological tests revealed that several of the tested DESs, such as camphor:octanoic acid, outperformed the reference oil in terms of friction reduction.},
	keywords = {ML,sigma-profile},
	file = {/Users/fredericbender/Zotero/storage/R8PPBZWC/Santos et al. - 2025 - Artificial Intelligence in the Discovery of Deep Eutectic Solvents with Lubricant Applications.pdf}
}