EUVIMEDEUVIMED entdecken
Crossref

HTS-Oracle v2: Prospective Ai-Guided Discovery and Experimental Validation of Small Molecule Modulators Across Multiple Targets

Somaya A Abdel-Rahman, Moustafa T Gabr iD

Journal of Chemical Information and Modeling · 10.08.2026 · 66 (15) · 8998-9008

DOI: 10.1021/acs.jcim.6c01522 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 13.07.2026. Verfasst von Somaya A Abdel-Rahman und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Molecular Imaging Innovations Institute (MI3), Weill Cornell Medicine, New York, New York10065, United States. Hauptthemen laut MEDLINE: Small Molecule Libraries, High-Throughput Screening Assays, Drug Discovery, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-throughput screening (HTS) remains the cornerstone of early phase small molecule discovery yet consistently underperforms against immunotherapy targets, yielding validated hit rates below 0.1%. Here we introduce HTS-Oracle v2, which features rigorous cross-validation that ensures honest performance estimates. HTS-Oracle v2 was trained and validated across four clinically significant immune checkpoint targets (CD28, ICOS, LAG-3, and TIGIT) achieving ROC-AUC values of 0.968, 0.969, 0.875, and 0.928, respectively, under rigorous cross-validation. For prospective experimental validation, HTS-Oracle v2 was applied to an 8960-compound Enamine Protein Mimetic Library, selecting only 25 compounds per target for experimental testing using temperature-related intensity change (TRIC) technology, a 99.7% reduction in screening burden. HTS-Oracle v2 identified 4, 5, 4, and 6 validated binders from 25 prospectively selected compounds per target, corresponding to validated hit rates of 16%, 20%, 16%, and 24%, respectively. Notably, 67–80% of all experimentally confirmed hits across the full 8960-compound library were captured within just 25 model-selected compounds per target. These results establish HTS-Oracle v2 as an efficient platform for AI-guided prospective hit discovery across immunotherapy targets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Small Molecule LibrariesHigh-Throughput Screening AssaysDrug DiscoveryArtificial IntelligenceHumans

Substanzen

Small Molecule Libraries

Autor:innen und Institutionen

  • Department of Radiology, Molecular Imaging Innovations Institute (MI3), Weill Cornell Medicine, New York, New York10065, United States.

ORCID-Profile: Moustafa T Gabr

Zitieren

APA

Abdel-Rahman, S. A., & Gabr, M. T. (2026). HTS-Oracle v2: Prospective Ai-Guided Discovery and Experimental Validation of Small Molecule Modulators Across Multiple Targets. Journal of Chemical Information and Modeling, 66(15), 8998-9008. https://doi.org/10.1021/acs.jcim.6c01522

Vancouver

Abdel-Rahman SA, Gabr MT. HTS-Oracle v2: Prospective Ai-Guided Discovery and Experimental Validation of Small Molecule Modulators Across Multiple Targets. Journal of Chemical Information and Modeling. 2026;66(15):8998-9008. doi:10.1021/acs.jcim.6c01522

BibTeX
@article{AbdelRahman2026,
  author = {Abdel-Rahman, Somaya A and Gabr, Moustafa T},
  title = {HTS-Oracle v2: Prospective Ai-Guided Discovery and Experimental Validation of Small Molecule Modulators Across Multiple Targets},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {15},
  pages = {8998--9008},
  doi = {10.1021/acs.jcim.6c01522}
}
Kostenlos starten →