Merge pull request #5 from nf-core/dev

update nf-core
lifebit-ai · Mar 17, 2020 · 53cef95 · 53cef95
2 parents d700351 + 1471b94
commit 53cef95
Show file tree

Hide file tree

Showing 8 changed files with 109 additions and 148 deletions.
diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
@@ -1,31 +1,30 @@
-name: nf-core aws test
+name: AWS Megatests
 # This workflow is triggered on PRs to the master branch.
 # It runs the -profile 'test' on AWS batch
+
 on:
   pull_request:
     branches:
-      - master
+    - master
   release:
     types: [published]
 
 jobs:
-    Awstest:
-        runs-on: ${{ matrix.os }}
-        strategy:
-            matrix:
-                os: ['ubuntu-latest']
-                python-version: ['3.7']
-        steps:
-        - uses: goanpeca/setup-miniconda@v1
-          with:
-            auto-update-conda: true
-            python-version: ${{ matrix.python-version }}
-        - name: Install aws client
-          run: conda install -c conda-forge awscli
-        - name: Start AWS batch job
-          env:
-            AWS_ACCESS_KEY_ID: ${{secrets.AWS_KEY_ID}}
-            AWS_SECRET_ACCESS_KEY: ${{secrets.AWS_KEY_SECRET}}
-            TOWER_ACCESS_TOKEN: ${{secrets.TOWER_ACCESS_TOKEN}}
-          run: |
-            aws batch submit-job --region eu-west-1 --job-name nf-core-sarek --job-queue 'default-8b3836e0-5eda-11ea-96e5-0a2c3f6a2a32' --job-definition nextflow --container-overrides command=nf-core/sarek,"-r ${GITHUB_SHA} -profile test --outdir s3://nf-core-awsmegatests/sarek/results-${GITHUB_SHA} -w s3://nf-core-awsmegatests/sarek/work-${GITHUB_SHA}"
+  run-awstest:
+    name: Run AWS test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Setup Miniconda
+        uses: goanpeca/[email protected]
+        with:
+          auto-update-conda: true
+          python-version: 3.7
+      - name: Install awscli
+        run: conda install -c conda-forge awscli
+      - name: Start AWS batch job
+        env:
+          AWS_ACCESS_KEY_ID: ${{secrets.AWS_KEY_ID}}
+          AWS_SECRET_ACCESS_KEY: ${{secrets.AWS_KEY_SECRET}}
+          TOWER_ACCESS_TOKEN: ${{secrets.TOWER_ACCESS_TOKEN}}
+        run: |
+          aws batch submit-job --region eu-west-1 --job-name nf-core-sarek --job-queue 'default-8b3836e0-5eda-11ea-96e5-0a2c3f6a2a32' --job-definition nextflow --container-overrides '{"command": ["nf-core/sarek", "-r ${GITHUB_SHA} -profile test --outdir s3://nf-core-awsmegatests/sarek/results-${GITHUB_SHA} -w s3://nf-core-awsmegatests/sarek/work-${GITHUB_SHA} -with-tower"], "environment": [{"name": "TOWER_ACCESS_TOKEN", "value": "'"$TOWER_ACCESS_TOKEN"'"}]}' 
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,7 +13,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 - [#115](https://github.com/nf-core/sarek/pull/115) - Add [@szilvajuhos](https://github.com/szilvajuhos) abstract for ESHG2020
 - [#117](https://github.com/nf-core/sarek/pull/117) - Add `Trim Galore` possibilities to Sarek
 - [#141](https://github.com/nf-core/sarek/pull/141) - Add containers for `WBcel235`
-- GitHub actions AWS megatests
+- [#150](https://github.com/nf-core/sarek/pull/150), [#151](https://github.com/nf-core/sarek/pull/151), [#154](https://github.com/nf-core/sarek/pull/154) - Add AWS mega test GitHub Actions
 
 ### `Changed`
 
@@ -40,6 +40,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 - [#141](https://github.com/nf-core/sarek/pull/141) - Update `VEP` databases to `99`
 - [#143](https://github.com/nf-core/sarek/pull/143) - Revert `snpEff` cache version to `75` for `GRCh37`
 - [#143](https://github.com/nf-core/sarek/pull/143) - Revert `snpEff` cache version to `86` for `GRCh38`
+- [#152](https://github.com/nf-core/sarek/pull/152) - Update docs
 
 ### `Fixed`
 
@@ -52,9 +53,13 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 - [#129](https://github.com/nf-core/sarek/pull/129) - Apply @drpatelh fix for `mardown_to_html.py` compatibility with Python 2
 - [#129](https://github.com/nf-core/sarek/pull/129) - Removed `Python` `3.7.3` from conda environment due to incompatibility
 - [#129](https://github.com/nf-core/sarek/pull/129) - Change ascii characters that were not supported from the `output.md` docs
+- [#140](https://github.com/nf-core/sarek/pull/140) - Fix extra T/N combinations for `ASCAT` cf [#136](https://github.com/nf-core/sarek/issues/136)
 - [#141](https://github.com/nf-core/sarek/pull/141) - Fix `download_cache.nf` script to download cache for `snpEff` and `VEP`
 - [#143](https://github.com/nf-core/sarek/pull/143) - Fix annotation CI testing with `snpEff` and `VEP`
 - [#144](https://github.com/nf-core/sarek/pull/144) - Fix CircleCI for building `VEP` containers
+- [#146](https://github.com/nf-core/sarek/pull/146) - Fix `--no_intervals` for `Mutect2` cf [#135](https://github.com/nf-core/sarek/issues/135)
+- [#156](https://github.com/nf-core/sarek/pull/156) - Fix typos
+- [#156](https://github.com/nf-core/sarek/pull/156) - Fix issues with `dbsnp` files while using only `Sention` tools
 
 ### `Deprecated`
 
@@ -93,6 +98,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/) a
 - [#107](https://github.com/nf-core/sarek/pull/107) - `--singleCPUMem` is now removed, use `--single_cpu_mem` instead
 - [#107](https://github.com/nf-core/sarek/pull/107) - `--snpeffDb` is now removed, use `--snpeff_db` instead
 - [#107](https://github.com/nf-core/sarek/pull/107) - `--vepCacheVersion` is now removed, use `--vep_cache_version` instead
+- [#152](https://github.com/nf-core/sarek/pull/152) - Removed `Jenkinsfile`
 
 ## [2.5.2] - Jåkkåtjkaskajekna
 

diff --git a/Jenkinsfile b/Jenkinsfile
diff --git a/README.md b/README.md
@@ -82,19 +82,28 @@ Main authors:
 
 Helpful contributors:
 
-* [Johannes Alneberg](https://github.com/alneberg)
-* [Phil Ewels](https://github.com/ewels)
+* [Adrian Lärkeryd](https://github.com/adrlar)
+* [Alexander Peltzer](https://github.com/apeltzer)
+* [Chela James](https://github.com/chelauk)
+* [Francesco L](https://github.com/nibscles)
+* [FriederikeHanssen](https://github.com/FriederikeHanssen)
+* [Gisela Gabernet](https://github.com/ggabernet)
 * [Jesper Eisfeldt](https://github.com/J35P312)
+* [Johannes Alneberg](https://github.com/alneberg)
+* [KochTobi](https://github.com/KochTobi)
+* [Lucia Conde](https://github.com/lconde-ucl)
 * [Malin Larsson](https://github.com/malinlarsson)
 * [Marcel Martin](https://github.com/marcelm)
-* [Alexander Peltzer](https://github.com/apeltzer)
 * [Nilesh Tawari](https://github.com/nilesh-tawari)
+* [Phil Ewels](https://github.com/ewels)
+* [Sabrina Krakau](https://github.com/skrakau)
+* [Sebastian-D](https://github.com/Sebastian-D)
+* [Winni Kretzschmar](https://github.com/winni2k)
 * [arontommi](https://github.com/arontommi)
 * [bjornnystedt](https://github.com/bjornnystedt)
+* [cgpu](https://github.com/cgpu)
 * [gulfshores](https://github.com/gulfshores)
-* [KochTobi](https://github.com/KochTobi)
 * [pallolason](https://github.com/pallolason)
-* [Sebastian-D](https://github.com/Sebastian-D)
 * [silviamorins](https://github.com/silviamorins)
 
 ## Contributions & Support
@@ -116,7 +125,7 @@ For further information or help, don't hesitate to get in touch on [Slack](https
 ## Citation
 
 If you use `nf-core/sarek` for your analysis, please cite the `Sarek` pre-print as follows:
-> Garcia M, Juhos S, Larsson M et al. **Sarek: A portable workflow for whole-genome sequencing analysis of germline and somatic variants [version 1; peer review: awaiting peer review].**. *F1000Research* 2020, 9:63. [doi: 10.12688/f1000research.16665.1](https://f1000research.com/articles/9-63/v1).
+> Garcia M, Juhos S, Larsson M et al. **Sarek: A portable workflow for whole-genome sequencing analysis of germline and somatic variants [version 1; peer review: 1 approved]** *F1000Research* 2020, 9:63 [doi: 10.12688/f1000research.16665.1](https://f1000research.com/articles/9-63/v1).
 
 You can cite the sarek zenodo record for a specific version using the following [doi: 10.5281/zenodo.3476426](https://zenodo.org/badge/latestdoi/184289291)
 

diff --git a/containers/vep/Dockerfile b/containers/vep/Dockerfile
@@ -17,7 +17,7 @@ RUN conda env export --name nf-core-sarek-vep-dev > nf-core-sarek-vep-dev.yml
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=95
+ARG VEP_VERSION=99
 
 # Download Genome
 RUN vep_install \

diff --git a/docs/annotation.md b/docs/annotation.md
@@ -16,16 +16,26 @@ With Sarek, annotation is done using `snpEff`, `VEP`, or even both consecutively
 VCF produced by Sarek will be annotated if `snpEff` or `VEP` are specified with the `--tools` command.
 As Sarek will use `bgzip` and `tabix` to compress and index VCF files annotated, it expects VCF files to be sorted.
 
-In these examples, all command lines will be launched starting with step `annotate`.
+In these examples, all command lines will be launched starting with `--step annotate`.
 It can of course be started directly from any other step instead.
 
 ## Using genome specific containers
 
-Sarek has already designed containers with `snpEff` and `VEP` files for `GRCh37`, `GRCh38` and `GRCm38`.
+Sarek has already designed containers with `snpEff` and `VEP` files for Human (`GRCh37`, `GRCh38`) Mouse (`GRCm38`), Dog (`CanFam3.1`) and Roundworm (`WBcel235`).
 Default settings will run using these containers.
 
 The main Sarek container has also `snpEff` and `VEP` installed, but without the cache files that can be downloaded separately.
 
+## Download cache
+
+A Nextflow helper script has been designed to help downloading `snpEff` and `VEP` cache.
+Such files are meant to be shared between multiple users, so this script is mainly meant for people administrating servers, clusters and advanced users.
+
+```bash
+nextflow run download_cache.nf --snpeff_cache </Path/To/snpEffCache> --snpeff_db <snpEff DB version> --genome <GENOME>
+nextflow run download_cache.nf --vep_cache </Path/To/VEPcache> --species <species> --vep_cache_version <VEP cache version> --genome <GENOME>
+```
+
 ## Using downloaded cache
 
 Both `snpEff` and `VEP` enable usage of cache.
@@ -36,8 +46,8 @@ The cache will only be used when `--annotation_cache` and cache directories are
 Example:
 
 ```bash
-nextflow run nf-core/sarek --tools snpEff --step annotate --sample file.vcf.gz --snpEff_cache /Path/To/snpEffCache --annotation_cache
-nextflow run nf-core/sarek --tools VEP --step annotate --sample file.vcf.gz --vep_cache /Path/To/vepCache --annotation_cache
+nextflow run nf-core/sarek --tools snpEff --step annotate --sample file.vcf.gz --snpEff_cache </Path/To/snpEffCache> --annotation_cache
+nextflow run nf-core/sarek --tools VEP --step annotate --sample file.vcf.gz --vep_cache </Path/To/vepCache> --annotation_cache
 ```
 
 ## Using VEP CADD plugin
@@ -52,10 +62,10 @@ Example:
 
 ```bash
 nextflow run nf-core/sarek --step annotate --tools VEP --sample file.vcf.gz --cadd_cache \
-    --cadd_InDels /PathToCADD/InDels.tsv.gz \
-    --cadd_InDels_tbi /PathToCADD/InDels.tsv.gz.tbi \
-    --cadd_WG_SNVs /PathToCADD/whole_genome_SNVs.tsv.gz \
-    --cadd_WG_SNVs_tbi /PathToCADD/whole_genome_SNVs.tsv.gz.tbi
+    --cadd_InDels </PathToCADD/InDels.tsv.gz> \
+    --cadd_InDels_tbi </PathToCADD/InDels.tsv.gz.tbi> \
+    --cadd_WG_SNVs </PathToCADD/whole_genome_SNVs.tsv.gz> \
+    --cadd_WG_SNVs_tbi </PathToCADD/whole_genome_SNVs.tsv.gz.tbi>
 ```
 
 ### Downloading CADD files
@@ -64,7 +74,7 @@ An helper script has been designed to help downloading CADD files.
 Such files are meant to be share between multiple users, so this script is mainly meant for people administrating servers, clusters and advanced users.
 
 ```bash
-nextflow run downloadcache.nf --cadd_cache /Path/To/CADDcache --cadd_version <CADD version> --genome <GENOME>
+nextflow run download_cache.nf --cadd_cache </Path/To/CADDcache> --cadd_version <CADD version> --genome <GENOME>
 ```
 
 ## Using VEP GeneSplicer plugin

diff --git a/download_cache.nf b/download_cache.nf
@@ -23,29 +23,27 @@ def helpMessage() {
     log.info nfcoreHeader()
     log.info"""
 
-Usage:
-    --help
-      you're reading it
-
-  nextflow run download_cache.nf [--snpeff_cache <pathToSNPEFFcache>] [--vep_cache <pathToVEPcache>]
-                                 [--cadd_cache <pathToCADDcache> --cadd_version <CADD Version>]
-    --snpeff_cache <Directoy>
-      Specify path to snpEff cache
-      If none, will use snpEff version specified in configuration
-      Will use snpEff cache version for ${params.genome}: ${params.genomes[params.genome].snpeff_db} in igenomes configuration file:
-      Change with --genome or in configuration files
-    --vep_cache <Directoy>
-      Specify path to VEP cache
-      If none, will use VEP version specified in configuration
-      Will from th iGenomes configuration file for ${params.genome}:
-      VEP cache version: ${params.genomes[params.genome].vep_cache_version}
-      and species ${params.genomes[params.genome].species}
-      Change with --genome or in configuration files
-    --cadd_cache <Directoy>
-      Specify path to CADD cache
-      Will use CADD version specified
-    --cadd_version <version>
-      Will specify which CADD version to download
+    Usage:
+
+    The typical command for running the pipeline is as follows:
+
+    nextflow run nf-core/sarek/download_cache.nf -profile docker --genome <genome> --help
+                                      [--snpeff_cache <pathToSNPEFFcache> --snpeff_db_version <snpEff DB version>]
+                                      [--vep_cache <pathToVEPcache> --vep_cache_version <VEP cache version> --species <species>]
+                                      [--cadd_cache <pathToCADDcache> --cadd_version <CADD Version>]
+
+    Options:
+      --help                   [bool] You're reading it
+      --snpeff_cache           [file] Path to snpEff cache
+      --snpeff_db_version       [str] snpEff DB version
+                                      Default: ${params.genomes[params.genome].snpeff_db}
+      --vep_cache              [file] Path to VEP cache
+      --vep_cache_version       [int] VEP cache version
+                                      Default: ${params.genomes[params.genome].vep_cache_version}
+      --species                 [str] Species
+                                      Default: ${params.genomes[params.genome].species}
+      --cadd_cache             [file] Path to CADD cache
+      --cadd_version            [str] CADD version to download
     """.stripIndent()
 }
 
@@ -216,20 +214,18 @@ process DownloadCADD {
 
 cadd_files = cadd_files.dump(tag: 'cadd_files')
 
-def nfcoreHeader(){
+def nfcoreHeader() {
     // Log colors ANSI codes
-    c_reset  = params.monochrome_logs ? '' : "\033[0m";
-    c_dim    = params.monochrome_logs ? '' : "\033[2m";
     c_black  = params.monochrome_logs ? '' : "\033[0;30m";
-    c_red    = params.monochrome_logs ? '' : "\033[0;31m";
-    c_green  = params.monochrome_logs ? '' : "\033[0;32m";
-    c_yellow = params.monochrome_logs ? '' : "\033[0;33m";
     c_blue   = params.monochrome_logs ? '' : "\033[0;34m";
+    c_dim    = params.monochrome_logs ? '' : "\033[2m";
+    c_green  = params.monochrome_logs ? '' : "\033[0;32m";
     c_purple = params.monochrome_logs ? '' : "\033[0;35m";
-    c_cyan   = params.monochrome_logs ? '' : "\033[0;36m";
+    c_reset  = params.monochrome_logs ? '' : "\033[0m";
     c_white  = params.monochrome_logs ? '' : "\033[0;37m";
+    c_yellow = params.monochrome_logs ? '' : "\033[0;33m";
 
-    return """    ${c_dim}----------------------------------------------------${c_reset}
+    return """    -${c_dim}--------------------------------------------------${c_reset}-
                                             ${c_green},--.${c_black}/${c_green},-.${c_reset}
     ${c_blue}        ___     __   __   __   ___     ${c_green}/,-._.--~\'${c_reset}
     ${c_blue}  |\\ | |__  __ /  ` /  \\ |__) |__         ${c_yellow}}  {${c_reset}
@@ -243,7 +239,7 @@ def nfcoreHeader(){
       ${c_white}`${c_green}|${c_reset}____${c_green}\\${c_reset}´${c_reset}
 
     ${c_purple}  nf-core/sarek v${workflow.manifest.version}${c_reset}
-    ${c_dim}----------------------------------------------------${c_reset}
+    -${c_dim}--------------------------------------------------${c_reset}-
     """.stripIndent()
 }