torchcell.verification.verify_expression_dataset

verify_expression_dataset(records: Sequence[dict[str, Any]], *, dataset_name: str, provenance: Provenance, expected_count: int) → VerificationReport[source]

Run the L0-L4 record-level gate for one microarray expression dataset.

Parameters:

  • records – the per-LMDB-entry dicts (experiment/reference/publication).

  • dataset_name – dataset identity for the report.

  • provenance – where the records came from.

  • expected_count – the record-count oracle (e.g. Sameith DM=72, SM=82, Kemmeren=1450).

Returns:

A VerificationReport carrying the L0-L3 results. L4 (cross-source) is asserted across datasets by the caller, not here.