Data

Classes and utilities for manipulating genomics data.

Fold intervals

data.fold_intervals.Subset(value)	Subset of the data.
data.fold_intervals.get_all_folds()	Returns the names of all data folds.
data.fold_intervals.get_fold_names(...)	Returns the names of the folds for a given model version and subset.
data.fold_intervals.get_fold_intervals(...)	Returns the intervals for a given model version and subset.

Genome

data.genome.Strand(value)	Represents the strand of a DNA sequence.
data.genome.VariantFormat(value)	A format for parsing a string into a Variant object.
data.genome.Interval(chromosome, start, end)	Represents a genomic interval.
data.genome.Variant(chromosome, position, ...)	Represents a genomic variant/mutation.
data.genome.Junction(chromosome, start, end)	Represents a splice junction.
data.genome.normalize_variant(variant, extractor)	Normalize a Variant by left-aligning the reference and alternate bases.
data.genome.intersect_intervals(lhs, rhs, *)	Generates the intersection of two interval sets.
data.genome.merge_overlapping_intervals(...)	Merges overlapping intervals and returns a sorted list.
data.genome.union_intervals(lhs, rhs, *[, ...])	Generates the union of two interval sets.

Gene annotation

data.gene_annotation.TranscriptType(value)	Valid Transcript types available in the GENCODE GTF.
data.gene_annotation.extract_tss(gtf[, feature])	Extract transcription start sites (TSS) from a DataFrame.
data.gene_annotation.filter_transcript_type(gtf)	Filter GTF entries by transcript types.
data.gene_annotation.filter_protein_coding(gtf)	Filter GTF entries to protein-coding transcripts or genes.
data.gene_annotation.filter_to_longest_transcript(gtf)	Filter GTF entries to only the longest transcript per gene.
data.gene_annotation.filter_to_mane_select_transcript(gtf)	Filter GTF entries to only the MANE select transcript.
data.gene_annotation.filter_transcript_support_level(...)	Filter GTF to only transcripts with specific GENCODE support levels.
data.gene_annotation.get_gene_interval(gtf)	Returns a stranded genome.Interval given a gene identifier.
data.gene_annotation.get_gene_intervals(gtf)	Returns stranded genome.Interval objects for the given identifiers.

FASTA Extractor

io.fasta.FastaExtractor(fasta_path)	FASTA file extractor.
io.fasta.reverse_complement(sequence)	Returns the reverse complement of a DNA sequence string.

Junction data

data.junction_data.JunctionData(junctions, ...)	Container for storing splice junction data.
data.junction_data.get_junctions_to_plot(*, ...)	Gets a list of junctions to plot.

Ontology

data.ontology.OntologyType(value)	Supported ontology types.
data.ontology.OntologyTerm(type, id)	A single biological ontology term.
data.ontology.from_curie(ontology_curie)	Creates an OntologyTerm from a CURIE.
data.ontology.from_curies(ontology_curies)	Creates a list of OntologyTerm objects from a list of CURIEs.

Track data

data.track_data.AggregationType(value)	Aggregation types for downsampling/upsampling track resolutions.
data.track_data.TrackData(values, metadata)	Container for storing track values and metadata.
data.track_data.concat(track_datas[, ...])	Concatenates multiple TrackData objects along the track dimension.
data.track_data.interleave(track_datas, ...)	Interleaves multiple TrackData objects by alternating rows.

Gene expression data

data.gene_expression_data.GeneExpressionData(...)	Container for storing gene expression data.
data.gene_expression_data.concat(...[, ...])	Concatenates multiple GeneExpressionData objects along the track dimension.

Transcript

data.transcript.Transcript(exons[, cds, ...])	Represents transcript object containing attributes from a GTF file.
data.transcript.TranscriptExtractor(gtf_df)	Transcript extractor from a GTF DataFrame.