Merge branch 'master' of https://github.com/jfy133/eager

Author: jfy133

.travis.yml

@@ -13,7 +13,7 @@ before_install:
   # Pull the docker image first so the test doesn't wait for this
   - docker pull nfcore/eager
   # Fake the tag locally so that the pipeline runs properly
-  - docker tag nfcore/eager nfcore/eager:2.0.2
+  - docker tag nfcore/eager nfcore/eager:latest
 
 install:
   # Install Nextflow
@@ -37,16 +37,16 @@ script:
   # Lint the pipeline code
   - nf-core lint ${TRAVIS_BUILD_DIR}
   # Run the basic pipeline with the test profile
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --saveReference
   # Run the basic pipeline with single end data (pretending its single end actually)
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --singleEnd 
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --singleEnd --bwa_index results/reference_genome/bwa_index/
   # Run the same pipeline testing optional step: fastp, complexity 
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --complexity_filter 
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --complexity_filter --bwa_index results/reference_genome/bwa_index/
   # Test BAM Trimming
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --trim_bam 
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --trim_bam --bwa_index results/reference_genome/bwa_index/
   # Test running with CircularMapper
   - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --circularmapper --circulartarget 'NC_007596.2'
   # Test running with BWA Mem
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --bwamem
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --pairedEnd --bwamem --bwa_index results/reference_genome/bwa_index/
   # Test basic pipeline with Conda too 
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,conda --pairedEnd
+  - travis_wait 25 nextflow run ${TRAVIS_BUILD_DIR} -profile test,conda --pairedEnd --bwa_index results/reference_genome/bwa_index/

CHANGELOG.md

@@ -6,6 +6,12 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## unpublished
 
+### `Added`
+* [#80](https://github.com/nf-core/eager/pull/80) - BWA Index file handling 
+* [#77](https://github.com/nf-core/eager/pull/77) - Lots of documentation updates by [@jfy133](https://github.com/jfy133)
+
+### `Fixed`
+* [#84](https://github.com/nf-core/eager/pull/85) - Fix for [Samtools index issues](https://github.com/nf-core/eager/issues/84)
 
 ## [2.0.2] - 2018-11-03
 

Dockerfile

@@ -3,4 +3,4 @@ FROM nfcore/base
 LABEL description="Docker image containing all requirements for nf-core/eager pipeline"
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-eager-2.0.2/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-eager-2.1.0dev/bin:$PATH

README.md

@@ -97,4 +97,4 @@ do so and everyone is welcome to contribute here!
 * *PMDTools* Skoglund, P., Northoff, B. H., Shunkov, M. V., Derevianko, A. P., Pääbo, S., Krause, J., & Jakobsson, M. (2014). Separating endogenous ancient DNA from modern day contamination in a Siberian Neandertal. Proceedings of the National Academy of Sciences of the United States of America, 111(6), 2229–2234. [https://doi.org/10.1073/pnas.1318934111](https://doi.org/10.1073/pnas.1318934111) Download: [https://github.com/pontussk/PMDtools](https://github.com/pontussk/PMDtools)
 * *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/)
 * *BamUtils* Jun, G., Wing, M. K., Abecasis, G. R., & Kang, H. M. (2015). An efficient and scalable analysis framework for variant extraction and refinement from population-scale DNA sequence data. Genome Research, 25(6), 918–925. [https://doi.org/10.1101/gr.176552.114](https://doi.org/10.1101/gr.176552.114) Download: [https://genome.sph.umich.edu/wiki/BamUtil](https://genome.sph.umich.edu/wiki/BamUtil)
-* *FastP* Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884–i890. [https://doi.org/10.1093/bioinformatics/bty560](https://doi.org/10.1093/bioinformatics/bty560) Download: [https://github.com/OpenGene/fastp](https://github.com/OpenGene/fastp)
+* *FastP* Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884–i890. [https://doi.org/10.1093/bioinformatics/bty560](https://doi.org/10.1093/bioinformatics/bty560) Download: [https://github.com/OpenGene/fastp](https://github.com/OpenGene/fastp)

Singularity

@@ -4,10 +4,10 @@ Bootstrap:docker
 %labels
     MAINTAINER Alexander Peltzer <alexander.peltzer@qbic.uni-tuebingen.de>
     DESCRIPTION Container image containing all requirements for the nf-core/eager pipeline
-    VERSION 2.0.2
+    VERSION 2.1.0dev
 
 %environment
-    PATH=/opt/conda/envs/nf-core-eager-2.0.2/bin:$PATH
+    PATH=/opt/conda/envs/nf-core-eager-2.1.0dev/bin:$PATH
     export PATH
 
 %files

conf/acad-pheonix.config

@@ -0,0 +1,22 @@
+/*
+ * ----------------------------------------------------------------------------
+ *  Nextflow config file for use with Singularity on Phoenix Cluster Adelaide
+ * ----------------------------------------------------------------------------
+ * Defines basic usage limits and singularity image id.
+ */
+
+singularity {
+    enabled = true
+    envWhitelist='SINGULARITY_BINDPATH'
+}
+
+process {
+    beforeScript = 'module load Singularity/2.5.2-GCC-5.4.0-2.26'
+    executor = 'slurm'
+}
+
+params {
+  max_memory = 128.GB
+  max_cpus = 32
+  max_time = 48.h
+}

conf/shh.config

@@ -0,0 +1,36 @@
+/*
+ * -------------------------------------------------------------
+ *  Nextflow config file for use with Singularity at SHH Clusters
+ * -------------------------------------------------------------
+ * Defines basic usage limits and singularity image id.
+ */
+
+singularity {
+    enabled = true
+}
+
+/*
+* To be improved by process specific resource requests
+* By default, take the medium queue, smaller processes might just go to short (e.g. multiqc or similar things)
+*/
+
+process {
+    executor = 'slurm'
+    queue = 'medium'
+
+    
+    withName:makeFastaIndex {
+        queue = 'short'
+        time = 2.h
+    }
+    withName:makeSeqDict {
+        queue = 'short'
+        time = 2.h
+    }
+}
+
+params {
+  max_memory = 734.GB
+  max_cpus = 64
+  max_time = 48.h
+}

docs/configuration/adding_your_own.md

@@ -51,7 +51,6 @@ Note that the dockerhub organisation name annoyingly can't have a hyphen, so is
 ### Singularity image
 Many HPC environments are not able to run Docker due to security issues.
 [Singularity](http://singularity.lbl.gov/) is a tool designed to run on such HPC systems which is very similar to Docker.
->>>>>>> TEMPLATE
 
 To specify singularity usage in your pipeline config file, add the following:
 
@@ -81,5 +80,4 @@ To use conda in your own config file, add the following:
 
 ```nextflow
 process.conda = "$baseDir/environment.yml"
->>>>>>> TEMPLATE
 ```

docs/configuration/local.md

@@ -11,7 +11,7 @@ First, install docker on your system: [Docker Installation Instructions](https:/
 
 Then, simply run the analysis pipeline:
 ```bash
-nextflow run nf-core/eager -profile docker --reads '<path to your reads>'
+nextflow run nf-core/eager -profile docker --reads '<path to your reads>' --pairedEnd
 ```
 
 Nextflow will recognise `nf-core/eager` and download the pipeline from GitHub. The `-profile docker` configuration lists the [nf-core/eager](https://hub.docker.com/r/nfcore/eager/) image that we have created and is hosted at dockerhub, and this is downloaded.
@@ -23,9 +23,13 @@ The public docker images are tagged with the same version numbers as the code, w
 
 
 ## Singularity image
-Many HPC environments are not able to run Docker due to security issues. [Singularity](http://singularity.lbl.gov/) is a tool designed to run on such HPC systems which is very similar to Docker. Even better, it can use create images directly from dockerhub.
+Many HPC environments are not able to run Docker due to security issues. [Singularity](http://singularity.lbl.gov/) is a tool designed to run on such HPC systems which is very similar to Docker. There is a particular profile that will download the singularity image for you.
 
-To use the singularity image for a single run, use `-with-singularity 'docker://nfcore/eager'`. This will download the docker container from dockerhub and create a singularity image for you dynamically.
+```bash
+nextflow run nf-core/eager -profile singularity --reads '<path to your reads>' --pairedEnd
+```
+
+Additionally, it can use create images directly from dockerhub. To use the singularity image for a single run, use `-with-singularity 'docker://nfcore/eager'`. This will download the docker container from dockerhub and create a singularity image for you dynamically.
 
 If you intend to run the pipeline offline, nextflow will not be able to automatically download the singularity image for you. Instead, you'll have to do this yourself manually first, transfer the image file and then point to that.
 
@@ -38,5 +42,14 @@ singularity pull --name nf-core-eager.img docker://nfcore/eager
 Then transfer this file and run the pipeline with this path:
 
 ```bash
-nextflow run /path/to/nf-core/eager -with-singularity /path/to/nf-core-eager.img
+nextflow run /path/to/nf-core/eager -with-singularity /path/to/nf-core-eager.img --reads --pairedEnd
 ```
+
+## Conda
+
+You may also use conda (utilising the bioconda repository) to download the pipeline dependencies for you.
+
+```bash
+nextflow run nf-core/eager -profile conda --reads '<path to your reads>' --pairedEnd
+```
+

docs/installation.md

@@ -69,6 +69,19 @@ Be warned of two important points about this default configuration:
     * See the [nextflow docs](https://www.nextflow.io/docs/latest/executor.html) for information about running with other hardware backends. Most job scheduler systems are natively supported.
 2. Nextflow will expect all software to be installed and available on the `PATH`
 
+The following software is currently required to be installed:
+
+* [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+* [Picard Tools](https://broadinstitute.github.io/picard/)
+* [Samtools](http://www.htslib.org/)
+* [Preseq](http://smithlabresearch.org/software/preseq/)
+* [MultiQC](https://multiqc.info/)
+* [BWA](http://bio-bwa.sourceforge.net/)
+* [Qualimap](http://qualimap.bioinfo.cipf.es/)
+* [GATK](https://software.broadinstitute.org/gatk/)
+* [bamUtil](https://genome.sph.umich.edu/wiki/BamUtil)
+* [fastP](https://github.com/OpenGene/fastp)
+
 #### 3.1) Software deps: Docker
 First, install docker on your system: [Docker Installation Instructions](https://docs.docker.com/engine/installation/)