.png){kind=icon}
.png){kind=icon}
Return
Large language models advance single-cell transcriptomics in major depressive disorder
.png){kind=icon}
OA
AI
S
J
J
Y
DOI：10.1038/s41398-026-04279-w.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Major depressive disorder (MDD) exhibits substantial heterogeneity, posing challenges for its diagnosis and treatment. Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for delineating cellular programs in neuronal and immune populations implicated in MDD pathogenesis. Advances in large language models (LLMs) are now enhancing single-cell analysis by improving annotation, clustering, regulatory network inference, and in silico perturbation to prioritize druggable targets. Integration with proteomic, metabolomic, epigenomic, and spatial data further clarifies disease mechanisms and potential biomarkers. Key challenges including data heterogeneity, model interpretability, computational scale, and ethical data usage remain to be addressed through rigorous benchmarks and validation to accelerate translation. Collectively, integration of LLMs with single-cell technologies provides a framework for more precise, cell-resolved hypothesis generation in MDD, while prospective validation of patient-level clinical utility remains a key next step.
Journal
IF:
6.2
Papers:
5.5K
Citations:
2.4W
Organization
Cited Papers