PSGRN: Gene regulatory network inference from single-cell perturbational data through self-training with synthetic gold standards
Science Advances · 2026
DOI: 10.1126/sciadv.aeb3376 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, 2026. Verfasst von Xinhan Song und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational Medicine and Bioinformatics, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Single-Cell Analysis, Computational Biology, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Gene regulatory networks (GRNs) are essential for understanding how genes coordinate cellular processes. Large-scale single-cell perturbation studies now offer powerful opportunities for GRN inference, yet many state-of-the-art (SOTA) methods fail to fully use interventional information. We present PSGRN, a top-performing method in the CausalBench Challenge, which integrates interventional and observational single-cell RNA sequencing data using a self-training framework with synthetic gold standards. Across eight datasets and six evaluation metrics, PSGRN consistently outperformed existing approaches. With interventional data, it achieved up to 43% higher Wasserstein distances and the lowest false omission rate in K562 compared with recent SOTA methods. Using experimentally validated regulatory interactions, PSGRN showed up to 30% gains in precision and over 100% gains in recall. These results highlight PSGRN’s versatility and scalability, establishing it as a robust tool for GRN inference and biological discovery from single-cell data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computational Medicine and Bioinformatics, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA.
- College of Literature, Science, and The Arts, University of Michigan, Ann Arbor, MI, USA.
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
ORCID-Profile: Xinhan Song, Kaiwen Deng, Mandy Chen, Yuanfang Guan
Förderung
- NIGMS NIH HHS
- National Institutes of Health
Zitieren
APA
Song, X., Deng, K., Chen, M., & Guan, Y. (2026). PSGRN: Gene regulatory network inference from single-cell perturbational data through self-training with synthetic gold standards. Science Advances. https://doi.org/10.1126/sciadv.aeb3376
Vancouver
Song X, Deng K, Chen M, Guan Y. PSGRN: Gene regulatory network inference from single-cell perturbational data through self-training with synthetic gold standards. Science Advances. 2026. doi:10.1126/sciadv.aeb3376
BibTeX
@article{Song2026,
author = {Song, Xinhan and Deng, Kaiwen and Chen, Mandy and Guan, Yuanfang},
title = {PSGRN: Gene regulatory network inference from single-cell perturbational data through self-training with synthetic gold standards},
journal = {Science Advances},
year = {2026},
doi = {10.1126/sciadv.aeb3376}
}
EUVIMED