EUVIMEDEUVIMED entdecken
Crossref

A novel computational machine learning pipeline to quantify similarities in 3D protein structures

Shreyas U Hirway iD, Xiao Xu, Fan Fan

Toxicological Sciences · 2025

DOI: 10.1093/toxsci/kfaf007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Toxicological Sciences, 2025. Verfasst von Shreyas U Hirway und 2 weiteren Autor:innen. Beteiligte Einrichtung: Janssen Research & Development, LLC, La Jolla, CA 92121, United States. Hauptthemen laut MEDLINE: Machine Learning, Proteins, Computational Biology. Die Arbeit nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Animal models are widely used during drug development. The selection of suitable animal model relies on various factors such as target biology, animal resource availability, and legacy species. It is imperative that the selected animal species exhibit the highest resemblance to humans, in terms of target biology as well as the similarity in the target protein. The current practice to address cross-species protein similarity relies on pairwise sequence comparison using protein sequences, instead of the biologically relevant 3D structure of proteins. We developed a novel quantitative machine learning pipeline using 3D structure-based feature data from the Protein Data Bank, nominal data from UNIPROT, and bioactivity data from ChEMBL, all of which were matched for human and animal data. Using the XGBoost regression model, similarity scores between targets were calculated and based on these scores, the best animal species for a target was identified. For real-world application, targets from an alternative source, i.e. AlphaFold, were tested using the model, and the animal species that had the most similar protein to the human counterparts were predicted. These targets were then grouped based on their associated phenotype such that the pipeline could predict an optimal animal species.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningProteinsComputational BiologyHumansAnimalsProtein ConformationDatabases, ProteinSpecies Specificity

Stichwörter der Autor:innen

animal species selectionmachine learningprotein structure

Substanzen

Proteins

Autor:innen und Institutionen

  • Janssen Research & Development, LLC, La Jolla, CA 92121, United States.
  • Janssen Research & Development, LLC, Springhouse, PA 19477, United States.

ORCID-Profile: Shreyas U Hirway

Zitieren

APA

Hirway, S. U., Xu, X., & Fan, F. (2025). A novel computational machine learning pipeline to quantify similarities in 3D protein structures. Toxicological Sciences. https://doi.org/10.1093/toxsci/kfaf007

Vancouver

Hirway SU, Xu X, Fan F. A novel computational machine learning pipeline to quantify similarities in 3D protein structures. Toxicological Sciences. 2025. doi:10.1093/toxsci/kfaf007

BibTeX
@article{Hirway2025,
  author = {Hirway, Shreyas U and Xu, Xiao and Fan, Fan},
  title = {A novel computational machine learning pipeline to quantify similarities in 3D protein structures},
  journal = {Toxicological Sciences},
  year = {2025},
  doi = {10.1093/toxsci/kfaf007}
}
Kostenlos starten →