Bases: BaseProcessor

Processor for URSA-HD annotations.

URSA-HD provides expert-curated annotations for GEO samples including disease (MESH → MONDO), tissue (GSE-level + description-based), age, and sex extracted from the GEO Sample Description field.

process(output_dir, **kwargs)

Process the URSA-HD CSV into standardized sample annotations.

Parameters:
  • output_dir (Path) –

    Directory where the processed parquet file will be written.

  • **kwargs (Any, default: {} ) –

    input_path (Path | str) — override the default URSA-HD CSV input path (defaults to URSAHD_CSV from config).
Returns:
  • DataFrame –

    Standardized annotations with columns sample_id, annotation_type, term_id, term_label, and ecode.

validate(data)

Validate processed URSA-HD data.

Parameters:
  • data (DataFrame) –

    Processed annotations DataFrame to validate.
Returns:
  • bool –

    True if validation passes.
Raises: