Merge pull request #117 from nf-core/dev

PR for 1.1.2 - Bugfix release

.github/workflows/ci.yml

@@ -20,7 +20,7 @@ jobs:
       - name: Download and tag image
         run: |
           docker pull nfcore/ampliseq:dev
-          docker tag nfcore/ampliseq:dev nfcore/ampliseq:1.1.1
+          docker tag nfcore/ampliseq:dev nfcore/ampliseq:1.1.2
       - name: Run test
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker

.travis.yml

@@ -12,7 +12,7 @@ before_install:
   - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && ([ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ] || [ $TRAVIS_PULL_REQUEST_BRANCH = "patch" ]))'  # Pull the docker image first so the test doesn't wait for this
   - docker pull nfcore/ampliseq:dev
   # Fake the tag locally so that the pipeline runs properly
-  - docker tag nfcore/ampliseq:dev nfcore/ampliseq:1.1.1
+  - docker tag nfcore/ampliseq:dev nfcore/ampliseq:1.1.2
 
 install:
   # Install Nextflow

CHANGELOG.md

@@ -1,11 +1,17 @@
 # nf-core/ampliseq
 
+## nf-core/ampliseq version 1.1.2 - 2019
+
+* No further changes, except a bugfix for the [timezone](https://github.com/nf-core/ampliseq/issues/114) issue found by @marchoeppner
+* Specification of '--qiime_timezone' might be required to run the analysis appropriately
+
 ## nf-core/ampliseq version 1.1.1 - 2019
 
 ### Pipeline Updates
 
 * Update from QIIME2 v2018.6 to v2019.10, including DADA2 v1.6 to DADA2 v1.10
-
+* Export absolute abundance files into 'results/abundance-table/filtered/' for optional external secondary analysis
+
 ### Bugfixes
 
 * [#78](https://github.com/nf-core/ampliseq/issues/78) - All sequenced classifed to the same species

Dockerfile

@@ -2,7 +2,7 @@ FROM nfcore/base:1.7
 LABEL description="Docker image containing all requirements for nf-core/ampliseq pipeline"
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-ampliseq-1.1.1/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-ampliseq-1.1.2/bin:$PATH
 ## Required to build the container properly
 RUN mkdir -p /root/.config/matplotlib
 RUN echo "backend : Agg" > /root/.config/matplotlib/matplotlibrc

README.md

@@ -1,11 +1,18 @@
 # ![nf-core/ampliseq](docs/images/nfcore-ampliseq_logo.png)
 
-[![Build Status](https://github.com/nf-core/ampliseq/workflows/ampliseq%20CI/badge.svg)](https://github.com/nf-core/ampliseq/workflows/ampliseq%20CI/badge.svg)
 [![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A519.10.0-brightgreen.svg)](https://www.nextflow.io/)
+[![nf-core](https://img.shields.io/badge/nf--core-pipeline-brightgreen.svg)](https://nf-co.re/)
+[![DOI](https://zenodo.org/badge/150448201.svg)](https://zenodo.org/badge/latestdoi/150448201)
+[![Cite Preprint](https://img.shields.io/badge/Cite%20Us!-Cite%20Preprint-orange)](https://biorxiv.org/cgi/content/short/2019.12.17.880468v1)
+
+[![GitHub Actions CI Status](https://github.com/nf-core/ampliseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/ampliseq/actions)
+[![GitHub Actions Linting Status](https://github.com/nf-core/ampliseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/ampliseq/actions)
 
 [![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/ampliseq.svg)](https://hub.docker.com/r/nfcore/ampliseq)
-[![DOI](https://zenodo.org/badge/150448201.svg)](https://zenodo.org/badge/latestdoi/150448201)
+![Singularity Container available](https://img.shields.io/badge/singularity-available-7E4C74.svg)
+
+[![Joins us on Slack](https://img.shields.io/badge/slack-nfcore/ampliseq-blue.svg)](https://nfcore.slack.com/channels/ampliseq)
 
 ## Introduction
 
@@ -30,3 +37,17 @@ The nf-core/ampliseq pipeline comes with documentation about the pipeline, found
 ### Credits
 
 These scripts were originally written for use at the [Quantitative Biology Center (QBiC)](http://www.qbic.life) and [Microbial Ecology, Center for Applied Geosciences](http://www.uni-tuebingen.de/de/104325), part of Eberhard Karls Universität Tübingen (Germany) by Daniel Straub ([@d4straub](https://github.com/d4straub)) and Alexander Peltzer ([@apeltzer](https://github.com/apeltzer)).
+
+## Citation
+
+If you use nf-core/ampliseq for your analysis, please cite it using the following DOI:
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3568091.svg)](https://doi.org/10.5281/zenodo.3568091)
+
+The pre-print can be cited as follows:
+
+[![DOI](https://img.shields.io/badge/-Cite%20Preprint-orange)](https://www.biorxiv.org/content/10.1101/2019.12.17.880468v1)
+
+You can cite the `nf-core` pre-print as follows:
+
+> Ewels PA, Peltzer A, Fillinger S, Alneberg JA, Patel H, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. **nf-core: Community curated bioinformatics pipelines**. *bioRxiv*. 2019. p. 610741. [doi: 10.1101/610741](https://www.biorxiv.org/content/10.1101/610741v2).

conf/base.config

@@ -28,7 +28,7 @@ process {
   withName: make_SILVA_132_16S_classifier {
     cpus = { check_max (2 * task.attempt, 'cpus' ) }
     memory = { check_max (35.GB * task.attempt, 'memory' ) }
-    time = { check_max (6.h * task.attempt, 'time' ) }
+    time = { check_max (12.h * task.attempt, 'time' ) }
   }
 
   //max memory seen yet: 63.GB

docs/output.md

@@ -138,6 +138,18 @@ All following analysis is based on these filtered tables.
 
 **Output directory: `results/abundance-table/filtered`**
 
+* `abs-abund-table-2.tsv`
+  * Tab-separated absolute abundance table at phylum level
+* `abs-abund-table-3.tsv`
+  * Tab-separated absolute abundance table at class level
+* `abs-abund-table-4.tsv`
+  * Tab-separated absolute abundance table at order level
+* `abs-abund-table-5.tsv`
+  * Tab-separated absolute abundance table at family level
+* `abs-abund-table-6.tsv`
+  * Tab-separated absolute abundance table at genus level
+* `abs-abund-table-7.tsv`
+  * Tab-separated absolute abundance table at species level
 * `count_table_filter_stats.tsv`
   * Tab-separated table with information on how much counts were filtered for each sample
 * `feature-table.biom`

docs/usage.md

@@ -13,6 +13,7 @@
     * [--reads](#--reads)
     * [--FW_primer and --RV_primer](#--fw_primer-and---rv_primer)
     * [--metadata](#--metadata)
+    * [----qiime_timezone](#--qiime_timezone)
   * [Other input options](#other-input-options)
     * [--extension](#--extension)
     * [--multipleSequencingRuns](#--multiplesequencingruns)
@@ -188,6 +189,11 @@ Please note the following requirements:
 2. The metadata file has to follow the [QIIME2 specifications](https://docs.qiime2.org/2019.10/tutorials/metadata/)
 3. In case of multiple sequencing runs, specific naming of samples are required, see [here](#--multipleSequencingRuns)
 
+### `--qiime_timezone`
+
+If a timezone error occurs, this parameter needs to be specified (default: 'Europe/Berlin'). Find your appropriate timezone with e.g. tzselect.
+Note, this affects the timezone of the entire software environment.
+
 ## Other input options
 
 ### `--extension`

environment.yml

@@ -1,4 +1,4 @@
-name: nf-core-ampliseq-1.1.1
+name: nf-core-ampliseq-1.1.2
 channels:
 - qiime2
 - qiime2/label/r2019.10

main.nf

@@ -18,6 +18,7 @@ def helpMessage() {
 	The minimal command for running the pipeline is as follows:
 	nextflow run nf-core/ampliseq -profile singularity --reads "data" --FW_primer GTGYCAGCMGCCGCGGTAA --RV_primer GGACTACNVGGGTWTCTAAT
 
+	In case of a timezone error, please specify "--qiime_timezone", e.g. --qiime_timezone 'Europe/Berlin'!
 
 	Main arguments:
 	  -profile [strings]            Use this parameter to choose a configuration profile. If not specified, runs locally and expects all software
@@ -28,6 +29,7 @@ def helpMessage() {
 	  --FW_primer [str]             Forward primer sequence
 	  --RV_primer [str]             Reverse primer sequence
 	  --metadata [path/to/file]     Path to metadata sheet, when missing most downstream analysis are skipped (barplots, PCoA plots, ...)
+	  --qiime_timezone [str]		Needs to be specified to resolve a timezone error (default: 'Europe/Berlin')
 
 	Other input options:
 	  --extension [str]             Naming of sequencing files (default: "/*_R{1,2}_001.fastq.gz"). 
@@ -1009,7 +1011,7 @@ process classifier {
 	env MATPLOTLIBRC from ch_mpl_classifier
 
 	output:
-	file("taxonomy.qza") into (ch_qiime_taxonomy_for_filter,ch_qiime_taxonomy_for_relative_abundance_reduced_taxa,ch_qiime_taxonomy_for_barplot,ch_qiime_taxonomy_for_ancom)
+	file("taxonomy.qza") into (ch_qiime_taxonomy_for_filter,ch_qiime_taxonomy_for_relative_abundance_reduced_taxa,ch_qiime_taxonomy_for_barplot,ch_qiime_taxonomy_for_ancom,ch_qiime_taxonomy_for_export_filtered_dada_output)
 	file("taxonomy/taxonomy.tsv") into ch_tsv_taxonomy
 
 
@@ -1115,19 +1117,22 @@ process export_filtered_dada_output {
 		saveAs: {filename -> 
 				 if (filename.indexOf("table/feature-table.biom") == 0)  "abundance_table/filtered/feature-table.biom"
 			else if (filename.indexOf("table/feature-table.tsv") == 0)   "abundance_table/filtered/feature-table.tsv"
+			else if (filename.indexOf("abs-abund-table-") == 0)          "abundance_table/filtered/$filename"
 			else if (filename.indexOf("filtered/*"))                     "representative_sequences/$filename"
 			else null}   
 
 	input:
 	file table from ch_qiime_table_for_filtered_dada_output
 	file repseq from ch_qiime_repseq_for_dada_output
+	file taxonomy from ch_qiime_taxonomy_for_export_filtered_dada_output
 	env MATPLOTLIBRC from ch_mpl_for_export_dada_output
 
 	output:
 	file("filtered/sequences.fasta") into ch_fasta_repseq
 	file("table/feature-table.tsv") into (ch_tsv_table_for_alpha_rarefaction,ch_tsv_table_for_report_filter_stats,ch_tsv_table_for_diversity_core)
 	file("table/feature-table.biom")
 	file("filtered/*")
+	file("abs-abund-table-*.tsv")
 
 	"""
 	#produce raw count table in biom format "table/feature-table.biom"
@@ -1145,6 +1150,25 @@ process export_filtered_dada_output {
 		--o-visualization rep-seqs.qzv
 	qiime tools export --input-path rep-seqs.qzv  \
 		--output-path filtered
+
+	##on several taxa level
+	array=( 2 3 4 5 6 7 )
+	for i in \${array[@]}
+	do
+		#collapse taxa
+		qiime taxa collapse \
+			--i-table ${table} \
+			--i-taxonomy ${taxonomy} \
+			--p-level \$i \
+			--o-collapsed-table table-\$i.qza
+		#export to biom
+		qiime tools export --input-path table-\$i.qza \
+			--output-path table-\$i
+		#convert to tab separated text file
+		biom convert \
+			-i table-\$i/feature-table.biom \
+			-o abs-abund-table-\$i.tsv --to-tsv
+	done
 	"""
 }
 

nextflow.config

@@ -20,6 +20,7 @@ params {
   igenomes_base = "./iGenomes"
   tracedir = "${params.outdir}/pipeline_info"
   clusterOptions = false
+  qiime_timezone = 'Europe/Berlin'
 
 // Defines all parameters that are independent of a test run
 trunc_qmin = 25 //to calculate params.trunclenf and params.trunclenr automatically
@@ -41,32 +42,37 @@ split = "-"
 reference_database = "https://www.arb-silva.de/fileadmin/silva_databases/qiime/Silva_132_release.zip"
 dereplication = 99
 
-  // Boilerplate options
-  name = false
-  multiqc_config = "$baseDir/assets/multiqc_config.yaml"
-  email = false
-  maxMultiqcEmailFileSize = 25.MB
-  plaintext_email = false
-  monochrome_logs = false
-  help = false
-  tracedir = "${params.outdir}/pipeline_info"
-  awsqueue = false
-  awsregion = 'eu-west-1'
-  igenomesIgnore = true
-  custom_config_version = 'master'
-  custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
-  hostnames = false
-  config_profile_description = false
-  config_profile_contact = false
-  config_profile_url = false
+// Boilerplate options
+name = false
+multiqc_config = "$baseDir/assets/multiqc_config.yaml"
+email = false
+maxMultiqcEmailFileSize = 25.MB
+plaintext_email = false
+monochrome_logs = false
+help = false
+tracedir = "${params.outdir}/pipeline_info"
+awsqueue = false
+awsregion = 'eu-west-1'
+igenomesIgnore = true
+custom_config_version = 'master'
+custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
+hostnames = false
+config_profile_description = false
+config_profile_contact = false
+config_profile_url = false
+}
+
+//export Time Zone required for QIIME2 2019.10
+env {
+  TZ = params.qiime_timezone
 }
 
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
 
 // Container slug. Stable releases should specify release tag!
 // Developmental code should specify :dev
-process.container = 'nfcore/ampliseq:1.1.1'
+process.container = 'nfcore/ampliseq:1.1.2'
 
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
@@ -77,6 +83,12 @@ try {
 } catch (Exception e) {
   System.err.println("WARNING: Could not load nf-core/config profiles: ${params.custom_config_base}/nfcore_custom.config")
 }
+// Load nf-core/ampliseq custom profiles from different Institutions
+try {
+  includeConfig "${params.custom_config_base}/pipeline/ampliseq.config"
+} catch (Exception e) {
+  System.err.println("WARNING: Could not load nf-core/config/ampliseq profiles: ${params.custom_config_base}/pipeline/ampliseq.config")
+}
 
 profiles {
   awsbatch { includeConfig 'conf/awsbatch.config' }
@@ -125,7 +137,7 @@ manifest {
   homePage = 'https://github.com/nf-core/ampliseq'
   description = '16S rRNA amplicon sequencing analysis workflow using QIIME2'
   homePage = 'https://github.com/nf-core/ampliseq'
-  version = '1.1.1'
+  version = '1.1.2'
   mainScript = 'main.nf'
   nextflowVersion = '>=19.10.0'
 }