Deng Reads: Single-Cell RNA Sequencing Data with Cell Type Labels

Single-cell RNA sequencing data transposed and annotated with cell type labels from the original source code. The dataset was prepared by authors Deng, Ramskold, Reinius, and Sandberg and is shared under a CC-BY-4.0 license on OpenML. Column names were changed to a numerical order to avoid issues with name length.

Use Cases

• Cell type classification based on annotated cell_type1 and cell_type2 labels.
• Benchmarking tabular classification algorithms on biological data.
• Analyzing gene expression patterns across different cell types.
• Developing feature selection methods for high-dimensional genomic data.

Strengths

• Includes explicit cell type annotations (cell_type1, cell_type2) derived from the original source code.
• Shared under a permissive CC-BY-4.0 license, facilitating reuse.
• Column names were standardized to a numerical order to avoid technical issues.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and last update date are unknown, limiting suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Deng, Q., Ramskold, D., Reinius, B. & Sandberg

Collection Method

Data was transposed and annotated according to the original source code.

Time Range

null

Freshness

Last updated date is unknown; freshness unverified.

Geography

null