#
# metadata for the example astrocyte ChipSeq workflow package
#

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

# A unique identifier for the workflow package, text/underscores only
name: 'rnaseq_bicf'
# Who wrote this?
author: 'Brandi Cantarel'
# A contact email address for questions
email: 'biohpc-help@utsouthwestern.edu'
# A more informative title for the workflow package
title: 'BICF RNASeq Analysis Workflow'
# A summary of the workflow package in plain text
description: |
  This is a workflow package for the BioHPC/BICF RNASeq workflow system.
  It implements a simple RNASeq analysis workflow using TrimGalore, HiSAT,FeatureCounts,
  StringTie and statistical analysis using EdgeR and Ballgown, 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
documentation_files:
  - 'index.md'

# -----------------------------------------------------------------------------
# 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:
  - 'trimgalore/0.4.1'
  - 'cutadapt/1.9.1'
  - 'hisat2/2.0.1-beta-intel'
  - 'samtools/intel/1.3'
  - 'picard/1.127'
  - 'subread/1.5.0-intel'
  - 'stringtie/1.1.2-intel'

# 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: fastqs
    type: files
    required: true
    description: |
      One or more input paired-end FASTQ files from a RNASeq experiment and a design file with the link between the same name and the sample group
    regex: ".*(fastq|fq).gz"
    min: 1

  - id: pairs
    type: select
    required: true
    choices:
      - [ 'pe', 'Paired End']
      - [ 'se', 'Single End']
    description: |
      In single-end sequencing, the sequencer reads a fragment from only one end to the other, generating the sequence of base pairs. In paired-end reading it starts at one read, finishes this direction at the specified read length, and then starts another round of reading from the opposite end of the fragment.

  - id: markdups
    type: select
    required: true
    choices:
      - [ 'mark', 'Remove Duplicates']
      - [ 'keep', 'Keep All Sequences']
    description: |
      Duplicate reads are defined as originating from the same original fragment of DNA. Duplicates are identified as read pairs having identical 5-prime positions (coordinate and strand) for both reads in a mate pair and optionally, matching unique molecular identifier reads.

  - id: design
    type: file
    required: true
    description: |
      A design file listing pairs of sample name and sample group.
      Columns must include: SampleID,SampleName,SampleGroup,FullPathToFqR1,FullPathToFqR2

      FullPathToFqR1 and FullPathToFqR2 are the file names of the R1 and R2 read files.
      ie Sample1.R1.fastq.gz, Sample_1.fastq.gz, Sample.fq.gz
      Single end mode needs only the FullPathToFqR1 column

      Optional columns are encouraged, such as:
      SubjectID,Tissue,Gender,CultureDate,Organism,CellPopulation
      
  - id: genome
    type: select
    choices:
      - [ '/project/apps_database/hisat2_index/GRCh38', 'Human GRCh38']
      - [ '/project/apps_database/hisat2_index/GRCh37', 'Human GRCh37']
      - [ '/project/apps_database/hisat2_index/GRCm38', 'Mouse GRCh38']
    required: true
    description: |
      Reference genome for alignment

  - id: gtf
    type: select
    choices:
      - [ '/project/apps_database/iGenomes/Homo_sapiens/NCBI/GRCh38/Annotation/Genes.gencode/genes.gtf', 'GENCODE Human GRCh38' ]
      - [ '/project/apps_database/iGenomes/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf', 'NCBI Human GRCh38' ]
      - [ '/project/apps_database/iGenomes/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf', 'Ensembl Human GRCh37' ]
      - [ '/project/apps_database/iGenomes/Mus_musculus/NCBI/GRCh38/Annotation/Genes/gencode/genes.gtf', 'NCBI Mouse GRCh38' ]
    required: true
    description: |
      The gene annotation file to use


# -----------------------------------------------------------------------------
# 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:
  - sqldf
  - shiny
  - Vennerable
  - DT
  - ggplot2
  - gplots
  - gtools
  - RColorBrewer


# # List of any Bioconductor packages, not provided by the modules, that must be made
# available to the vizapp
vizapp_bioc_packages:
  - qusage
  - ballgown
  - edgeR
  - DESeq2