models/FactorNet/CEBPB/meta_Unique35_DGF/dataloader.yaml at master · kipoi/models · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
type: Dataset
defined_as: dataloader.py::SeqDataset
args:
  intervals_file:
    doc: bed3 file with `chrom start end id score strand`
    example:
      md5: a060800e9c7ecccc2fc7d212ea6e6a61
      url: https://zenodo.org/record/1466084/files/CEBPB-meta_Unique35_DGF-example_files-intervals.bed?download=1
  fasta_file:
    doc: Reference genome sequence
    example:
      md5: b0f5cdd4f75186f8a4d2e23378c57b5b
      url: https://zenodo.org/record/1466084/files/CEBPB-meta_Unique35_DGF-example_files-hg38_chr22.fa?download=1
  dnase_file:
    doc: DNase bigwig file
    example:
      md5: 9e7d6fbd169867dded34840f7f3be15c
      url: https://zenodo.org/record/1466084/files/CEBPB-meta_Unique35_DGF-example_files-dnase_synth.chr22.bw?download=1
  cell_line:
    doc: Cell type as a string.
    example: PC-3
    optional: True
  RNAseq_PC_file:
    doc: file path to a RNAseq PC file computed by https://github.com/davidaknowles/tf_net/blob/master/gene_expression_pca.R. See https://github.com/uci-cbcl/FactorNet/blob/master/data/README.md.
    optional: True
  mappability_file:
    doc: USCS mappability track - http://hgdownload.cse.ucsc.edu/goldenpath/hg19/encodeDCC/wgEncodeMapability/wgEncodeDukeMapabilityUniqueness35bp.bigWig. by deafult, provide this file with the dataloader, download in background
    example:
      url: https://s3.eu-central-1.amazonaws.com/kipoi-models/dataloader_files/FactorNet/dataloader_files/wgEncodeDukeMapabilityUniqueness35bp.chr22.bigWig
      md5: 912e1bb77fb67c1a792ac4a05d9416f9
    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: Ziga Avsec
        github: avsecz
  doc: Dataloader for the FactorNet model.
dependencies:
  conda:
    - bioconda::bedtools
    - bioconda::pybedtools
    - bioconda::genomelake==0.1.4
    - numpy
    - cython
output_schema:
  inputs:
    - name: seq
      shape: (1002, 6)
      doc: DNA sequence and other big-wig channels (mappability and DNase-seq)
      associated_metadata: ranges
    - name: seq_rc
      shape: (1002, 6)
      doc: Reverse-complemented DNA sequence and reversed other bigwig channels (mappability and DNase-seq)
      associated_metadata: ranges_rc
    - name: meta_features
      shape: (8,)
      doc: First 8 RNAseq principle-components for the tissue.
  targets:
    name: is_binding_site
    shape: (1,)
    doc: TF binding class
    column_labels: tasks.txt
  metadata:
    ranges:
      type: GenomicRanges
      doc: Ranges describing inputs.seq
    ranges_rc:
      type: GenomicRanges
      doc: Ranges describing inputs.seq_rc