EUVIMEDEUVIMED entdecken
Crossref

Advancing molecular graphs with descriptors for the prediction of chemical reaction yields

Dzvenymyra Yarish, Sofiya Garkot, Oleksandr O Grygorenko, Dmytro S Radchenko, Yurii S Moroz iD, Oleksandr Gurbych iD

Journal of Computational Chemistry · 15.01.2023 · 44 (2) · 76-92

DOI: 10.1002/jcc.27016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Chemistry, online erschienen am 20.10.2022. Verfasst von Dzvenymyra Yarish und 5 weiteren Autor:innen. Beteiligte Einrichtung: SoftServe, Inc., Lviv, Ukraine. Hauptthemen laut MEDLINE: Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 87 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chemical yield is the percentage of the reactants converted to the desired products. Chemists use predictive algorithms to select high‐yielding reactions and score synthesis routes, saving time and reagents. This study suggests a novel graph neural network architecture for chemical yield prediction. The network combines structural information about participants of the transformation as well as molecular and reaction‐level descriptors. It works with incomplete chemical reactions and generates reactants‐product atom mapping. We show that the network benefits from advanced information by comparing it with several machine learning models and molecular representations. Models included logistic regression, support vector machine, CatBoost, and Bidirectional Encoder Representations from Transformers. Molecular representations included extended‐connectivity fingerprints, Morgan fingerprints, SMILESVec embeddings, and textual. Classification and regression objectives were assessed for each model and feature set. The goal of each classification model was to separate zero‐ and non‐zero‐yielding reactions. The models were trained and evaluated on a proprietary dataset of 10 reaction types. Also, the models were benchmarked on two public single reaction type datasets. The study was supplemented with analysis of data, results, and errors, as well as the impact of steric factors, side reactions, isolation, and purification efficiency. The supplementary code is available at https://github.com/SoftServeInc/yield-paper .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAlgorithmsHumansMachine LearningSupport Vector Machine

Stichwörter der Autor:innen

SMILESchemical reactionsdeep learninggraph neural networksreaction yields

Autor:innen und Institutionen

  • SoftServe, Inc., Lviv, Ukraine.
  • Ukrainian Catholic University, Lviv, Ukraine.
  • Enamine Ltd., Kyiv, Ukraine.
  • Taras Shevchenko National University of Kyiv, Kyiv, Ukraine.
  • Chemspace LLC, Kyiv, Ukraine.
  • Lviv Polytechnic National University, Lviv, Ukraine.

ORCID-Profile: Yurii S Moroz, Oleksandr Gurbych

Zitieren

APA

Yarish, D., Garkot, S., Grygorenko, O. O., Radchenko, D. S., Moroz, Y. S., & Gurbych, O. (2023). Advancing molecular graphs with descriptors for the prediction of chemical reaction yields. Journal of Computational Chemistry, 44(2), 76-92. https://doi.org/10.1002/jcc.27016

Vancouver

Yarish D, Garkot S, Grygorenko OO, Radchenko DS, Moroz YS, Gurbych O. Advancing molecular graphs with descriptors for the prediction of chemical reaction yields. Journal of Computational Chemistry. 2023;44(2):76-92. doi:10.1002/jcc.27016

BibTeX
@article{Yarish2023,
  author = {Yarish, Dzvenymyra and Garkot, Sofiya and Grygorenko, Oleksandr O and Radchenko, Dmytro S and Moroz, Yurii S and Gurbych, Oleksandr},
  title = {Advancing molecular graphs with descriptors for the prediction of chemical reaction yields},
  journal = {Journal of Computational Chemistry},
  year = {2023},
  volume = {44},
  number = {2},
  pages = {76--92},
  doi = {10.1002/jcc.27016}
}
Kostenlos starten →