.png){kind=icon}
.png){kind=icon}
Return
CellTune: an integrative software for accurate cell classification in spatial proteomics
.png){kind=icon}
PRE
AI
Y
D
E
S
N
N
T
R
C
N
E
D
I
O
R
L
DOI：10.1038/s41592-026-03162-2.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spatial proteomics measures multiple proteins in situ, capturing tissue complexity. However, cell classification in densely packed tissues remains challenging because of the lack of efficient classification algorithms, annotation tools and high-quality labeled datasets to benchmark computational methods. We introduce CellTune, an integrated software for analysis of large spatial proteomics datasets, which streamlines precise cell classification through an optimized human-in-the-loop active learning workflow. It advances core capabilities for analysis of large datasets with an intuitive and code-free interface. To evaluate CellTune, we created CellTuneDepot, a resource of 40,000 manually annotated cells and 3.5 million high-quality labeled cells across 60 cell types. CellTune outperforms alternative methods, achieving accuracy comparable to human performance while enabling increased classification resolution and discovery of novel cell types. Together, CellTune and CellTuneDepot provide researchers with a tool for state-of-the-art classification accuracy and resolution at scale to drive biological insights. CellTune enables high precision analysis of spatial proteomics datasets through a human-in-the-loop active learning workflow.
Journal
IF:
32.1
Papers:
7.2K
Citations:
12.7W
Organization
Cited Papers