aaanalysis.AnnotationPreprocessor.ingest

AnnotationPreprocessor.ingest(df_user=None)

Ingest a user / predictor annotation table into df_annot.

Every ingested feature_type is treated as a 'Functional sites' key; unknown keys auto-register (num_dims=1, identity normalization) unless previously registered via register_feature().

Parameters:

df_user (pd.DataFrame) – Must contain protein_id, start (1-based position), and feature_type columns. Optional: end (defaults to start), source (defaults to 'user'), score (defaults to 1.0, must lie in [0, 1]), aa (expected residue; '' disables the encode-time guard for that row).

Returns:

df_annot – Canonical per-residue annotation schema, category='Functional sites' for every row.

Return type:

pd.DataFrame

Raises:

ValueError – On missing required columns or out-of-range scores.