score_variant

score_variant#

DnaClient.score_variant(interval, variant, condition=None, variant_scorers=(), *, organism=Organism.HOMO_SAPIENS, cell_conditioning=None, cell_condition_name=None)[source]#

Generate variant scores for a single given DNA variant.

Parameters:

  • interval (Interval) – DNA interval to make prediction for.

  • variant (Variant) – DNA variant to make prediction for.

  • condition (ModelCondition | str | None (default: None)) – The condition or composite curie to generate the prediction for.

  • variant_scorers (Sequence[CenterMaskScorer | ContactMapScorer | GeneMaskLFCScorer | GeneMaskActiveScorer | GeneMaskSplicingScorer | MethylationScorer | PolyadenylationScorer | SpliceJunctionScorer] (default: ())) – Sequence of variant scorers to use for scoring. If no variant scorers are provided, the recommended variant scorers for the organism and conditioning type will be used.

  • organism (Organism (default: <Organism.HOMO_SAPIENS: 9606>)) – Organism to use for the prediction.

  • cell_conditioning (AnnData | None (default: None)) – Optional human single-cell raw UMI counts (AnnData, up to MAX_CONDITIONING_CELLS cells). Unlocks OutputType.SC_GENE_EXPRESSION_DENOISED (denoised single-cell gene expression; one channel per strand, in CPM).

  • cell_condition_name (str | None (default: None)) – Optional label for expression conditioning. When provided, the output track names are suffixed with this name and the biosample_name column is set in the var metadata. Must be provided when cell_conditioning is used.

Return type:

list[AnnData]

Returns:

List of AnnData variant scores.