GRIT: Graph-Regularized Logit Refinement for Zero-shot Cell Type Annotation

TL;DR

GRIT enhances zero-shot cell type annotation in scRNA-seq data by enforcing local consistency on CLIP logits over a PCA-based k-NN graph, significantly improving accuracy without additional training.

Contribution

Introduces a training-free, graph-based inference paradigm that improves zero-shot cell annotation accuracy by leveraging local consistency in existing foundation models.

Findings

Achieves up to 10% accuracy improvement across diverse datasets.

Effectively propagates correct labels through the k-NN graph.

Compatible as a plug-in with existing models for scalable annotation.

Abstract

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.