.png){kind=icon}
.png){kind=icon}
Return
ProtoCloud: A prototypical self-explaining model for single-cell analysis
.png){kind=icon}
OA
AI
DOI：10.1016/j.xgen.2026.101217.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Accurate and efficient annotation of single-cell data, including rare cell types • A disentangled latent space separates biological identity from other variations • Built-in uncertainty estimates identify and correct potential misannotations • Instant explainability reveals genes driving cell type classification
Keywords:
single-cell RNA sequencing
cell state
rare cell type
prototypical network
self-explaining model
disentanglement
layer-wise relevance propagation
prototypical relevance propagation
deep generative models
variational autoencoder
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.