Work

Visual LLM-guided consensus spatial domain detection with L-STAR

Year: 2026

Type: article

Abstract: ABSTRACT Spatial domain detection is a central task in spatial transcriptomics, yet existing methods exhibit highly variable performance across datasets. We introduce L-STAR, a visual LLM-guided, consensus-based framework that leverages the visual reasoning capacity of large language models to adaptively rank and integrate spatial domain detection methods. L-STAR achieves robust and consistently improved performance, outperforming single spatial domain detection methods across diverse datasets.

Source: Nature Communications

DOI: 10.1038/s41467-026-78923-w

Authors: Changyue Zhao, Zhicheng Ji

Institutions: Duke University, Duke Medical Center

Language: English

Topic: Single-cell and spatial transcriptomics

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $6,990

Funders: Division of Intramural Research, National Institute of Allergy and Infectious Diseases, National Institutes of Health, National Institute of General Medical Sciences