scROSHI: robust supervised hierarchical identification of single cells


Loading...

Date

2023-06

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Identifying cell types based on expression profiles is a pillar of single cell analysis. Existing machine-learning methods identify predictive features from annotated training data, which are often not available in early-stage studies. This can lead to overfitting and inferior performance when applied to new data. To address these challenges we present scROSHI, which utilizes previously obtained cell type-specific gene lists and does not require training or the existence of annotated data. By respecting the hierarchical nature of cell type relationships and assigning cells consecutively to more specialized identities, excellent prediction performance is achieved. In a benchmark based on publicly available PBMC data sets, scROSHI outperforms competing methods when training data are limited or the diversity between experiments is large.

Publication status

published

Editor

Book title

Volume

5 (2)

Pages / Article No.

Publisher

Oxford University Press

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

02892 - NEXUS Personalized Health / NEXUS Personalized Health check_circle
09671 - Boeva, Valentina / Boeva, Valentina check_circle
09735 - Bodenmiller, Bernd / Bodenmiller, Bernd check_circle

Notes

Authors on behalf of the Tumor Profiler Consortium

Funding

Related publications and datasets