Merge pull request #99 from ctmrbio/develop

Merge 2.7.0

CHANGELOG.md

@@ -17,7 +17,35 @@ Changes should fall into one of the following categories:
 - `Removed`, for now removed features.
 - `Fixed`, for any bug fixes.
 
-## [2.6.0] - In development
+
+## [2.8.0]
+### Added
+
+### Changed
+
+### Removed
+
+### Deprecated
+
+
+## [2.7.0] - 2019-01-16
+### Added
+- New command-line argument `--ignore_contamination_screen` will ignore all inputs
+  that `FAIL` mash screen contamination check. 
+
+### Changed
+- Set default errorstrategy for Nextflow to `ignore`. 
+- Updated process declarations to use new `withName` syntax.
+
+### Removed
+- The intermediate output from `mash screen` (i.e.  `<sample>.mash_screen.tsv`)
+  is now removed from the output directory, in favor of the concatenated table
+  `all_samples.mash_screening_results.tsv`, containing results for all samples.
+
+### Deprecated
+
+
+## [2.6.0] - 2018-05-28
 ### Added
 - Created this changelog.
 - New output file, `all_samples.mash_screening_results.tsv`, which is a concatenation

bactpipe.nf

@@ -1,7 +1,7 @@
 #!/usr/bin/env nextflow
 // vim: syntax=groovy expandtab
 
-bactpipe_version = '2.6.0'
+bactpipe_version = '2.7.0'
 nf_required_version = '0.26.0'
 
 log.info "".center(60, "=")
@@ -111,7 +111,6 @@ try {
 process screen_for_contaminants {
     validExitStatus 0,3
     tag { pair_id }
-    publishDir "${params.output_dir}/mash_screen", mode: 'copy'
 
     input:
     set pair_id, file(reads) from mash_input
@@ -164,6 +163,10 @@ pure_isolates = screening_results_for_bbduk.filter {
     passed = screening_result == "PASS"
     if ( ! passed ) {
         log.warn "'${it[0]}' might not be a pure isolate! Check screening results in the output folder."
+        if ( params.ignore_contamination_screen ) {
+            log.warn "Ignoring warning for '${it[0]}' (ignore_contamination_screen=true)."
+            passed = true
+        }
     }
     return passed
 }
@@ -299,6 +302,14 @@ process prokka {
         prokka_reference_argument = "--proteins ${params.prokka_reference}"
     }
     gram_stain_argument = ""
+    /* 
+     * If ignore_contamination_screen is used, gram_stain is a string with
+     * potentially several comma-separated gram stain assignments. We just
+     * use the first one.
+     */
+    if ( gram_stain.split(", ").size() > 1 ) {
+        gram_stain = gram_stain.split(", ")[0]
+    }
     if (gram_stain) {
         gram_stain_argument = "--gram ${gram_stain}"
     }

conf/ctmrnas.config

@@ -7,6 +7,7 @@ params {
 }
 
 process {
+    errorStrategy = 'ignore'
     executor = 'local'
     clusterOptions = {
       " -A ${params.project}" + (params.clusterOptions ?: '')
@@ -16,27 +17,27 @@ process {
     stageOutMode = 'copy'
 
     //Resource and module requirements
-    $screen_for_contaminants {
+    withName: screen_for_contaminants {
        cpus = 8
        time = 15.m
     }
-    $bbduk {
+    withName: bbduk {
        cpus = 4
        time = 15.m
     }
-    $fastqc {
+    withName: fastqc {
        cpus = 2
        time = 30.m
     }
-    $shovill {
+    withName: shovill {
        cpus = 8
        time = 1.h
     }
-    $prokka {
+    withName: prokka {
         cpus = 1
         time = 2.h
     }
-    $multiqc {
+    withName: multiqc {
         cpus = 1
         time = 10.m
     }

conf/local.config

@@ -1,33 +1,34 @@
 // vim: syntax=groovy expandtab
 // BACTpipe Nextflow configuration file
 process {
+    errorStrategy = 'ignore'
     executor = 'local'  
     scratch = true
     stageInMode = 'copy'
     stageOutMode = 'copy'
 
     //Resource and module requirements
-    $screen_for_contaminants {
+    withName: screen_for_contaminants {
         cpus = 1
         time = 20.m
     }
-    $bbduk {
+    withName: bbduk {
         cpus = 1
         time = 20.m
     }
-    $fastqc {
+    withName: fastqc {
         cpus = 1
         time = 40.m
     }
-    $shovill {
+    withName: shovill {
         cpus = 1
         time = 3.h
     }
-    $prokka {
+    withName: prokka {
          cpus = 1
          time = 2.h
     }
-    $multiqc {
+    withName: multiqc {
          cpus = 1
          time = 10.m
     }

conf/params.config

@@ -8,6 +8,7 @@ params {
     reads = ""  // Set on command line as e.g.: --reads 'path/to/*_R{1,2}.fastq.gz'
 
     mashscreen_database = ""  // Often set in specific profiles
+    ignore_contamination_screen = false
 
     bbduk_adapters = "adapters"  // Set to "adapters" to use adapters bundled with BBDuk
     bbduk_minlen = "30"

conf/rackham.config

@@ -6,6 +6,7 @@ params {
 }
 
 process {
+    errorStrategy = 'ignore'
     executor = 'slurm'
     clusterOptions = {
        " -A ${params.project}" + (params.clusterOptions ?: '')
@@ -16,36 +17,36 @@ process {
 
     //Resource and module requirements
 
-    $screen_for_contaminants {
-        module = 'python/3.6.0'
+    withName: screen_for_contaminants {
+        module = 'bioinfo-tools:mash/2.0:python/3.6.0'
         cpus = 2
         time = 30.m
     }
-    $bbduk {
+    withName: bbduk {
         module = 'bioinfo-tools:bbmap'
         cpus = 1
         memory = 8.GB
         time = 20.m
     }
-    $fastqc {
+    withName: fastqc {
         module = 'bioinfo-tools:FastQC'
         cpus = 2
         time = 40.m
         memory = 16.GB
     }
-    $shovill {
+    withName: shovill {
         module = 'bioinfo-tools:shovill/1.0.0'
         cpus = 16
         time = 3.h
         memory = 32.GB
     }
-    $prokka {
+    withName: prokka {
         module = 'bioinfo-tools:prokka/1.12-12547ca'
         cpus = 1
         time = 2.h
         memory = 8.GB
     }
-    $multiqc {
+    withName: multiqc {
         module = 'bioinfo-tools:MultiQC/1.5'
         cpus = 1
         time = 10.m

docs/source/conf.py

@@ -57,9 +57,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '2.6'
+version = '2.7'
 # The full version, including alpha/beta/rc tags.
-release = '2.6.0'
+release = '2.7.0'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/source/running.rst

@@ -48,27 +48,28 @@ when running BACTpipe, e.g.::
 The ``--bbduk_mink`` flag will modify the minimum kmer length for BBDuk. The 
 following parameters can be easily configured from the command line::
 
-    Parameter name        Default setting
-    output_dir            BACTpipe_results
-    reads                 [empty]  
-    mashscreen_database   Path to refseq minhash sketches for Mash screen
-    bbduk_adapters        [default BBDuk adapters]
-    bbduk_minlen          30
-    bbduk_qtrim           rl
-    bbduk_trimq           10
-    bbduk_ktrim           r
-    bbduk_k               30
-    bbduk_mink            11
-    bbduk_hdist           1
-    bbduk_trimbyoverlap   trimbyoverlap
-    bbduk_trimpairsevenly trimpairsevenly
-    shovill_depth         100
-    shovill_kmers         31,33,55,77,99,127
-    shovill_minlen        500
-    prokka_evalue         1e-09
-    prokka_kingdom        Bacteria
-    prokka_reference      [not used]
-    prokka_gram_stain     [not used]
+    Parameter name               Default setting
+    output_dir                   BACTpipe_results
+    reads                        [empty]
+    mashscreen_database          Path to refseq minhash sketches for Mash screen
+    ignore_contamination_screen  [false]
+    bbduk_adapters               [default BBDuk adapters]
+    bbduk_minlen                 30
+    bbduk_qtrim                  rl
+    bbduk_trimq                  10
+    bbduk_ktrim                  r
+    bbduk_k                      30
+    bbduk_mink                   11
+    bbduk_hdist                  1
+    bbduk_trimbyoverlap          trimbyoverlap
+    bbduk_trimpairsevenly        trimpairsevenly
+    shovill_depth                100
+    shovill_kmers                31,33,55,77,99,127
+    shovill_minlen               500
+    prokka_evalue                1e-09
+    prokka_kingdom               Bacteria
+    prokka_reference             [not used]
+    prokka_gram_stain            [not used]
 
 To modify any parameter, just add ``--<parameter_name> <new_setting>`` on the
 command line when running BACTpipe, e.g. ``--shovill_depth 75`` to set