astrocyte_pkg.yml 6.36 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
#
# metadata for the example astrocyte ChipSeq workflow package
#

# -----------------------------------------------------------------------------
# BASIC INFORMATION
# -----------------------------------------------------------------------------

# A unique identifier for the workflow package, text/underscores only
name: 'astrocyte_example'
# Who wrote this?
Peng Lian's avatar
Peng Lian committed
12
author: 'David Trudgian, Peng Lian'
13
14
15
16
17
18
19
20
# A contact email address for questions
email: 'biohpc-help@utsouthwestern.edu'
# A more informative title for the workflow package
title: 'Astrocyte Example ChIPSeq Workflow'
# A summary of the workflow package in plain text
description: |
  This is an example workflow package for the BioHPC astrocyte workflow system.
  It implements a simple ChIPSeq analysis workflow using BWA and MACS, plus a
Peng Lian's avatar
Peng Lian committed
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
  simple R Shiny visualization application. Please note that start from publish 
  version 0.0.8 and test version 0.0.1, this workflow will only support 
  Astrocyte 0.4.1 and above.

# The minimum Astrocyte version that requires to run this workflow. For old pipelines, which do not have this label 
# a default value of 0.3.1 will be assigned automatically. A request of minimum version less than 0.4.0 will be ignored.
minimum_astrocyte_version: '0.4.1'
# The Nextflow version that requires to run this workflow.  For old pipelines, which do not have this label 
# a default value of 0.31.0 will be assigned automatically. Please make sure the requested nextflow version is available
# in the module list.
nextflow_version: '21.04.1'
# (Optional) The Nextflow config file to use for this workflow. If provided, the file should exist in workflow/configs
nextflow_config: 'biohpc.config'
# The container to use for this workflow, none/singularity. If omitted, the default value 'none' will be used.
container: 'none'
# The version of singularity to use. This is required if container == 'singularity'
singularity_version: '3.5.3'
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

# -----------------------------------------------------------------------------
# DOCUMENTATION
# -----------------------------------------------------------------------------

# A list of documentation file in .md format that should be viewable from the
# web interface. These files are in the 'docs' subdirectory. The first file
# listed will be used as a documentation index and is index.md by convention
# To supply a title for documentation use a pair of [ 'filename', 'title' ]
documentation_files:
  - [ 'index.md', 'ChIPSeq Example' ]

# -----------------------------------------------------------------------------
# NEXTFLOW WORKFLOW CONFIGURATION
# -----------------------------------------------------------------------------

# Remember - The workflow file is always named 'workflow/main.f'
#            The workflow must publish all final output into $baseDir

# A list of clueter environment modules that this workflow requires to run.
# Specify versioned module names to ensure reproducability.
workflow_modules:
  - 'BWA/0.7.5'
  - 'picard/1.127'
  - 'macs/1.4.2'

Peng Lian's avatar
Peng Lian committed
64
65
66
# A list of container images requires to run this workflow.
# Specify full path and version names to ensure reproducability.
# This keyword is required when 'container' is specified in Astrocyte 0.4.1 and above
Peng Lian's avatar
Peng Lian committed
67
68
#workflow_containers:
#  -
Peng Lian's avatar
Peng Lian committed
69

70
71
72
73
74
75
76
77
78
79
80
81
# A list of parameters used by the workflow, defining how to present them,
# options etc in the web interface. For each parameter:
#
# REQUIRED INFORMATION
#  id:         The name of the parameter in the NEXTFLOW workflow
#  type:       The type of the parameter, one of:
#                string    - A free-format string
#                integer   - An integer
#                real      - A real number
#                file      - A single file from user data
#                files     - One or more files from user data
#                select    - A selection from a list of values
David Trudgian's avatar
David Trudgian committed
82
83
#                multiselect - One or more selections from a list of values
#
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
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
#  required:    true/false, must the parameter be entered/chosen?
#  description: A user friendly description of the meaning of the parameter
#
# OPTIONAL INFORMATION
#  default:   A default value for the parameter (optional)
#  min:       Minium value/characters/files for number/string/files types
#  max:       Maxumum value/characters/files for number/string/files types
#  regex:     A regular expression that describes valid entries / filenames
#
# SELECT TYPE
#  choices:   A set of choices presented to the user for the parameter.
#             Each choice is a pair of value and description, e.g.
# 
#             choices:
#               - [ 'myval', 'The first option']
#               - [ 'myval', 'The second option']
#
# NOTE - All parameters are passed to NEXTFLOW as strings... but they
#        are validated by astrocyte using the information provided above

workflow_parameters:

  - id: fastq
    type: files
    required: true
    description: |
      One or more input FASTQ files from a ChIPSeq experiment
    regex: ".*(fastq|fq)"
    min: 1

  - id: index
    type: select
    choices:
      - [ '/project/apps_database/iGenomes/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/genome.fa', 'UCSC hg38']
      - [ '/project/apps_database/iGenomes/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/genome.fa', 'UCSC hg19']
      - [ '/project/apps_database/iGenomes/Homo_sapiens/UCSC/hg18/Sequence/BWAIndex/genome.fa', 'UCSC hg18']
      - [ '/project/apps_database/iGenomes/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/genome.fa', 'UCSC mm10']
      - [ '/project/apps_database/iGenomes/Mus_musculus/UCSC/mm9/Sequence/BWAIndex/genome.fa', 'UCSC mm9']
    required: true
    description: |
      Reference genome for BWA alignment

# -----------------------------------------------------------------------------
# SHINY APP CONFIGURATION
# -----------------------------------------------------------------------------

# Remember - The vizapp is always 'vizapp/server.R' 'vizapp/ui.R'
#            The workflow must publish all final output into $baseDir

# Name of the R module that the vizapp will run against
David Trudgian's avatar
David Trudgian committed
134
vizapp_r_module: 'R/3.4.1-gccmkl'
135
136
137
138
139
140
141

# List of any CRAN packages, not provided by the modules, that must be made
# available to the vizapp
vizapp_cran_packages:
  - shiny
  - shinyFiles

David Trudgian's avatar
David Trudgian committed
142
# List of any Bioconductor packages, not provided by the modules, that must be made
143
144
# available to the vizapp
vizapp_bioc_packages:
145
146
  - ChIPseeker
  - org.Hs.eg.db
David Trudgian's avatar
David Trudgian committed
147
148
149
150
151
152

# List of any packages to install from GitHub using devtools, that must be
# made availavle to the vizapp
vizapp_github_packages:
  -