TranscriptExtractor

TranscriptExtractor#

class alphagenome.data.transcript.TranscriptExtractor(gtf_df)[source]#

Transcript extractor from a GTF DataFrame.

Initializes the extractor from a GTF DataFrame.

Parameters:

gtf_df (DataFrame) – pd.DataFrame of GENCODE GTF entries containing transcript annotation. Must contain columns ‘Chromosome’, ‘Start’, ‘End’, ‘Strand’, ‘Feature’, and ‘transcript_id’.

Methods

cache_transcripts()

Speed up extract() by converting GTF to dictionary of Transcripts.

extract(interval)

Extract transcripts overlapping an interval.