Machine learning transition temperatures from 2D structure

Andrew E. Sifain, Betsy M. Rice, Samuel H. Yalkowsky, Brian C. Barnes

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


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 Bergström) comprised of over 47k structures. Open source software is available at

Original languageEnglish (US)
Article number107848
JournalJournal of Molecular Graphics and Modelling
StatePublished - Jun 2021


  • Cheminformatics
  • Gradient boosting
  • Machine learning
  • Melting and boiling points
  • Phase transitions
  • Quantitative structure-property relationships

ASJC Scopus subject areas

  • Spectroscopy
  • Physical and Theoretical Chemistry
  • Computer Graphics and Computer-Aided Design
  • Materials Chemistry


Dive into the research topics of 'Machine learning transition temperatures from 2D structure'. Together they form a unique fingerprint.

Cite this