Merge pull request #97 from gagneurlab/dev

First release on bioconda

.gitignore

@@ -26,11 +26,13 @@ auto
 docs/build/*
 
 # IDE project files
+.idea/
 *.project
 readme.html
 *.Rproj
 .Rproj.user
 .Rhistory
+.RData
 
 # other
 *~
@@ -40,5 +42,3 @@ slurm-*.out
 *_files
 *.cache
 tmp/
-
-.RData

.travis.yml

@@ -1,68 +1,40 @@
 language: python
-sudo: required
 dist: xenial
 
-cache:
-  - directories:
-    - $HOME/R/Library
-    - /usr/bin/R
-    - $HOME/miniconda
-    - $HOME/htslib
-    - $HOME/bcftools
-
-env:
-  global:
-    - DROP_DIR=$(pwd)
-    - PROJECT_DIR="$HOME/project"
-    - MINICONDA_DIR="$HOME/miniconda"
-    - CONDA_SCRIPT="$MINICONDA_DIR/etc/profile.d/conda.sh"
-    - R_LIBS_USER="$HOME/R/Library"
-    - TAR="/bin/tar"
+#cache:
+#  - directories:
+#    - $HOME/miniconda
 
 python:
-  - "3.6.7"
+  - "3.7"
 
-addons:
-  apt:
-    packages:
-      - r-base
-      - libxml2-dev
-      - libcurl4-openssl-dev
-      - libssl-dev
-      - libblas-dev
-      - liblapack-dev
-      - gfortran
-      - graphviz
-      - pandoc
-      - tabix
-    sources:
-      - sourceline: 'deb https://cloud.r-project.org/bin/linux/ubuntu xenial-cran35/'
-        key_url: 'http://keyserver.ubuntu.com:11371/pks/lookup?op=get&search=0xe298a3a825c0d65dfd57cbb651716619e084dab9'
-    update: true
-
 install:
-  - cd $DROP_DIR
-#  - R -e "if ('FRASER' %in% rownames(installed.packages())) remove.packages('FRASER')"
-#  - R -e "if ('tMAE' %in% rownames(installed.packages())) remove.packages('tMAE')"
-  - Rscript travis/installRPackages.R drop/requirementsR.txt
-  - bash travis/install_bcftools.sh
-  - export PATH="$HOME/bcftools:$PATH"
-  - bcftools --version
-  - bash travis/install_conda.sh
-  - source $CONDA_SCRIPT
-  - conda activate drop_env
-  - pip install .
+  # Install Anaconda
+  - wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O /tmp/miniconda.sh
+  - bash /tmp/miniconda.sh -b -p $HOME/miniconda
+  - export PATH="$HOME/miniconda/bin:$PATH"
+  - hash -r
+  - conda config --set always_yes yes --set changeps1 no
+  - conda update -q conda
+
+  - conda config --add channels bioconda
+  - conda config --add channels conda-forge
 
-before_script:
-  - mkdir -p $PROJECT_DIR
-  - cd $PROJECT_DIR
-  - drop demo
+  # build package with cond
+  - conda install conda-build
+  - conda build conda.recipe --output-folder=$HOME/build
+  - conda config --add channels "file://${HOME}/build"
+
+  # test package
+  - source $HOME/miniconda/etc/profile.d/conda.sh
+  - conda create -q -n drop drop
+  - conda activate drop
 
 script: 
-  - cd $PROJECT_DIR
-  - snakemake -n
-  - snakemake aberrantExpression --cores 2
-  - snakemake aberrantSplicing --cores 2
-  - snakemake mae --cores 2
-  - snakemake --cores 2
-  - snakemake exportCounts --cores 2
+  - conda list 
+  - java -version
+  - gatk --help
+  - samtools --version
+  - bcftools --version
+  - drop --version
+  - python --version

README.md

@@ -1,84 +1,55 @@
 # Detection of RNA Outlier Pipeline
 [![Pipeline status](https://travis-ci.org/gagneurlab/drop.svg?branch=master)](https://travis-ci.org/gagneurlab/drop)
 [![Version](https://img.shields.io/badge/Version-0.9.0-green.svg)](https://github.com/gagneurlab/drop/master)
+[![Version](https://readthedocs.org/projects/gagneurlab-drop/badge/?version=latest)](https://gagneurlab-drop.readthedocs.io/en/latest)
 
-The manuscript main file, supplementary figures and table can be found in the manuscript folder or in [protocol exchange](https://protocolexchange.researchsquare.com/article/993ff4a5-38ce-4261-902a-600dbd528ba2/v1).
-
-
-[DROP documentation](https://gagneurlab-drop.readthedocs.io/en/latest/)
+The manuscript main file, supplementary figures and table can be found in the manuscript folder or in 
+[protocol exchange](https://protocolexchange.researchsquare.com/article/993ff4a5-38ce-4261-902a-600dbd528ba2/v1).
 
 <img src="drop_sticker.png" alt="drop logo" width="200" class="center"/>
 
-## Dependencies
-Programming languages:
-
-+ python >= 3.6.7
-     + pip >= 19.1
-     + we recommend using a virtual environment e.g. anaconda
-+ R >= 3.5 (https://www.r-project.org/). We recomment not to install R and its packages through conda.
-
-### R packages
-Bioconductor and base R packages need to be installed. The packages are listed in `drop/requirementsR.txt`. A script for installing these packages is provided. From the repository root just execute:
-```
-Rscript drop/installRPackages.R drop/requirementsR.txt
-```
-### Other packages
-+ samtools >= 1.7 (https://www.htslib.org/download/)
-+ bcftools (newest) (https://github.com/samtools/bcftools)
-+ tabix (https://www.htslib.org/download/)
-+ GATK (https://software.broadinstitute.org/gatk/)
-+ graphviz (https://www.graphviz.org/)
-+ pandoc (https://pandoc.org/)
-
 ## Installation
-Make sure that all of the above listed [dependencies](#dependencies) are installed.
-Then install DROP from github using `pip`. For this you need to recursively clone the repository with all its submodules first.
-```
-git clone https://github.com/gagneurlab/drop.git --recurse-submodules
-```
-Install DROP (activate your python environment if you are using one)
-```
-# conda activate drop_env
-cd drop
-pip install .
-```
-Alternatively, you can also install it directly without cloning
-```
-pip install git+https://github.com/gagneurlab/drop.git
+DROP is available on [bioconda](https://anaconda.org/bioconda/drop) for python 3.6 and above.
+We recommend using a dedicated conda environment.
+
 ```
-Installation time (including all dependencies): ~ 1h
+# create environment
+conda create -n drop_env python=3.6
+conda activate drop_env
 
-### Initialize a project
-DROP projects are initialized in a separate directory dedicated to the analysis project. Calling the initialization command creates the necessary files.
+# install drop
+conda install -c bioconda drop
 ```
-cd <project/path>
-drop init
-``` 
+Installation time: ~ 10min
 
-## Set up the demo project
+Test whether the pipeline runs through by setting up the demo dataset in an empty directory (e.g. ``~/drop_demo``).
 
-First, install the drop module according to [installation](#installation). 
-Initialize the demo directory with a custom test project path.
-In the following we will use `$HOME/drop_demo` as <project/path>.
 ```
-cd $HOME/drop_demo
+mkdir ~/drop_demo
+cd ~/drop_demo
+
+# demo will download the necessary data and pipeline files
 drop demo
 ```
-This command downloads the demo data (10 BAM files and a VCF file with 10 samples from the GEUVADIS project subset to chromosome 21), initializes DROP and adapts the config file paths to your current project directory. 
-Now the pipeline is ready to be executed using `snakemake`.
+
+The pipeline can be run using `snakemake` commands
+
 ```
 snakemake -n # dryrun
 snakemake
 ```
-Once the pipeline has run through, you will find the output in the `$HOME/drop_demo/Output`. It will consist of processed data, results and HTML pages. In order to view the complete HTML summary, open `$HOME/drop_demo/Output/htmlOutput/drop_demo_index.html` in the browser. Please note that this is a very small subset of the data used in the manuscript (100 samples and all chromosomes).
 
 Expected runtime: 25 min
 
+For more information on different installation options, check out the 
+[documentation](https://gagneurlab-drop.readthedocs.io/en/latest/installation.html)
+
 ## Set up a custom project
 Install the drop module according to [installation](#installation) and initialize the project in a custom project directory.
 ### Prepare the input data
 Create a sample annotation that contains the sample IDs, file locations and other information necessary for the pipeline.
-Edit the config file to set the correct file path of sample annotation and locations of non-sample specific input files. For these steps, please refer to the [documentation](https://drop-rna.readthedocs.io/en/latest/prepare.html).
+Edit the config file to set the correct file path of sample annotation and locations of non-sample specific input files.
+The requirements are described in the [documentation](https://gagneurlab-drop.readthedocs.io/en/latest/prepare.html).
 
 ### Execute the pipeline
 Once these files are set up, you can execute a dry run from your project directory

conda.recipe/meta.yaml

@@ -0,0 +1,106 @@
+{% set name = "drop" %}
+{% set version = "0.9.0" %}
+
+package:
+  name: "{{ name|lower }}"
+  version: "{{ version }}"
+
+source:
+  path: ..
+
+build:
+  number: 0
+  script: 
+    - "{{ PYTHON }} -m pip install -vv git+https://github.com/gagneurlab/wbuild.git#egg=wbuild"
+    - "${R} -e 'BiocManager::install(\"mumichae/tMAE\", dependencies=FALSE, update=FALSE, ask=FALSE)'"
+    - "{{ PYTHON }} -m pip install . -vv"
+  rpaths:
+    - lib/R/lib/
+    - lib/
+
+requirements:
+  build:
+    - {{ compiler('c') }}
+
+  host:
+    - python
+    - pip
+
+    # wbuild requirements
+    - pyyaml>=4.2b1
+    - pytest-runner
+
+    # tMAE requirements
+    - r-base>=4.0.0
+    - r-devtools
+    - r-biocmanager
+    - r-data.table
+    - r-ggplot2
+    - r-dplyr
+    - bioconductor-DESeq2
+    - bioconductor-GenomicScores 
+
+  run:
+    - python
+    - pandas
+    - Click>=7.0
+    - click-log
+    - python-dateutil
+
+    # snakemake/wbuild
+    - snakemake=>5.5.2
+    - pandoc
+    - graphviz
+    - pyyaml>=4.2b1
+
+    # command line tools
+    - tabix
+    - samtools>=1.7
+    - bcftools>=1.7
+    - gatk4>=4.0.4
+    - star>=2.7
+
+    # R dependencies
+    - r-base>=4.0.0
+    - r-rmarkdown
+    - r-knitr
+    - r-ggplot2
+    - r-ggthemes
+    - r-cowplot
+    - r-data.table
+    - r-dplyr
+    - r-tidyr
+    - r-magrittr
+    - r-devtools
+
+    # bioconductor packages
+    - bioconductor-deseq2
+    - bioconductor-GenomicScores
+    - bioconductor-outrider
+    - bioconductor-fraser
+    - bioconductor-variantannotation
+    - bioconductor-bsgenome.hsapiens.ucsc.hg19
+    #- bioconductor-mafdb.gnomad.r2.1.hs37d5
+    #- bioconductor-mafdb.gnomad.r2.1.grch38
+
+test:
+  imports:
+    - drop
+    - wbuild
+  commands:
+    - ${R} -e "library(tMAE)"
+    - wbuild --version
+    - drop --version
+
+about:
+  home: "https://gagneurlab-drop.readthedocs.io"
+  license: MIT
+  license_family: MIT
+  license_file: ../LICENSE
+  summary: "Detection of RNA Outliers Pipeline"
+  doc_url: 
+  dev_url: 
+
+extra:
+  recipe-maintainers:
+    - mumichae

docs/source/conf.py

@@ -23,7 +23,7 @@
 author = 'Michaela Müller'
 
 # The full version, including alpha/beta/rc tags
-release = '0.0.9'
+release = '0.9.0'
 
 
 # -- General configuration ---------------------------------------------------

docs/source/index.rst

@@ -1,8 +1,10 @@
 DROP - Detection of RNA Outliers Pipeline
 ==========================================
 
-DROP is intended to help researchers use RNA-Seq data in order to detect genes with aberrant expression, aberrant splicing and mono-allelic expression. It consists of three independent modules for each of those strategies. 
-After installing DROP, the user needs to fill in the config file and sample annotation table (Preparing Input Data). Then, DROP can be executed in multiple ways (Executing the Pipeline).
+DROP is intended to help researchers use RNA-Seq data in order to detect genes with aberrant expression,
+aberrant splicing and mono-allelic expression. It consists of three independent modules for each of those strategies.
+After installing DROP, the user needs to fill in the config file and sample annotation table (:ref:`prepare`).
+Then, DROP can be executed in multiple ways (:ref:`pipeline`).
 
 .. toctree::
    :maxdepth: 2
@@ -17,20 +19,23 @@ After installing DROP, the user needs to fill in the config file and sample anno
 Quickstart
 -----------
 
-Install via pip
+DROP is available on `bioconda <https://anaconda.org/bioconda/drop>`_ for python 3.6 and above.
+We recommend using a dedicated conda environment.
 
-    pip install drop
+.. code-block:: bash
+
+    conda install -c bioconda drop
+
+Initialize project
+
+.. code-block:: bash
+
+    cd <path-to-project>
+    drop demo
 
-Initialize the project
+Call the pipeline
 
 .. code-block:: bash
-    
-    cd <project/path>
-    drop init
 
-Indices and tables
-==================
+    snakemake
 
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`