astrocyte_pkg.yml 4.95 KB
Newer Older
David Trudgian's avatar
David Trudgian committed
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
#
# 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?
author: 'David Trudgian'
# 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
  simple R Shiny visualization application.

# -----------------------------------------------------------------------------
# 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
David Trudgian's avatar
David Trudgian committed
30
# To supply a title for documentation use a pair of [ 'filename', 'title' ]
David Trudgian's avatar
David Trudgian committed
31
documentation_files:
David Trudgian's avatar
David Trudgian committed
32
  - [ 'index.md', 'ChIPSeq Example' ]
David Trudgian's avatar
David Trudgian committed
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

# -----------------------------------------------------------------------------
# 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'

# 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
#  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:
93
      - [ '/project/apps_database/iGenomes/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/genome.fa', 'UCSC hg38']
David Trudgian's avatar
David Trudgian committed
94 95
      - [ '/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']
96 97
      - [ '/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']
David Trudgian's avatar
David Trudgian committed
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
    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
vizapp_r_module: 'R/3.2.1-Intel'

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

# # List of any Bioconductor packages, not provided by the modules, that must be made
# available to the vizapp
vizapp_bioc_packages:
121
  - chipseq