JunctionData

class alphagenome.data.junction_data.JunctionData(junctions, values, metadata, interval=None, uns=None)

Container for storing splice junction data.

junctions

A numpy array representing the splice junctions.

values

A numpy array of floats representing the values associated with each junction for each track.

metadata

A pandas DataFrame containing metadata for each track.

interval

An optional Interval object representing the genomic region containing the junctions.

uns

An optional dictionary to store additional unstructured data.

Raises:

ValueError – If the number of tracks in values does not match the number of rows in metadata, or if metadata contains duplicate names.

Methods

filter_by_name(name)	Filters tracks by name.
filter_by_ontology(ontology_curie)	Filters tracks by ontology term.
filter_by_tissue(tissue)	Filters tracks by GTEx tissue type.
filter_to_negative_strand()	Filters junctions to the negative DNA strand.
filter_to_observed()	Filters tracks to observed tracks.
filter_to_positive_strand()	Filters junctions to the positive DNA strand.
filter_to_strand(strand)	Filters junctions to a specific DNA strand.
filter_tracks(mask)	Filters tracks by a boolean mask.
intersect_with_interval(interval)	Returns the intersection of the junctions and the interval.
normalize_values([total_k])	Normalizes the values by the k value.
with_metadata_column(name, value)	Returns a new JunctionData with an added/updated metadata column.
with_name_suffix(suffix)	Returns a new JunctionData with a suffix added to all track names.