EUVIMEDEUVIMED entdecken
Crossref

Descriptor-Free Deep Learning QSAR Model for the Fraction Unbound in Human Plasma

Michael Riedl iD, Sayak Mukherjee, Mitch Gauthier

Molecular Pharmaceutics · 02.10.2023 · 20 (10) · 4984-4993

DOI: 10.1021/acs.molpharmaceut.3c00129 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Pharmaceutics, online erschienen am 01.09.2023. Verfasst von Michael Riedl und 2 weiteren Autor:innen. Beteiligte Einrichtung: Battelle, Columbus, Ohio 43201, United States. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Deep Learning. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: Battelle.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chemical-specific parameters are either measured in vitro or estimated using quantitative structure-activity relationship (QSAR) models. The existing body of QSAR work relies on extracting a set of descriptors or fingerprints, subset selection, and training a machine learning model. In this work, we used a state-of-the-art natural language processing model, Bidirectional Encoder Representations from Transformers, which allowed us to circumvent the need for calculation of these chemical descriptors. In this approach, simplified molecular-input line-entry system (SMILES) strings were embedded in a high-dimensional space using a two-stage training approach. The model was first pre-trained on a masked SMILES token task and then fine-tuned on a QSAR prediction task. The pre-training task learned meaningful high-dimensional embeddings based upon the relationships between the chemical tokens in the SMILES strings derived from the "in-stock" portion of the ZINC 15 dataset─a large dataset of commercially available chemicals. The fine-tuning task then perturbed the pre-trained embeddings to facilitate prediction of a specific QSAR endpoint of interest. The power of this model stems from the ability to reuse the pre-trained model for multiple different fine-tuning tasks, reducing the computational burden of developing multiple models for different endpoints. We used our framework to develop a predictive model for fraction unbound in human plasma (fu,p). This approach is flexible, requires minimum domain expertise, and can be generalized for other parameters of interest for rapid and accurate estimation of absorption, distribution, metabolism, excretion, and toxicity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipDeep LearningHumansMachine Learning

Stichwörter der Autor:innen

BERTQSARdeep learningfraction unboundhuman plasma

Autor:innen und Institutionen

  • Battelle, Columbus, Ohio 43201, United States.

ORCID-Profile: Michael Riedl

Förderung

  • Battelle

Zitieren

APA

Riedl, M., Mukherjee, S., & Gauthier, M. (2023). Descriptor-Free Deep Learning QSAR Model for the Fraction Unbound in Human Plasma. Molecular Pharmaceutics, 20(10), 4984-4993. https://doi.org/10.1021/acs.molpharmaceut.3c00129

Vancouver

Riedl M, Mukherjee S, Gauthier M. Descriptor-Free Deep Learning QSAR Model for the Fraction Unbound in Human Plasma. Molecular Pharmaceutics. 2023;20(10):4984-4993. doi:10.1021/acs.molpharmaceut.3c00129

BibTeX
@article{Riedl2023,
  author = {Riedl, Michael and Mukherjee, Sayak and Gauthier, Mitch},
  title = {Descriptor-Free Deep Learning QSAR Model for the Fraction Unbound in Human Plasma},
  journal = {Molecular Pharmaceutics},
  year = {2023},
  volume = {20},
  number = {10},
  pages = {4984--4993},
  doi = {10.1021/acs.molpharmaceut.3c00129}
}
Kostenlos starten →