Spatial Transcriptomics Pre-training Corpus for Foundation Model

SToCorpus-88M is a pre-training dataset used for the SToFM multi-scale foundation model for spatial transcriptomics. The dataset is associated with a research paper and model code published on GitHub. Specific details on data volume, structure, and features are not provided in the input.

Use Cases

• Pre-training foundation models for spatial transcriptomics analysis, as referenced in the associated paper.
• Benchmarking multi-scale genomic models using the corpus defined for SToFM.
• Supporting research in bioinformatics and multimodal genomics as indicated by the dataset tags.

Strengths

• Dataset is explicitly linked to a peer-reviewed research paper (arXiv:2507.11588).
• Associated with a publicly available model implementation on GitHub.
• Tagged for relevance to Foundation Model and Spatial Transcriptomics research areas.

Limitations

• No information is provided on the dataset's size, number of samples, features, or internal structure.
• The source and collection methodology for the underlying data are not described.
• Potential for specialized domain knowledge prerequisites in spatial transcriptomics and genomics.

Provenance

Source

Author is listed as 'Toycat'; organization is unknown.

Collection Method

Described as the pre-training dataset for the SToFM model; specific gathering method is null.

Freshness

Last updated metadata indicates a date of 2025-12-05.