scTCR-Guide: Processed Single-Cell T-Cell Receptor Datasets

A 443.7 MB processed data bundle for scTCR-Guide, containing gene expression and cell metadata for CD8 T-cells. The archive includes a training/validation/test bundle and three independent external test bundles from GSE269981, GSE277428, and GSE273019. It was authored by Haijun Tang and last updated on May 14, 2026.

Use Cases

• Training machine learning models for T-cell receptor sequence analysis based on the 1,024-gene expression profiles.
• Benchmarking model performance on independent external test datasets based on the three provided GSE bundles.
• Reproducing computational analyses from the associated manuscript based on the provided expression matrices and cell metadata.

Strengths

• Includes three independent external test datasets (GSE269981, GSE277428, GSE273019) for robust validation.
• Provides a complete bundle with manifest, data dictionary, and checksums for reproducibility.
• Focuses on a specific, biologically relevant cell type (CD8 T-cells).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific modeling tasks.

Provenance

Source

figshare

Collection Method

Processed from original single-cell RNA sequencing studies; specific methods are not detailed.

Freshness

Last updated 2026-05-14 05:48:07