Screening and Evaluation of Computationally Predicted JAK1-Binding Candidates from Multi-Source Chemical Space Using Deep Learning and Generative Models
Pharmaceuticals · 13.11.2026 · 19 (11) · 1800
DOI: 10.3390/ph19111800 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pharmaceuticals, online erschienen am 13.11.2026. Verfasst von Shiying Li und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Background/Objectives: Janus kinase 1 (JAK1) is a key mediator in inflammatory and autoimmune signaling pathways and represents a validated therapeutic target. Despite the availability of several JAK inhibitors, challenges in safety and efficacy persist, necessitating further computational prioritization of candidate molecules.
Methods
We developed an integrated virtual screening workflow combining ensemble deep learning scoring (KPGT, KarmaDock, DrugCLIP), ADMET-AI filtering, and AutoDock Vina (v1.2.3) docking. The workflow was applied to the NPBS Atlas natural-product database and to molecules generated by 3DSMILES-GPT. Selected candidates were further evaluated by molecular dynamics simulations, DFT calculations, and synthetic accessibility assessment, with Filgotinib used as a reference compound.
Results
Three natural-product-derived and three AI-generated molecules were prioritized. Among them, the MM-PBSA-estimated binding free energies were −26.251 kcal/mol for NPBS_111591, −19.858 kcal/mol for 3DSMILES_17365, and −19.593 kcal/mol for 3DSMILES_38767, compared with −29.253 kcal/mol for the reference compound Filgotinib. These MM-PBSA values were obtained under the same computational protocol and can provide relative computational comparisons, but pharmacological potency still requires validation by IC50 or biochemical binding assays.
Conclusions
The study prioritizes computationally predicted JAK1-binding candidates and provides a multi-stage in silico workflow for further experimental evaluation.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, S., Li, J., Galindo, V. H., Xing, S., & Han, W. (2026). Screening and Evaluation of Computationally Predicted JAK1-Binding Candidates from Multi-Source Chemical Space Using Deep Learning and Generative Models. Pharmaceuticals, 19(11), 1800. https://doi.org/10.3390/ph19111800
Vancouver
Li S, Li J, Galindo VH, Xing S, Han W. Screening and Evaluation of Computationally Predicted JAK1-Binding Candidates from Multi-Source Chemical Space Using Deep Learning and Generative Models. Pharmaceuticals. 2026;19(11):1800. doi:10.3390/ph19111800
BibTeX
@article{Li2026,
author = {Li, Shiying and Li, Jing and Galindo, Vivian Huerta and Xing, Shu and Han, Weiwei},
title = {Screening and Evaluation of Computationally Predicted JAK1-Binding Candidates from Multi-Source Chemical Space Using Deep Learning and Generative Models},
journal = {Pharmaceuticals},
year = {2026},
volume = {19},
number = {11},
pages = {1800},
doi = {10.3390/ph19111800}
}
EUVIMED