Add nonpareil

nf-core · jfy133 · Nov 30, 2023 · Nov 9, 2023 · Nov 10, 2023 · Nov 13, 2023
commit a050658cf99d0a6cbece4d6a577acc84b15d69a7
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,6 +13,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Dependencies`
 
+| Tool    | Previous version | New version |
+| ------- | ---------------- | ----------- |
+| multiqc | 1.15             | 1.18        |
+
 ### `Deprecated`
 
 ## v1.1.2 - Augmented Akita Patch [2023-10-27]

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -10,6 +10,44 @@ report_section_order:
     order: -1001
   "nf-core-taxprofiler-summary":
     order: -1002
+  general_stats":
+    order: 1000
+  fastqc:
+    order: 900
+  fastqc-1:
+    order: 800
+  fastp:
+    order: 700
+  adapterRemoval:
+    order: 600
+  nonpareil_all_samples:
+    order: 500
+  porechop:
+    order: 400
+  bbduk:
+    order: 300
+  prinseqplusplus:
+    order: 200
+  filtlong:
+    order: 100
+  bowtie2:
+    order: 90
+  samtools:
+    order: 80
+  kraken:
+    order: 70
+  bracken:
+    order: 60
+  centrifuge:
+    order: 50
+  malt:
+    order: 40
+  diamond:
+    order: 30
+  kaiju:
+    order: 20
+  motus:
+    order: 10
 
 export_plots: true
 
@@ -21,6 +59,7 @@ run_modules:
   - fastqc
   - adapterRemoval
   - fastp
+  - custom_content
   - bbduk
   - prinseqplusplus
   - porechop
@@ -33,7 +72,6 @@ run_modules:
   - diamond
   - malt
   - motus
-  - custom_content
 
 sp:
   diamond:
@@ -42,6 +80,13 @@ sp:
     fn_re: ".*(fastqc|falco)_data.txt$"
   fastqc/zip:
     fn: "*_fastqc.zip"
+  nonpareil_all_samples_mqc:
+    fn: "nonpareil_all_samples_mqc.png"
+
+custom_data:
+  nonpareil_all_samples:
+    section_name: "Nonpareil"
+    description: "Nonpareil uses the redundancy of the reads in metagenomic datasets to estimate the average coverage and predict the amount of sequences that will be required to achieve “nearly complete coverage”. Plots here are not interactive - being exported directly from the tool. If you have difficulty reading the plot, please see the individual PNG files in the results directory. DOI: https://doi.org/10.1128/mSystems.00039-18"
 
 top_modules:
   - "fastqc":
@@ -58,13 +103,8 @@ top_modules:
       path_filters_exclude:
         - "*raw*"
       extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith."
-  - "fastp"
-  - "adapterRemoval"
   - "porechop":
       extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop did not detect any adapters and therefore no statistics generated."
-  - "bbduk"
-  - "prinseqplusplus"
-  - "filtlong"
   - "bowtie2":
       name: "bowtie2"
   - "samtools":
@@ -93,12 +133,11 @@ top_modules:
         - "*.centrifuge.txt"
   - "malt":
       name: "MALT"
-  - "diamond"
   - "kaiju":
       name: "Kaiju"
-  - "motus"
 
-#It is not possible to set placement for custom kraken and centrifuge columns.
+# It is not possible to set placement for custom kraken
+# and centrifuge columns.
 
 table_columns_placement:
   FastQC / Falco (pre-Trimming):

diff --git a/conf/modules.config b/conf/modules.config
@@ -182,7 +182,7 @@ process {
     }
 
     // Redundancy estimation with nonpareil
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.prefix = { "${meta.id}_${meta.run_accession}" }
         publishDir = [
             path: { "${params.outdir}/nonpareil/" },
@@ -191,6 +191,24 @@ process {
         ]
     }
 
+    withName: 'NONPAREIL_CURVE' {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/nonpareil/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.png'
+        ]
+    }
+
+    withName: 'NONPAREIL_SET' {
+        ext.prefix = { "nonpareil_all_samples_mqc" }
+        publishDir = [
+            path: { "${params.outdir}/nonpareil/" },
+            mode: params.publish_dir_mode,
+            pattern: '*.png'
+        ]
+    }
+
     // AdapterRemoval separate output merging
     withName: CAT_FASTQ {
         ext.prefix = { "${meta.id}_${meta.run_accession}" }

diff --git a/conf/test.config b/conf/test.config
@@ -62,7 +62,7 @@ process {
     withName: MEGAN_RMA2INFO_KRONA {
         maxForks = 1
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_adapterremoval.config b/conf/test_adapterremoval.config
@@ -50,7 +50,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_bbduk.config b/conf/test_bbduk.config
@@ -49,7 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_falco.config b/conf/test_falco.config
@@ -49,7 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_fastp.config b/conf/test_fastp.config
@@ -51,7 +51,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_krakenuniq.config b/conf/test_krakenuniq.config
@@ -65,7 +65,7 @@ process {
     withName: MEGAN_RMA2INFO_KRONA {
         maxForks = 1
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_malt.config b/conf/test_malt.config
@@ -51,7 +51,7 @@ process {
     withName: MALT_RUN {
         maxForks = 1
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_motus.config b/conf/test_motus.config
@@ -55,7 +55,7 @@ process {
     withName: MALT_RUN {
         maxForks = 1
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_nopreprocessing.config b/conf/test_nopreprocessing.config
@@ -50,7 +50,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_noprofiling.config b/conf/test_noprofiling.config
@@ -50,7 +50,7 @@ process {
         maxForks = 1
     }
 
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_nothing.config b/conf/test_nothing.config
@@ -49,7 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/conf/test_prinseqplusplus.config b/conf/test_prinseqplusplus.config
@@ -49,7 +49,7 @@ process {
         maxForks = 1
         ext.args = { "-m ${params.malt_mode} -J-Xmx12G" }
     }
-    withName: NONPAREIL {
+    withName: NONPAREIL_NONPAREIL {
         ext.args = { "-k 5" }
     }
 }
diff --git a/docs/output.md b/docs/output.md
@@ -131,10 +131,14 @@ Turns on [nonpareil](https://nonpareil.readthedocs.io/en/latest/) is a tool for
   - `<sample_id>.npo` - redundancy summary file. This is the most useful file and contains the information for generating metagenome coverage curves. These six columns are: seq. effort (_n_ reads), average redundancy, standard deviation, quartile 1, median (quartile 2), and quartile 3.
   - `<sample_id>.npa` - raw version of npo but with all replicates not just a summary (average) at each point. These three columns are: seq. effort (_n_ reads), replicate ID, redundancy value.
   - `<sample_id>.npc` - raw list with the number of reads in the dataset matching a query read.
+  - `<sample_id>.png` - rendered version of a Nonpareil curve, with extrapolation and sequencing effort information.
+  - `nonpareil_all_samples_mqc.png` summary of plot of curves of all samples with sequencing effort information.
 
   </details>
 
-  In most cases you will just want to look at the output of applying Nonpareil's `Nonpareil.curve()` or `Nonpareil.set()` R functions on the `.npo` file to generate the coverage and extrapolation plot.
+  In most cases you will just want to look at the PNG files which contain the extrapolation information for estimating how much of the metagenome 'coverage' you will recover if you sequence more (i.e., to help indicate at what point you will keep just keep sequencing redundant reads that provide no more new taxonomic information).
+
+  The `.npo` files can be used for re-generating and customising the plots using the companion `Nonpareil` R package.
 
 ### Porechop
 

diff --git a/docs/usage.md b/docs/usage.md
@@ -272,7 +272,7 @@ If this is the case you will need to specify in a custom config
 
 ```nextflow
 process {
-  withName: NONPAREIL {
+  withName: NONPAREIL_NONPAREIL {
     ext.args = { "-k <NUMBER>" }
     }
 }

diff --git a/lib/WorkflowTaxprofiler.groovy b/lib/WorkflowTaxprofiler.groovy
@@ -67,7 +67,7 @@ class WorkflowTaxprofiler {
             ].join(' ').trim()
 
             def text_shortread_redundancy = [
-                "Short-read reference-free metagenome coverage estimation was performed with Nonpareil (Rodriguez-R et al. 2018)"
+                "Short-read reference-free metagenome coverage estimation was performed with Nonpareil (Rodriguez-R et al. 2018)."
             ].join(' ').trim()
 
             def text_longread_qc = [

diff --git a/modules.json b/modules.json
@@ -198,12 +198,22 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "a6e11ac655e744f7ebc724be669dd568ffdc0e80",
+                        "git_sha": "1537442a7be4a78efa3d1ff700a923c627bbda5d",
                         "installed_by": ["modules"]
                     },
-                    "nonpareil": {
+                    "nonpareil/curve": {
                         "branch": "master",
-                        "git_sha": "d1e3f0e70e025bb2c48f59465db31609330a65f2",
+                        "git_sha": "729335dda8ba226323edc54dec80ae959079207e",
+                        "installed_by": ["modules"]
+                    },
+                    "nonpareil/nonpareil": {
+                        "branch": "master",
+                        "git_sha": "56ace4ddc46f6346656d5d791782aca9b1754aea",
+                        "installed_by": ["modules"]
+                    },
+                    "nonpareil/set": {
+                        "branch": "master",
+                        "git_sha": "729335dda8ba226323edc54dec80ae959079207e",
                         "installed_by": ["modules"]
                     },
                     "porechop/porechop": {

diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml
diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf
diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml