Article

When Simpler Models Win: A Calibration Benchmark of scGPT for Cell-Type Annotation

2026-07-20

Abstract excerpt

<title>Abstract</title> <p>Background. Single-cell large language models (scLLMs) such as scGPT promise transferable representations for cell-type annotation in single-cell RNA sequencing (scRNA-seq), but their statistical calibration under large-scale supervised within-atlas evaluation is largely unexamined. Poorly calibrated confidence scores can mislead downstream biological interpretation, particularly in cli...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 98a144b4-c500-5d58-a62f-c23a30886c68
DOI: 10.21203/rs.3.rs-10152510/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

When Simpler Models Win: A Calibration Benchmark of scGPT for Cell-Type AnnotationDOI 10.21203/rs.3.rs-10152510/v1Read

RNABag: A Generalizable Transcriptome Foundation Model for Precision Oncology across Biopsy ModalitiesSemantic proximity Read

scBERT as a Large-scale Pretrained Deep Language Model for Cell Type Annotation of Single-cell RNA-seq DataSemantic proximity Read

scGenAI: A generative AI platform with biological context embedding of multimodal features enhances single cell state classificationSemantic proximity Read

Single-cell foundation models reveal context-sensitive cancer programmes under subtype shiftSemantic proximity Read

Species-specific small models for cell type classification approach the performance of large single cell foundation modelsSemantic proximity Read

Scaling cross-tissue single-cell annotation modelsSemantic proximity Read

Gene-Family Encoding Boosts Domain-Adapted Single-Cell Language ModelsSemantic proximity Read

Generative pretraining from large-scale transcriptomes: Implications for single-cell deciphering and clinical translationSemantic proximity Read

Benchmarking single cell transcriptome matching methods for incremental growth of cell atlasesSemantic proximity Read

Cross-Tissue Generalization of Rare Cell-Type Representations in Single-Cell Foundation Models: A Benchmark Using Public Reference AtlasesSemantic proximity Read

Harnessing the Power of Single Cell Large Language Models with Parameter Efficient Fine-Tuning using scPEFTSemantic proximity Read

CancerFoundation: A single-cell RNA sequencing foundation model to decipher drug resistance in cancerSemantic proximity Read