GRIT: Graph-Regularized Logit Refinement for Zero-shot Cell Type Annotation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912889296650240 |
|---|---|
| author | Hu, Tianxiang Zhou, Chenyi Liu, Jiaxiang Wang, Jiongxin Chen, Ruizhe Xia, Haoxiang Wang, Gaoang Wu, Jian Liu, Zuozhu |
| author_facet | Hu, Tianxiang Zhou, Chenyi Liu, Jiaxiang Wang, Jiongxin Chen, Ruizhe Xia, Haoxiang Wang, Gaoang Wu, Jian Liu, Zuozhu |
| contents | Cell type annotation is a fundamental step in the analysis of single-cell RNA sequencing (scRNA-seq) data. In practice, human experts often rely on the structure revealed by principal component analysis (PCA) followed by $k$-nearest neighbor ($k$-NN) graph construction to guide annotation. While effective, this process is labor-intensive and does not scale to large datasets. Recent advances in CLIP-style models offer a promising path toward automating cell type annotation. By aligning scRNA-seq profiles with natural language descriptions, models like LangCell enable zero-shot annotation. While LangCell demonstrates decent zero-shot performance, its predictions remain suboptimal. In this paper, we propose a principled inference-time paradigm for zero-shot cell type annotation (GRIT) which bridges the scalability of pre-trained foundation models with the structural robustness relied upon in human expert annotation workflows. Specifically, we enforce local consistency of the zero-shot CLIP logits over the task-specific PCA-based $k$-NN graph. We evaluate our approach on 14 annotated human scRNA-seq datasets from 4 distinct studies, spanning 11 organs and over 200,000 single cells. Our method consistently improves zero-shot annotation accuracy, achieving accuracy gains of up to 10\%. Further analysis showcase the mechanism by which GRIT effectively propagates correct signals through the graph, pulling back mislabeled cells toward more accurate predictions. The method is training-free, model-agnostic, and serves as a simple yet effective plug-in for enhancing zero-shot cell type annotation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GRIT: Graph-Regularized Logit Refinement for Zero-shot Cell Type Annotation Hu, Tianxiang Zhou, Chenyi Liu, Jiaxiang Wang, Jiongxin Chen, Ruizhe Xia, Haoxiang Wang, Gaoang Wu, Jian Liu, Zuozhu Genomics Machine Learning Cell type annotation is a fundamental step in the analysis of single-cell RNA sequencing (scRNA-seq) data. In practice, human experts often rely on the structure revealed by principal component analysis (PCA) followed by $k$-nearest neighbor ($k$-NN) graph construction to guide annotation. While effective, this process is labor-intensive and does not scale to large datasets. Recent advances in CLIP-style models offer a promising path toward automating cell type annotation. By aligning scRNA-seq profiles with natural language descriptions, models like LangCell enable zero-shot annotation. While LangCell demonstrates decent zero-shot performance, its predictions remain suboptimal. In this paper, we propose a principled inference-time paradigm for zero-shot cell type annotation (GRIT) which bridges the scalability of pre-trained foundation models with the structural robustness relied upon in human expert annotation workflows. Specifically, we enforce local consistency of the zero-shot CLIP logits over the task-specific PCA-based $k$-NN graph. We evaluate our approach on 14 annotated human scRNA-seq datasets from 4 distinct studies, spanning 11 organs and over 200,000 single cells. Our method consistently improves zero-shot annotation accuracy, achieving accuracy gains of up to 10\%. Further analysis showcase the mechanism by which GRIT effectively propagates correct signals through the graph, pulling back mislabeled cells toward more accurate predictions. The method is training-free, model-agnostic, and serves as a simple yet effective plug-in for enhancing zero-shot cell type annotation. |
| title | GRIT: Graph-Regularized Logit Refinement for Zero-shot Cell Type Annotation |
| topic | Genomics Machine Learning |
| url | https://arxiv.org/abs/2508.04747 |