Merge branch 'astrocyte' into 'master'

Astrocyte

See merge request !2

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+# Created by https://www.gitignore.io/api/r,perl,macos,linux,python,windows
+# Edit at https://www.gitignore.io/?templates=r,perl,macos,linux,python,windows
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Perl ###
+!Build/
+.last_cover_stats
+/META.yml
+/META.json
+/MYMETA.*
+*.o
+*.pm.tdy
+*.bs
+
+# Devel::Cover
+cover_db/
+
+# Devel::NYTProf
+nytprof.out
+
+# Dizt::Zilla
+/.build/
+
+# Module::Build
+_build/
+Build
+Build.bat
+
+# Module::Install
+inc/
+
+# ExtUtils::MakeMaker
+/blib/
+/_eumm/
+/*.gz
+/Makefile
+/Makefile.old
+/MANIFEST.bak
+/pm_to_blib
+/*.zip
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+### Python Patch ###
+.venv/
+
+### R ###
+# History files
+.Rhistory
+.Rapp.history
+
+# Session Data files
+.RData
+
+# Example code in package build process
+*-Ex.R
+
+# Output files from R CMD build
+/*.tar.gz
+
+# Output files from R CMD check
+/*.Rcheck/
+
+# RStudio files
+.Rproj.user/
+
+# produced vignettes
+vignettes/*.html
+vignettes/*.pdf
+
+# OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
+.httr-oauth
+
+# knitr and R markdown default cache directories
+/*_cache/
+/cache/
+
+# Temporary files created by R markdown
+*.utf8.md
+*.knit.md
+
+### R.Bookdown Stack ###
+# R package: bookdown caching files
+/*_files/
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.gitignore.io/api/r,perl,macos,linux,python,windows
+
+# nextflow analysis folders/files
+/test_data/*.fastq.gz
+/test_data/*.fastq
+/workflow/.nextflow/*
+/workflow/work/*
+/workflow/output/*
+pipeline_trace*.txt*
+.nextflow*.log*
+report.html*
+timeline*.html*
+
+*~
+
+!.gitkeep
+/Clinical
+/Expression

.gitlab-ci.yml

+before_script:
+  - module load python/3.6.1-2-anaconda
+  - module load nextflow/0.27.6
+  - ln -s /project/shared/bicf_workflow_ref/workflow_testdata/cellranger_count/*fastq.gz test_data/
+
+stages:
+  - integration
+
+simple_test:
+  stage: integration
+  script:
+  - nextflow run workflow/main.nf

astrocyte_pkg.yml

+#
+# metadata for the  Astrocyte CellRanger mkfastq workflow package
+#
+
+# -----------------------------------------------------------------------------
+# BASIC INFORMATION
+# -----------------------------------------------------------------------------
+
+# A unique identifier for the workflow package, text/underscores only
+name: 'tcga_shiny'
+# Who wrote this?
+author: 'Spencer Barnes, Gervaise Henry and Venkat Malladi'
+# A contact email address for questions
+email: 'bicf@utsouthwestern.edu'
+# A more informative title for the workflow package
+title: 'BICF TCGA Shiny Workflow'
+# A summary of the workflow package in plain text
+description: |
+  This is a workflow package for the exploration of TCGA data.
+
+# -----------------------------------------------------------------------------
+# 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.nf'
+#            The workflow must publish all final output into $baseDir
+
+# A list of cluster environment modules that this workflow requires to run.
+# Specify versioned module names to ensure reproducability.
+workflow_modules:
+  - 'R'
+
+# 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: []
+# -----------------------------------------------------------------------------
+# 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
+  - ggplot2
+  - shinyjs
+  - survival
+  - survminer
+

docs/index.md

+# Astrocyte TCGA Shiny Workflow Package
+
+## Workflow SOP

vizapp/ui.R

+shinyUI(
+  fluidPage(
+    headerPanel("TCGA Analysis"),
+    sidebarLayout(
+      sidebarPanel(
+        selectInput("operation","Select Plot Type",choices = c("Boxplot","Survival")),
+        conditionalPanel(condition = "input.operation=='Boxplot'",
+                         selectInput("cancerType","Select one or more cancer types",
+                                     choices = substr(list.files("../Expression/",pattern=".txt"),1,
+                                                      nchar(list.files("../Expression/",pattern=".txt"))-4),
+                                     multiple = TRUE),
+                         textInput("gene","Please input one gene of interest",placeholder = "Gene name ie TRIM21")
+        ),
+        conditionalPanel(condition="input.operation=='Survival'",
+                         selectInput("cancerType2","Select a cancer type",
+                                     choices = substr(list.files("../Expression/",pattern=".txt"),1,
+                                                      nchar(list.files("../Expression/",pattern=".txt"))-4)),
+                         textInput("gene2","Please input one gene of interest",placeholder = "Gene name ie BRCA1"),
+                         selectInput("operation2","Select automatic or manual cutoff", choices = c("Automatic", "Manual"))
+                         
+        ),
+        conditionalPanel(condition="input.operation2=='Manual' & input.operation=='Survival'",
+                         sliderInput("cut.off","Select a cutoff value",min = .10,max=.50,step = .05,value = .25)
+        ),
+        actionButton("go","GO")
+        
+      ),
+      mainPanel(
+        plotOutput("myPlot"),
+        downloadButton('downloadplot',"Download Figure")
+      )
+      
+    )
+  )
+)
+

workflow/conf/biohpc.config

+process {
+  executor = 'slurm'
+  queue='super'
+
+  // Process specific configuration
+  $checkDesignFile {
+    module = ['python/3.6.1-2-anaconda']
+    executor = 'local'
+  }
+  $count2 {
+    module = ['cellranger/2.1.1']
+  }
+  $count3 {
+    module = ['cellranger/3.0.1']
+  }
+}
+
+trace {
+  enabled = true
+  file = 'pipeline_trace.txt'
+  fields = 'task_id,native_id,process,name,status,exit,submit,start,complete,duration,realtime,%cpu,%mem,rss'
+}
+
+timeline {
+  enabled = true
+  file = 'timeline.html'
+}
+
+report {
+  enabled = true
+  file = 'report.html'
+}

workflow/main.nf

+#!/usr/bin/env nextflow
+
+// Path to an input file, or a pattern for multiple inputs
+// Note - $baseDir is the location of this workflow file main.nf
+
+// Define Input variables
+params.run = "TRUE"
+
+process copy {
+
+  publishDir "$baseDir/output", mode: 'copy'
+
+  input:
+
+  params.run
+
+  output:
+
+  file("**/Clinical/**") into outPathClinical
+  file("**/Expression/**") into outPathExpression
+
+  script:
+
+  """
+  cp -r /project/shared/bicf_workflow_ref/tcga_shiny_app_data/* .
+  """
+}

workflow/nextflow.config

+profiles {
+  standard {
+    includeConfig 'conf/biohpc.config'
+  }
+}