peppro/peppro_input_schema.yaml at master · databio/peppro · 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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
description: A PEP for nascent RNA samples for the PEPPRO pipeline.
imports:
 - http://schema.databio.org/pep/2.0.0.yaml
properties:
  samples:
    type: array
    items:
      type: object
      properties:
        sample_name:
          type: string
          description: "Name of the sample"
        organism:
          type: string
          description: "Organism"
        protocol:
          type: string
          description: "Specifies whether the sample is pro-seq or gro-seq"
          enum: ["PRO", "pro", "PRO-SEQ", "PRO-seq", "proseq", "PROSEQ", "GRO", "gro", "groseq", "GROSEQ", "GRO-SEQ", "GRO-seq"]
        genome:
          type: string
          description: "Refgenie genome registry identifier"
        prealignment_names:
          type: ["string", "array"]
          description: "Refgenie genome registry identifiers for prealignment genomes"
        prealignment_index:
          type: ["string", "array"]
          description: "Prealignment genome name and bowtie2 index path pairs (e.g. rCRSd=/path/to/index)"
        read_type:
          type: string
          description: "Is this single or paired-end data?"
          enum: ["SINGLE", "single", "PAIRED", "paired"]
        read1:
          type: string
          description: "Fastq file for read 1"
        read2:
          type: string
          description: "Fastq file for read 2 (for paired-end experiments)"
        umi_len:
          type: string
          description: "Length of the Unique Molecular Identifier, if any"
        max_len:
          type: string
          description: "Specify the maximum read length to trim all reads to"
        adapter:
          type: string
          description: "Specify the adapter removal tool"
          enum: ["cutadapt", "fastp"]
        dedup:
          type: string
          description: "Specify the read deduplication tool (only if UMI is present)"
          enum: ["seqkit", "fqdedup"]
        trimmer:
          type: string
          description: "Specify the read trimming tool"
          enum: ["seqtk", "fastx"]
        TSS_name:
          type: string
          description: "TSS annotation file (by default uses Refgenie refgene_anno asset)"
        pi_tss:
          type: string
          description: "Pause index TSS annotation file (by default uses Refgenie ensembl_gft asset)"
        pi_body:
          type: string
          description: "Pause index gene body annotation file (by default uses Refgenie ensembl_gft asset)"
        pre_name:
          type: string
          description: "Premature mRNA annotation file (by default uses Refgenie refgene_anno asset)"
        anno_name:
          type: string
          description: "Genomic partitions annotation file (by default uses Refgenie asset)"
        intron_name:
          type: string
          description: "Introns annotation file (by default uses Refgenie refgene_anno asset)"
        exon_name:
          type: string
          description: "Exons annotation file (by default uses Refgenie refgene_anno asset)"
        search_file:
          type: string
          description: "GenomeTools Tallymer read-length matched index search file (by default uses Refgenie asset)"
        sob:
          type: ["boolean", "string"]
          description: "Use seqOutBias to generate signal tracks"
        scale:
          type: ["boolean", "string"]
          description: "Scale signal tracks"
        coverage:
          type: ["boolean", "string"]
          description: "Report library complexity using coverage: reads / (bases in genome / read length)"
        keep:
          type: ["boolean", "string"]
          description: "Keep prealignment BAM files"
        noFIFO:
          type: ["boolean", "string"]
          description: "Do NOT use named pipes during prealignments"
        complexity:
          type: ["boolean", "string"]
          description: "Disable library complexity calculation (faster)"
        prioritize:
          type: ["boolean", "string"]
          description: "Plot cFRiF/FRiF using mutually exclusive priority ranked features based on the order of feature appearance in the feature annotation asset"
        config_file:
          type: string
          description: "Path to a custom pipeline configuration file (peppro.yaml)"
      required:
        - sample_name
        - protocol
        - read1
        - genome
      files:
        - read1
        - read2
      required_files:
        - read1
required:
  - samples