ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
2 files

Machine Learning Transition Temperatures from 2D Structure

preprint
revised on 19.11.2020, 20:38 and posted on 20.11.2020, 07:29 by Andrew Sifain, Samuel Yalkowsky, Betsy Rice, Brian Barnes

A priori knowledge of physicochemical properties such as melting and boiling could expedite materials discovery. However, theoretical modeling from first principles poses a challenge for efficient virtual screening of potential candidates.

As an alternative, the tools of data science are becoming increasingly important for exploring chemical datasets and predicting material properties. Herein, we extend a molecular representation, or set of descriptors, first developed for quantitative structure-property relationship modeling by Yalkowsky and coworkers known as the Unified Physicochemical Property Estimation Relationships (UPPER). This molecular representation has group-constitutive and geometrical descriptors that map to enthalpy and entropy; two thermodynamic quantities that drive thermal phase transitions. We extend the UPPER representation to include additional information about sp2-bonded fragments. Additionally, instead of using the UPPER descriptors in a series of thermodynamically-inspired calculations, as per Yalkowsky, we use the descriptors to construct a vector representation for use with machine learning techniques. The concise and easy-to-compute representation, combined with a gradient-boosting decision tree model, provides an appealing framework for predicting experimental transition temperatures in a diverse chemical space. An application to energetic materials shows that the method is predictive, despite a relatively modest energetics reference dataset. We also report competitive results on diverse public datasets of melting points (i.e., OCHEM, Enamine, Bradley, and Bergstrom) comprised of over 47k structures. Open source software is available at https://github.com/USArmyResearchLab/ARL-UPPER.

History

Email Address of Submitting Author

sifain@usc.edu

Institution

US Army Research Laboratory

Country

USA

ORCID For Submitting Author

0000-0002-2964-1923

Declaration of Conflict of Interest

No conflict of interest

Exports