Peer-reviewedCC BY 4.0Scientific Reports
An accuracy and calibration benchmark of scGPT pipelines and matched classical models for cell type annotation
Related
- Diagnostic probes reveal shortcuts induced by the benchmark protocol in vision-language model annotation pipelines for video-based self-harm detection
- Cell-type separability predicts annotation accuracy and outweighs algorithm choice: a factorial benchmark across seven scRNA paradigms
- FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors
- scBOA: Bayesian optimization of single-cell analysis pipelines for robust annotation and discovery
- SCADA-based multiobjective calibration of hydraulic models for multi-fluid petroleum pipelines
BibTeX
@article{khosravi2026accuracy,
title = {{An accuracy and calibration benchmark of scGPT pipelines and matched classical models for cell type annotation}},
author = {Alireza Khosravi and Arshia Khosravi and Kamil Łangowski and Michał Sieczczyński and Krzysztof Pastuszak and Anna Supernat and Anna J. Żaczek},
journal = {Scientific Reports},
year = {2026},
month = nov,
doi = {10.1038/s41598-026-77853-3},
url = {https://www.nature.com/articles/s41598-026-77853-3},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - An accuracy and calibration benchmark of scGPT pipelines and matched classical models for cell type annotation
AU - Alireza Khosravi
AU - Arshia Khosravi
AU - Kamil Łangowski
AU - Michał Sieczczyński
AU - Krzysztof Pastuszak
AU - Anna Supernat
AU - Anna J. Żaczek
PY - 2026
DA - 2026/11/05
JO - Scientific Reports
DO - 10.1038/s41598-026-77853-3
UR - https://www.nature.com/articles/s41598-026-77853-3
SN - 2045-2322
ER -