scROSHI: robust supervised hierarchical identification of single cells
OPEN ACCESS
Loading...
Author / Producer
Date
2023-06
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
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.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
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
09671 - Boeva, Valentina / Boeva, Valentina
09735 - Bodenmiller, Bernd / Bodenmiller, Bernd
Notes
Authors on behalf of the Tumor Profiler Consortium