Autozyme Datasets: Preprocessed Single-Cell RNA-Seq Data

Autozyme Datasets provides preprocessed single-cell RNA sequencing data for the AutoZyme project. The collection includes raw and fully processed count matrices in both Seurat (R) and Scanpy (Python) formats. The dataset was authored by elliotxie and last updated on Hugging Face in June 2026.

Use Cases

• Benchmarking single-cell analysis pipelines based on the provided preprocessed data.
• Comparing results between Seurat and Scanpy workflows using the parallel checkpoint files.
• Developing new clustering or dimensionality reduction methods using the provided leiden and PCA results.

Strengths

• Data is provided in two standard, interoperable formats (H5AD for Scanpy, RDS for Seurat).
• Includes fully preprocessed checkpoints with high-variance genes, PCA, neighbor graphs, and leiden clustering.
• Last updated on 2026-06-11, suggesting recent maintenance.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and dataset scale are unknown, which may limit suitability assessment.

Provenance

Source

Hugging Face user elliotxie.

Collection Method

Likely generated as part of the AutoZyme project's optimized pipelines.

Freshness

Last updated 2026-06-11 20:16:58.