Merge pull request #61 from nf-core/dev

rnafusion v1.0.1

Author: matq007

.travis.yml

@@ -10,7 +10,7 @@ before_install:
   # PRs made to 'master' branch should always orginate from another repo or the 'dev' branch
   - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && [ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ])'
   - docker pull nfcore/rnafusion:dev
-  - docker tag nfcore/rnafusion:dev nfcore/rnafusion:1.0
+  - docker tag nfcore/rnafusion:dev nfcore/rnafusion:1.0.1
 
 env:
   - NXF_VER='0.32.0' # Specify a minimum NF version that should be tested and work
@@ -25,23 +25,19 @@ install:
   - pip install nf-core
   # Install markdownlint-cli
   - sudo apt-get install npm && npm install -g markdownlint-cli
-  # Install pylint
-  - pip install pylint
   # Reset 
   - mkdir ${TRAVIS_BUILD_DIR}/tests && cd ${TRAVIS_BUILD_DIR}
 
 script:
   # Create and download test data
   - |
     touch tests/genome.fa tests/genes.gtf
-    mkdir tests/star_index
+    mkdir tests/star_index tests/databases
     wget http://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_1.fq.gz -O tests/reads_1.fq.gz
     wget http://github.com/nf-core/test-datasets/raw/rnafusion/testdata/human/reads_2.fq.gz -O tests/reads_2.fq.gz
   # Lint the pipeline code
   - nf-core lint ${TRAVIS_BUILD_DIR}
   # Lint markdown
   - markdownlint ${TRAVIS_BUILD_DIR} -c ${TRAVIS_BUILD_DIR}/.github/markdownlint.yml
-  # Lint python code
-  - pylint --rcfile=${TRAVIS_BUILD_DIR}/.github/pylintrc ${TRAVIS_BUILD_DIR}/bin/*/*.py --ignore=scrape_software_versions.py
   # Running the pipeline
   - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker

CHANGELOG.md

@@ -1,5 +1,31 @@
 # nfcore/rnafusion
 
+## nfcore/rnafusion version 1.0.1 - 2018/04/06
+
+### Added
+
+* Added support for extra parameters for tools STAR-Fusion, FusionCatcher and fusion-report
+* Added example configuration for `singularity` and `docker`
+* Added [fusion-report](https://github.com/matq007/fusion-report) into the stack [#62](https://github.com/nf-core/rnafusion/issues/62), [#55](https://github.com/nf-core/rnafusion/issues/55), [#53](https://github.com/nf-core/rnafusion/issues/53), [#51](https://github.com/nf-core/rnafusion/issues/51)
+* Added nextflow helper script `download-singularity-img.nf`
+* Added nextflow helper script `download-references.nf`
+* Added `Jenkinsfile` for in-house testing
+
+### Changed
+
+* Updated installation of `FusionCatcher` (available now on bioconda)
+
+### Fixed
+
+* Fixed empty symlinks (`input.X`) in fusion-report [#68](https://github.com/nf-core/rnafusion/issues/68)
+* Fixed FASTA issues [#60](https://github.com/nf-core/rnafusion/issues/60)
+* Fixed centralized nf-core/config [#64](https://github.com/nf-core/rnafusion/issues/64)
+* Fixed `scrape_software_versions.py` to parse tools versions correctly [#65](https://github.com/nf-core/rnafusion/issues/65)
+
+### Removed
+
+* Removed `Singularity`
+
 ## nfcore/rnafusion version 1.0 - 2018/02/14
 
 Version 1.0 marks the first production release of this pipeline under the nf-core flag. The pipeline includes

Dockerfile

@@ -1,25 +1,10 @@
-# This Dockerfile was generated by tools/build.sh
 FROM nfcore/base
 
 LABEL authors="[email protected], [email protected], [email protected]" \
     description="Docker image containing all requirements for nfcore/rnafusion pipeline"
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-rnafusion-1.0/bin:$PATH
-
-WORKDIR /script-db
-# Download FusionGDB
-RUN apt-get update && apt-get install -y wget \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/TCGA_ChiTaRS_combined_fusion_information_on_hg19.txt -O TCGA_ChiTaRS_combined_fusion_information_on_hg19.txt \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/TCGA_ChiTaRS_combined_fusion_ORF_analyzed_gencode_h19v19.txt -O TCGA_ChiTaRS_combined_fusion_ORF_analyzed_gencode_h19v19.txt \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/uniprot_gsymbol.txt -O uniprot_gsymbol.txt \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fusion_uniprot_related_drugs.txt -O fusion_uniprot_related_drugs.txt \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fusion_ppi.txt -O fusion_ppi.txt \
-    && wget --no-check-certificate https://ccsm.uth.edu/FusionGDB/tables/fgene_disease_associations.txt -O fgene_disease_associations.txt \
-    && ln -s /opt/conda/envs/nf-core-rnafusion-1.0/bin/python3 /bin/python3
-
-COPY ./FusionGDB.sql .
-RUN sqlite3 fusions.db < FusionGDB.sql
+ENV PATH /opt/conda/envs/nf-core-rnafusion-1.0.1/bin:$PATH
 
 WORKDIR /

FusionGDB.sql

@@ -0,0 +1,40 @@
+pipeline {
+    agent any
+
+    environment {
+        NXF_VER = '0.32.0'
+        JENKINS_API = credentials('api')
+    }
+
+    stages {
+        stage('Setup environment') {
+            steps {
+                sh "pip install nf-core"
+                sh "docker pull nfcore/rnafusion:dev"
+                sh "docker tag nfcore/rnafusion:dev nfcore/rnafusion:1.0.1"
+            }
+        }
+        stage('Lint markdown') {
+            steps {
+                sh "markdownlint $WORKSPACE -c $WORKSPACE/.github/markdownlint.yml"
+            }
+        }
+        stage('Build') {
+            steps {
+                // sh "nextflow run kraken,jenkins nf-core/rnafusion"
+                sh "nextflow run nf-core/rnafusion -r dev --help"
+                sh "nextflow run nf-core/rnafusion/download-references.nf -r dev --help"
+                sh "nextflow run nf-core/rnafusion/download-singularity-img.nf -r dev --help"
+            }
+        }
+    }
+    
+    post {
+        failure {
+            script {
+                def response = sh(script: "curl -u ${JENKINS_API_USR}:${JENKINS_API_PSW} ${BUILD_URL}/consoleText", returnStdout: true).trim().replace('\n', '<br>')
+                def comment = pullRequest.comment("##:rotating_light: Buil log output:<br><summary><details>${response}</details></summary>")
+            }
+        }
+    }
+}

Jenkinsfile

@@ -2,18 +2,18 @@
 
 [![Build Status](https://travis-ci.org/nf-core/rnafusion.svg?branch=master)](https://travis-ci.org/nf-core/rnafusion)
 [![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A50.32.0-brightgreen.svg)](https://www.nextflow.io/)
+[![DOI](https://zenodo.org/badge/151721952.svg)](https://zenodo.org/badge/latestdoi/151721952)
+[![Slack Status](https://nf-core-invite.herokuapp.com/badge.svg)](https://nf-core-invite.herokuapp.com)
 [![MIT License](https://img.shields.io/github/license/nf-core/rnafusion.svg)](https://github.com/nf-core/rnafusion/blob/master/LICENSE)
 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](http://bioconda.github.io/)
 [![Docker](https://img.shields.io/docker/automated/nfcore/rnafusion.svg)](https://hub.docker.com/r/nfcore/rnafusion)
-![Singularity Container available](
-https://img.shields.io/badge/singularity-available-7E4C74.svg)
 
 **nfcore/rnafusion** uses RNA-seq data to detect fusions genes.
 
-The workflow processes RNA-sequencing data from FastQ files. It runs quality control on the raw data ([FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)), detects fusion genes ([STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion), [Fusioncatcher](https://github.com/ndaniel/fusioncatcher), [Ericscript](https://sites.google.com/site/bioericscript/), [Pizzly](https://github.com/pmelsted/pizzly), [Squid](https://github.com/Kingsford-Group/squid)), gathers information ([FusionGDB](https://ccsm.uth.edu/FusionGDB/index.html)), visualizes the fusions ([FusionInspector](https://github.com/FusionInspector/FusionInspector)), performs quality-control on the results ([MultiQC](http://multiqc.info)) and finally generates custom summary report.
+The workflow processes RNA-sequencing data from FastQ files. It runs quality control on the raw data ([FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)), detects fusion genes ([STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion), [Fusioncatcher](https://github.com/ndaniel/fusioncatcher), [Ericscript](https://sites.google.com/site/bioericscript/), [Pizzly](https://github.com/pmelsted/pizzly), [Squid](https://github.com/Kingsford-Group/squid)), gathers information ([FusionGDB](https://ccsm.uth.edu/FusionGDB/index.html), [Mitelman](https://cgap.nci.nih.gov/Chromosomes/Mitelman), [COSMIC](https://cancer.sanger.ac.uk/cosmic/fusion)), visualizes the fusions ([FusionInspector](https://github.com/FusionInspector/FusionInspector)), performs quality-control on the results ([MultiQC](http://multiqc.info)) and finally generates custom summary report witch scored fusions ([fusion-report](https://github.com/matq007/fusion-report)).
 
-![Final summary report](docs/images/example-summary-report.png)
+> Live **demo** output **[here](https://matq007.github.io/fusion-report/example/)**.
 
 The pipeline works with both single-end and paired-end data, though not all fusion detection tools work with single-end data (Ericscript, Pizzly, Squid and FusionInspector).
 
@@ -22,18 +22,12 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
 | Tool            | Single-end reads | CPU (recommended) | RAM (recommended) |
 | --------------- |:----------------:|:-----------------:|:-----------------:|
 | [Star-Fusion](https://github.com/STAR-Fusion/STAR-Fusion/wiki) | Yes              | >=16 cores        | ~30GB             |
-| [Fusioncatcher](https://github.com/ndaniel/fusioncatcher/blob/master/doc/manual.md) | Yes              | >=16 cores        | ~60GB             |
-| [Ericscript](https://sites.google.com/site/bioericscript/getting-started) | **No**           | >=16 cores        | ~30GB             |
+| [FusionCatcher](https://github.com/ndaniel/fusioncatcher/blob/master/doc/manual.md) | Yes              | >=16 cores        | ~64GB             |
+| [EricScript](https://sites.google.com/site/bioericscript/getting-started) | **No**           | >=16 cores        | ~30GB             |
 | [Pizzly](https://github.com/pmelsted/pizzly) | **No**           | >=16 cores        | ~30GB             |
 | [Squid](https://github.com/Kingsford-Group/squid) | **No**           | >=16 cores        | ~30GB             |
 | [FusionInspector](https://github.com/FusionInspector/FusionInspector/wiki) | **No**           | >=16 cores        | ~30GB             |
 
-> **TL;DR:** Make sure to download all required references for each tool. More details can be found in section [tools](docs/tools.md).
-
-```bash
-nextflow run nf-core/rnafusion --reads '*_R{1,2}.fastq.gz' --genome GRCh38 -profile docker --star_fusion --fusioncatcher --ericscript --pizzly --squid --fusion_inspector
-```
-
 For available parameters or help run:
 
 ```bash
@@ -54,3 +48,27 @@ The nf-core/rnafusion pipeline comes with documentation about the pipeline, foun
 5. [Troubleshooting](docs/troubleshooting.md)
 
 Use predefined configuration for desired Institution cluster provided at [nfcore/config](https://github.com/nf-core/configs) repository.
+
+## Credits
+
+This pipeline was written by Martin Proks ([@matq007](https://github.com/matq007)) in collaboration with Karolinska Institutet, SciLifeLab and University of Southern Denmark as a master thesis. This is a follow-up development started by Rickard Hammarén ([@Hammarn](https://github.com/Hammarn)). Special thanks goes to all supervisors: Teresita Díaz de Ståhl, PhD., Assoc. Prof., Monica Nistér, MD, PhD, Maxime U Garcia PhD([@MaxUlysse](https://github.com/MaxUlysse)), Szilveszter Juhos ([@szilvajuhos](https://github.com/szilvajuhos)), Phil Ewels ([@ewels](https://github.com/ewels)) PhD and Lars Grøntved, PhD., Assoc. Prof.
+
+## Tool References
+
+* **STAR-Fusion: Fast and Accurate Fusion Transcript Detection from RNA-Seq**
+Brian Haas, Alexander Dobin, Nicolas Stransky, Bo Li, Xiao Yang, Timothy Tickle, Asma Bankapur, Carrie Ganote, Thomas Doak, Natalie Pochet, Jing Sun, Catherine Wu, Thomas Gingeras, Aviv Regev
+bioRxiv 120295; doi: [https://doi.org/10.1101/120295](https://doi.org/10.1101/120295)
+* D. Nicorici, M. Satalan, H. Edgren, S. Kangaspeska, A. Murumagi, O. Kallioniemi, S. Virtanen, O. Kilkku, **FusionCatcher – a tool for finding somatic fusion genes in paired-end RNA-sequencing data**, bioRxiv, Nov. 2014,
+[DOI:10.1101/011650](http://dx.doi.org/10.1101/011650)
+* Benelli M, Pescucci C, Marseglia G, Severgnini M, Torricelli F, Magi A. **Discovering chimeric transcripts in paired-end RNA-seq data by using EricScript**. Bioinformatics. 2012; 28(24): 3232-3239.
+* **Fusion detection and quantification by pseudoalignment**
+Páll Melsted, Shannon Hateley, Isaac Charles Joseph, Harold Pimentel, Nicolas L Bray, Lior Pachter, bioRxiv 166322; doi: [https://doi.org/10.1101/166322](https://doi.org/10.1101/166322)
+* **SQUID: transcriptomic structural variation detection from RNA-seq** Cong Ma, Mingfu Shao and Carl Kingsford, Genome Biology, 2018, doi: [https://doi.org/10.1186/s13059-018-1421-5](https://doi.org/10.1186/s13059-018-1421-5)
+* **Fusion-Inspector** download: [https://github.com/FusionInspector](https://github.com/FusionInspector)
+* Martin Proks. (2019, March 26). matq007/fusion-report: **fusion-report:1.0** (Version 1.0). Zenodo. http://doi.org/10.5281/zenodo.2609227
+* **FastQC** download: [https://www.bioinformatics.babraham.ac.uk/projects/fastqc/](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+* **MultiQC** Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. [https://doi.org/10.1093/bioinformatics/btw354](https://doi.org/10.1093/bioinformatics/btw354) Download: [https://multiqc.info/](https://multiqc.info/)
+
+| | | |
+:-:|:-:|:-:|
+![nf-core/rnafusion](docs/images/ngi-logo.png) | ![nf-core/rnafusion](docs/images/ki-logo.png) | ![nf-core/rnafusion](docs/images/sdu-logo.png)