Skip to main navigation Skip to search Skip to main content

Completing Partial Reaction Equations with Rule and Language Model-based Methods

Research output: Contribution to journal › Article › Scientific › peer-review

4 Downloads (Pure)

Abstract

Large chemical reaction data sets often suffer from incompleteness, such as missing molecules or stoichiometric information. Incomplete chemical reaction equations currently hinder us to perform automated mass balances across large sets of chemical reactions. In this work, we integrate two approaches for computational completion of partial reaction equations. Specifically, we combine a rule-based method and a machine learning model, a tailored version of the pre-trained Molecular Transformer, to complete reactions. The rule-based method takes sets of helper species into a linear solver and therewith balances some incomplete reactions. The machine learning model is trained to take partial reactions as inputs and predicts missing molecules and stoichiometries. We apply our methodology to the USPTO STEREO chemical reaction data set. The rule-based method completes about 50 % of the reactions. The language model shows a top 1 accuracy of 88.3 % on our test set and high validity (> 99 % of outputs are valid SMILES).

Original languageEnglish
Pages (from-to)3139-3144
Number of pages6
JournalComputer Aided Chemical Engineering
Volume53
DOIs
Publication statusPublished - 2024

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Chemical reaction completion
  • Language models
  • Molecular transformer
  • reaction SMILES
  • rule-based methods

Fingerprint

Dive into the research topics of 'Completing Partial Reaction Equations with Rule and Language Model-based Methods'. Together they form a unique fingerprint.

Cite this