dataloader.yaml

defined_as: dataloader.SeqDataset
args:
  intervals_file:
    doc: bed3 file with `chrom start end id score strand`
    example: example_files/intervals.tsv
  fasta_file:
    doc: Reference genome sequence
    example: example_files/hg38_chr22.fa
  target_file:
    doc: path to the targets (.tsv) file
    optional: True
  use_linecache:
    doc: if True, use linecache https://docs.python.org/3/library/linecache.html to access bed file rows
    optional: True
info:
  authors:
      - name: Lara Urban
        github: LaraUrban
      - name: Ziga Avsec
        github: avsecz
  doc: Dataloader for the DeepSEA model.
dependencies:
  conda:
    - python
    - numpy
    - pandas
    - cython
  pip:
    - cython
    - pybedtools
output_schema:
  inputs:
    name: input
    shape: (1000, 4)
    special_type: DNASeq
    doc: DNA sequence
    associated_metadata: ranges
  targets:
    name: epigen_mod
    shape: (1, )
    doc: Specific epigentic feature class (multi-task binary classification)
  metadata:
    ranges:
      type: GenomicRanges
      doc: Ranges describing inputs.seq