Merge pull request #660 from nf-core/dev

Release 2.7.1

CHANGELOG.md

@@ -3,6 +3,24 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## nf-core/ampliseq version 2.7.1 - 2023-11-14
+
+### `Added`
+
+### `Changed`
+
+- [#657](https://github.com/nf-core/ampliseq/pull/657) - Improved parameter descriptions and sequence
+
+### `Fixed`
+
+- [#655](https://github.com/nf-core/ampliseq/pull/655) - Added `NUMBA_CACHE_DIR` to fix downstream analysis with QIIME2 that failed on some systems
+- [#656](https://github.com/nf-core/ampliseq/pull/656) - Moved conda-check to script-section and replaced `exit 1` with `error()`
+- [#657](https://github.com/nf-core/ampliseq/pull/657) - Corrected inaccurate reporting of QIIME2 taxonomic classifications and ASV length filtering
+
+### `Dependencies`
+
+### `Removed`
+
 ## nf-core/ampliseq version 2.7.0 - 2023-10-20
 
 ### `Added`

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/ampliseq/releases/tag/2.7.0" target="_blank">nf-core/ampliseq</a>
+  This report has been generated by the <a href="https://github.com/nf-core/ampliseq/releases/tag/2.7.1" target="_blank">nf-core/ampliseq</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/ampliseq/2.7.0/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/ampliseq/2.7.1/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-ampliseq-methods-description":
     order: -1000

assets/report_template.Rmd

@@ -370,7 +370,7 @@ cat(paste0("
 Overall read quality profiles are displayed as heat map of the frequency of each quality score at each base position.
 The mean quality score at each position is shown by the green line, and the quartiles of the quality score
 distribution by the orange lines. The red line shows the scaled proportion of reads that extend to at least
-that position. Original plots can be found [folder dada2/QC/](../dada2/QC/) with names that end in `_qual_stats.pdf`.
+that position. Original plots can be found in folder [dada2/QC/](../dada2/QC/) with names that end in `_qual_stats.pdf`.
 "))
 ```
 
@@ -426,8 +426,8 @@ cat(paste0("
 Estimated error rates are displayed for each possible transition. The black line shows the estimated error rates after
 convergence of the machine-learning algorithm. The red line shows the error rates expected under the nominal
 definition of the Q-score. The estimated error rates (black line) should be a good fit to the observed rates
-(points), and the error rates should drop with increased quality. Original plots can be found in
-[folder dada2/QC/](../dada2/QC/) with names that end in `.err.pdf`.
+(points), and the error rates should drop with increased quality. Original plots can be found in folder
+[dada2/QC/](../dada2/QC/) with names that end in `.err.pdf`.
 "))
 ```
 
@@ -724,9 +724,10 @@ if ( params$max_len_asv != 0 ) {
 }
 
 # replace 1 with 1.5 to display on log scale
-filter_len_profile$Counts[filter_len_profile$Counts == 1] <- 1.5
+filter_len_profile_replaced <- filter_len_profile
+filter_len_profile_replaced$Counts[filter_len_profile_replaced$Counts == 1] <- 1.5
 
-plot_filter_len_profile <- ggplot(filter_len_profile,
+plot_filter_len_profile <- ggplot(filter_len_profile_replaced,
         aes(x = Length, y = Counts)) +
         geom_bar(stat = "identity", fill = rgb(0.1, 0.4, 0.75), width = 0.5) +
         ylab("Number of ASVs") +
@@ -989,17 +990,18 @@ asv_tax <- read.table(params$qiime2_taxonomy, header = TRUE, sep = "\t")
 asv_tax <- subset(asv_tax, select = Taxon)
 
 # Remove greengenes85 ".__" placeholders
-df = as.data.frame(lapply(asv_tax, function(x) gsub(".__", "", x)))
-# remove all last, empty ;
-df = as.data.frame(lapply(df, function(x) gsub(" ;","",x)))
+df = as.data.frame(lapply(asv_tax, function(x) gsub(" .__", "", x)))
+# remove all empty ;
+df = as.data.frame(lapply(df, function(x) gsub(";;","",x)))
 # remove last remaining, empty ;
-df = as.data.frame(lapply(df, function(x) gsub("; $","",x)))
+df = as.data.frame(lapply(df, function(x) gsub(";$","",x)))
 
 # get maximum amount of taxa levels per ASV
-max_taxa <- lengths(regmatches(df$Taxon, gregexpr("; ", df$Taxon)))+1
+max_taxa <- lengths(regmatches(df$Taxon, gregexpr(";", df$Taxon)))+1
 
-# Currently, all QIIME2 databases seem to have the same levels!
+# Currently, all QIIME2 databases seem to have the same levels! But for compatibility, restrict number of levels to max_taxa
 level <- c("Kingdom","Phylum","Class","Order","Family","Genus","Species")
+level <- head(level, n = max(max_taxa) )
 
 # Calculate the classified numbers/percent of asv
 n_asv_tax = nrow(asv_tax)
@@ -1811,7 +1813,7 @@ if ( !isFALSE(params$dada2_ref_tax_title) ) {
         "- citation: `", params$dada2_ref_tax_citation, "`\n\n", sep = "")
 } else if (!isFALSE(params$dada2_taxonomy)) {
     cat("Taxonomic classification by DADA2:\n\n",
-        "- database: unknown - user provided\n\n", sep = "")
+        "- database: user provided file(s)\n\n", sep = "")
 }
 
 if ( !isFALSE(params$sintax_ref_tax_title) ) {
@@ -1821,7 +1823,7 @@ if ( !isFALSE(params$sintax_ref_tax_title) ) {
         "- citation: `", params$sintax_ref_tax_citation, "`\n\n", sep = "")
 } else if (!isFALSE(params$sintax_taxonomy)) {
     cat("Taxonomic classification by SINTAX:\n\n",
-        "- database: unknown - user provided\n\n", sep = "")
+        "- database: user provided file\n\n", sep = "")
 }
 
 if ( !isFALSE(params$kraken2_ref_tax_title) ) {
@@ -1831,7 +1833,7 @@ if ( !isFALSE(params$kraken2_ref_tax_title) ) {
         "- citation: `", params$kraken2_ref_tax_citation, "`\n\n", sep = "")
 } else if (!isFALSE(params$kraken2_taxonomy)) {
     cat("Taxonomic classification by Kraken2:\n\n",
-        "- database: unknown - user provided\n\n", sep = "")
+        "- database: user provided files\n\n", sep = "")
 }
 
 if ( !isFALSE(params$qiime2_ref_tax_title) ) {
@@ -1841,7 +1843,7 @@ if ( !isFALSE(params$qiime2_ref_tax_title) ) {
         "- citation: `", params$qiime2_ref_tax_citation, "`\n\n", sep = "")
 } else if (!isFALSE(params$qiime2_taxonomy)) {
     cat("Taxonomic classification by QIIME2:\n\n",
-        "- database: unknown - user provided\n\n", sep = "")
+        "- database: user provided file\n\n", sep = "")
 }
 ```
 

docs/usage.md

@@ -36,7 +36,7 @@ The typical command for running the pipeline is as follows:
 
 ```bash
 nextflow run nf-core/ampliseq \
-    -r 2.7.0 \
+    -r 2.7.1 \
     -profile singularity \
     --input "samplesheet.tsv" \
     --FW_primer GTGYCAGCMGCCGCGGTAA \
@@ -45,7 +45,7 @@ nextflow run nf-core/ampliseq \
     --outdir "./results"
 ```
 
-In this example, `--input` is the [Samplesheet input](#samplesheet-input), other options are [Direct FASTQ input](#direct-fastq-input) and [ASV/OTU fasta input](#asvotu-fasta-input). For more details on metadata, see [Metadata](#metadata). For [Reproducibility](#reproducibility), specify the version to run using `-r` (= release, e.g. 2.7.0, please use the most recent release). See the [nf-core/ampliseq website documentation](https://nf-co.re/ampliseq/parameters) for more information about pipeline specific parameters.
+In this example, `--input` is the [Samplesheet input](#samplesheet-input), other options are [Direct FASTQ input](#direct-fastq-input) and [ASV/OTU fasta input](#asvotu-fasta-input). For more details on metadata, see [Metadata](#metadata). For [Reproducibility](#reproducibility), specify the version to run using `-r` (= release, e.g. 2.7.1, please use the most recent release). See the [nf-core/ampliseq website documentation](https://nf-co.re/ampliseq/parameters) for more information about pipeline specific parameters.
 
 It is possible to not provide primer sequences (`--FW_primer` & `--RV_primer`) and skip primer trimming using `--skip_cutadapt`, but this is only for data that indeed does not contain any PCR primers in their sequences. Also, metadata (`--metadata`) isnt required, but aids downstream analysis.
 

modules/local/qiime2_alphararefaction.nf

@@ -3,11 +3,6 @@ process QIIME2_ALPHARAREFACTION {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     path(metadata)
     path(table)
@@ -22,8 +17,14 @@ process QIIME2_ALPHARAREFACTION {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     maxdepth=\$(count_table_minmax_reads.py $stats maximum 2>&1)
 

modules/local/qiime2_ancom_asv.nf

@@ -7,11 +7,6 @@ process QIIME2_ANCOM_ASV {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple path(metadata), path(table)
 
@@ -23,8 +18,14 @@ process QIIME2_ANCOM_ASV {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime composition add-pseudocount \\
         --i-table ${table} \\

modules/local/qiime2_ancom_tax.nf

@@ -5,11 +5,6 @@ process QIIME2_ANCOM_TAX {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple path(metadata), path(table), path(taxonomy) ,val(taxlevel)
 
@@ -21,8 +16,14 @@ process QIIME2_ANCOM_TAX {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
     mkdir ancom
 
     # Sum data at the specified level

modules/local/qiime2_barplot.nf

@@ -3,11 +3,6 @@ process QIIME2_BARPLOT {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     path(metadata)
     path(table)
@@ -22,10 +17,16 @@ process QIIME2_BARPLOT {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     suffix = setting ? "_${table.baseName}" : ""
     def metadata_cmd = metadata ? "--m-metadata-file ${metadata}": ""
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime taxa barplot  \\
         --i-table ${table}  \\

modules/local/qiime2_classify.nf

@@ -4,11 +4,6 @@ process QIIME2_CLASSIFY {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     path(trained_classifier)
     path(repseq)
@@ -22,8 +17,14 @@ process QIIME2_CLASSIFY {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime feature-classifier classify-sklearn  \\
         --i-classifier ${trained_classifier}  \\

modules/local/qiime2_diversity_adonis.nf

@@ -4,11 +4,6 @@ process QIIME2_DIVERSITY_ADONIS {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple path(metadata), path(core), val(formula)
 
@@ -20,9 +15,15 @@ process QIIME2_DIVERSITY_ADONIS {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     def args = task.ext.args ?: ''
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime diversity adonis \\
         --p-n-jobs $task.cpus \\

modules/local/qiime2_diversity_alpha.nf

@@ -4,11 +4,6 @@ process QIIME2_DIVERSITY_ALPHA {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple path(metadata), path(core)
 
@@ -20,8 +15,14 @@ process QIIME2_DIVERSITY_ALPHA {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime diversity alpha-group-significance \\
         --i-alpha-diversity ${core} \\

modules/local/qiime2_diversity_beta.nf

@@ -4,11 +4,6 @@ process QIIME2_DIVERSITY_BETA {
 
     container "qiime2/core:2023.7"
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        exit 1, "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
-    }
-
     input:
     tuple path(metadata), path(core), val(category)
 
@@ -20,8 +15,14 @@ process QIIME2_DIVERSITY_BETA {
     task.ext.when == null || task.ext.when
 
     script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "QIIME2 does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
     """
-    export XDG_CONFIG_HOME="\${PWD}/HOME"
+    export XDG_CONFIG_HOME="./xdgconfig"
+    export MPLCONFIGDIR="./mplconfigdir"
+    export NUMBA_CACHE_DIR="./numbacache"
 
     qiime diversity beta-group-significance \\
         --i-distance-matrix ${core} \\