EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Discovering CO 2 –Reactive Carbanions via Property-Guided Generative AI

Bo Li iD, De-En Jiang iD

Journal of Chemical Information and Modeling · 22.06.2026 · 66 (12) · 6983-6991

DOI: 10.1021/acs.jcim.6c00680 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 10.06.2026. Verfasst von Bo Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biomolecular Engineering, Vanderbilt University, Nashville, Tennessee37235, United States. Hauptthemen laut MEDLINE: Carbon Dioxide. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Energy Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High Resolution Image Download MS PowerPoint Slide Designing carbanions capable of efficient CO 2 chemisorption is an important approach for advancing reactive capture and conversion technologies. In this work, we integrate a nucleophilicity prediction model, trained using directed message-passing neural networks on Mayr’s Reactivity Database (a large, experimentally derived collection of nucleophilicity, electrophilicity, and sensitivity parameters for organic and inorganic molecules), with the Hierarchical Variational Autoencoder (HierVAE) to generate novel carbanions. Fine-tuning the pretrained latent space with predicted log k values yields structurally diverse carbanions with strong CO 2 reactivity and high generation success. Analysis of the top candidates reveals consistent trends in α-substitution, electron-withdrawing groups, and synthetic accessibility. Density functional theory (DFT) validation of the highest-ranked reactive candidates reveals good agreement for electronically stabilized systems bearing strong electron-withdrawing substituents, while deviations increase for weakly stabilized or sterically distinct carbanions, defining a clear domain of applicability for the predictive model. This study demonstrates the promise of property-guided generative AI for discovering novel carbanions for room-temperature CO 2 chemisorption.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carbon DioxideGenerative Artificial IntelligenceAutoencoderNeural Networks, ComputerDensity Functional Theory

Substanzen

Carbon Dioxide

Autor:innen und Institutionen

  • Department of Chemical and Biomolecular Engineering, Vanderbilt University, Nashville, Tennessee37235, United States.

ORCID-Profile: Bo Li, De-En Jiang

Förderung

  • Basic Energy Sciences

Zitieren

APA

Li, B., & Jiang, D. E. (2026). Discovering CO 2 –Reactive Carbanions via Property-Guided Generative AI. Journal of Chemical Information and Modeling, 66(12), 6983-6991. https://doi.org/10.1021/acs.jcim.6c00680

Vancouver

Li B, Jiang DE. Discovering CO 2 –Reactive Carbanions via Property-Guided Generative AI. Journal of Chemical Information and Modeling. 2026;66(12):6983-6991. doi:10.1021/acs.jcim.6c00680

BibTeX
@article{Li2026,
  author = {Li, Bo and Jiang, De-En},
  title = {Discovering CO 2 –Reactive Carbanions via Property-Guided Generative AI},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {12},
  pages = {6983--6991},
  doi = {10.1021/acs.jcim.6c00680}
}
Kostenlos starten →