EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Predicting both thermodynamic and kinetic properties of crystallizing molecules via transformer‐based language model

Silabrata Pahari, Chi Ho Lee, Niranjan Sitapure, Joseph Sang‐Il Kwon

AIChE Journal · 2025-10 · 71 (10)

DOI: 10.1002/aic.18923 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIChE Journal, online erschienen am 10.07.2025. Verfasst von Silabrata Pahari und 3 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crystallization is pivotal in the chemical and pharmaceutical industry, affecting particle stability, and drug release. Crystal size distribution (CSD), a critical attribute of the final dosage form, is determined by the molecular structure of the crystallizing entity. Due to molecular diversity, establishing a clear relationship between molecular structure and CSD is challenging. This study unveils CrystalFormer, a novel framework that bridges this gap. By utilizing machine‐learned molecular fingerprints derived from an encoder‐based transformer trained on a dataset of 1.8 billion molecules, CrystalFormer introduces a “universal chemical language” to represent molecules in a latent space. These fingerprints enable the prediction of thermodynamic and kinetic properties using neural networks and probabilistic regression models. The integration of these predictions with first‐principles models like population balance equations allows for the determination of CSD with confidence bounds. The results highlight good prediction accuracy of thermodynamic and kinetic parameters with errors less than 8% for paracetamol and salicylic acid.

Zitieren

APA

Pahari, S., Lee, C. H., Sitapure, N., & Kwon, J. S. (2025). Predicting both thermodynamic and kinetic properties of crystallizing molecules via transformer‐based language model. AIChE Journal, 71(10). https://doi.org/10.1002/aic.18923

Vancouver

Pahari S, Lee CH, Sitapure N, Kwon JS. Predicting both thermodynamic and kinetic properties of crystallizing molecules via transformer‐based language model. AIChE Journal. 2025;71(10). doi:10.1002/aic.18923

BibTeX
@article{Pahari2025,
  author = {Pahari, Silabrata and Lee, Chi Ho and Sitapure, Niranjan and Kwon, Joseph Sang‐Il},
  title = {Predicting both thermodynamic and kinetic properties of crystallizing molecules via transformer‐based language model},
  journal = {AIChE Journal},
  year = {2025},
  volume = {71},
  number = {10},
  doi = {10.1002/aic.18923}
}
Kostenlos starten →