Merge pull request #20 from Aratz/dev

Implement tagging system

Author: Aratz

CHANGELOG.md

@@ -9,6 +9,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 
 ### `Added`
 
+- [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 
 ### `Fixed`

README.md

@@ -44,8 +44,8 @@ First, prepare a samplesheet with your input data that looks as follows:
 `samplesheet.csv`:
 
 ```csv
-sample,lane,group,fastq_1,fastq_2,rundir
-CONTROL_REP1,1,GROUP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX
+sample,fastq_1,fastq_2,rundir,tags
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,200624_A00834_0183_BHMTFYDRXX,lane1:project5:group2
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).

assets/samplesheet.csv

@@ -1,3 +1,7 @@
-sample,lane,group,fastq_1,fastq_2,rundir
-SAMPLE_PAIRED_END,1,P001,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir
-SAMPLE_SINGLE_END,2,P002,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir
+sample,fastq_1,fastq_2,rundir,tags
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A2_S2_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A2_S2_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane1
+SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A3_S3_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A3_S3_L002_R2_001.fastq.gz,/path/to/rundir,paired_sample:lane2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group1
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group2
+SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,,/path/to/rundir,group3

assets/schema_input.json

@@ -13,18 +13,6 @@
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["sample"]
             },
-            "lane": {
-                "type": "integer",
-                "pattern": "^\\d+$",
-                "errorMessage": "Lane ID must be a number",
-                "meta": ["lane"]
-            },
-            "group": {
-                "type": "string",
-                "pattern": "^\\S+$",
-                "errorMessage": "Group ID cannot contain spaces",
-                "meta": ["group"]
-            },
             "fastq_1": {
                 "type": "string",
                 "format": "file-path",
@@ -45,6 +33,12 @@
                 "exists": true,
                 "errorMessage": "Run directory must be a path",
                 "meta": ["rundir"]
+            },
+            "tags": {
+                "type": "string",
+                "pattern": "^([A-Za-z0-9_-]+:)*([A-Za-z0-9_-]+)$",
+                "errorMessage": "Tags must be separated by colons and only consist of lowercase letters, numbers, underscores and hyphens.",
+                "meta": ["tags"]
             }
         },
         "required": ["sample", "fastq_1"],

conf/modules.config

@@ -25,79 +25,29 @@ process {
     withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
-            path: { "${params.outdir}/multiqc" },
+            path: { "${params.outdir}/multiqc/global_report" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
-    withName: 'MULTIQC_PER_LANE' {
+    withName: 'MULTIQC_PER_TAG' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [
-            path: { "${params.outdir}/multiqc/lanes" },
+            path: { "${params.outdir}/multiqc/group_reports" },
             mode: params.publish_dir_mode,
             saveAs: {
                 filename ->
                     switch (filename) {
                         case 'versions.yml':
                             null
                             break
-                        case ~/\[LANE:\d+\]_multiqc_(report\.html|plots|data)/:
-                            def lane = (filename =~ /\[LANE:(\d+)\]_multiqc_(report\.html|plots|data)/)[0][1]
+                        case ~/\[TAG:.+\]_multiqc_(report\.html|plots|data)/:
+                            def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
                             def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[LANE:${lane}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
+                                "(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
                                 '${prefix}${suffix}')
-                            "L${lane}/${new_filename}"
-                            break
-                        default:
-                            filename
-                    }
-            }
-        ]
-    }
-
-    withName: 'MULTIQC_PER_GROUP' {
-        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
-        publishDir = [
-            path: { "${params.outdir}/multiqc/groups" },
-            mode: params.publish_dir_mode,
-            saveAs: {
-                filename ->
-                    switch (filename) {
-                        case 'versions.yml':
-                            null
-                            break
-                        case ~/\[GROUP:.+\]_multiqc_(report\.html|plots|data)/:
-                            def group = (filename =~ /\[GROUP:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
-                            def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[GROUP:${group}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
-                                '${prefix}${suffix}')
-                            "${group}/${new_filename}"
-                            break
-                        default:
-                            filename
-                    }
-            }
-        ]
-    }
-
-    withName: 'MULTIQC_PER_RUNDIR' {
-        ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
-        publishDir = [
-            path: { "${params.outdir}/multiqc/rundirss" },
-            mode: params.publish_dir_mode,
-            saveAs: {
-                filename ->
-                    switch (filename) {
-                        case 'versions.yml':
-                            null
-                            break
-                        case ~/\[RUNDIR:.+\]_multiqc_(report\.html|plots|data)/:
-                            def rundir = (filename =~ /\[RUNDIR:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
-                            def new_filename = filename.replaceFirst(
-                                "(?<prefix>.*)\\[RUNDIR:${rundir}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
-                                '${prefix}${suffix}')
-                            "${rundir}/${new_filename}"
+                            "${tag}/${new_filename}"
                             break
                         default:
                             filename

conf/test.config

@@ -22,7 +22,7 @@ params {
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/MiSeq/samplesheet.csv'
+    input  = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
 
     // Genome references
     genome = 'R64-1-1'

docs/output.md

@@ -39,36 +39,29 @@ The FastQC plots displayed in the MultiQC report shows _untrimmed_ reads. They m
 
 ### MultiQC
 
+nf-core/seqinspector will generate the following MultiQC reports:
+
+- one global reports including all the samples listed in the samplesheet
+- one group report per unique tag. These reports compile samples that share the same tag.
+
 <details markdown="1">
 <summary>Output files</summary>
 
 - `multiqc/`
-  - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-  - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-  - `multiqc_plots/`: directory containing static images from the report in various formats.
-  - `lanes/` [1]
-    - `L1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `L2/`
-      - ...
-  - `groups/` [1]
-    - `GROUPNAME1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `GROUPNAME2/`
-      - ...
-  - `rundir/` [1]
-    - `RUNDIR1/`
-      - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
-      - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
-      - `multiqc_plots/`: directory containing static images from the report in various formats.
-    - `RUNDIR2/`
-      - ...
-
-[1] These files will only be generated if `lane`, `group` or `rundir` were specified for some samples.
+  - `global_report`
+    - `multiqc_report.html`: a standalone HTML file that can be viewed in your web browser.
+    - `multiqc_data/`: directory containing parsed statistics from the different tools used in the pipeline.
+    - `multiqc_plots/`: directory containing static images from the report in various formats.
+  - `group_reports`
+    - `tag1/`
+      - `multiqc_report.html`
+      - `multiqc_data/`
+      - `multiqc_plots/`
+    - `tag2/`
+      - `multiqc_report.html`
+      - `multiqc_data/`
+      - `multiqc_plots/`
+    - ...
 
 </details>
 

docs/usage.md

@@ -31,22 +31,21 @@ run_dir
 ...would be represented in the following samplesheet (shown as .tsv for readability)
 
 ```csv title="samplesheet.csv"
-sample  lane  group   fastq_1                                       fastq_2 rundir
-sample1 1     group1  path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir
-sample2 1     group1  path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir
-sample3 2     group2  path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir
-sample4 2     group3  path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir
+sample  fastq_1                                       fastq_2 rundir          tags
+sample1 path/to/run_dir/sample1_lane1_group1_r1.fq.gz         path/to/run_dir project1:group1
+sample2 path/to/run_dir/sample2_lane1_group1_r1.fq.gz         path/to/run_dir project1:group1
+sample3 path/to/run_dir/sample3_lane2_group2_r1.fq.gz         path/to/run_dir project1:group2
+sample4 path/to/run_dir/sample4_lane2_group3_r1.fq.gz         path/to/run_dir control
 
 ```
 
 | Column    | Description                                                                                                                                                                            |
 | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `sample`  | Custom sample name. This entry will be identical for multiple sequencing libraries/runs from the same sample. Spaces in sample names are automatically converted to underscores (`_`). |
-| `lane`    | Lane where the sample was processed on an Illumina instrument (optional).                                                                                                              |
-| `group`   | Group the sample belongs too, useful when several groups are pooled together (optional).                                                                                               |
 | `fastq_1` | Full path to FastQ file for Illumina short reads 1. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz".                                                             |
 | `fastq_2` | Full path to FastQ file for Illumina short reads 2. File has to be gzipped and have the extension ".fastq.gz" or ".fq.gz" (optional).                                                  |
-| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional) .                                                                                               |
+| `rundir`  | Path to the runfolder containing extra information about the sequencing run (optional).                                                                                                |
+| `tags`    | Colon-separated list of tags to group samples in special reports.                                                                                                                      |
 
 Another [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 

main.nf

@@ -58,10 +58,8 @@ workflow NFCORE_SEQINSPECTOR {
     )
 
     emit:
-    global_report = SEQINSPECTOR.out.global_report  // channel: /path/to/multiqc_report.html
-    lane_reports  = SEQINSPECTOR.out.lane_reports   // channel: /path/to/multiqc_report.html
-    group_reports = SEQINSPECTOR.out.group_reports  // channel: /path/to/multiqc_report.html
-    rundir_report = SEQINSPECTOR.out.rundir_reports // channel: /path/to/multiqc_report.html
+    global_report   = SEQINSPECTOR.out.global_report    // channel: /path/to/multiqc_report.html
+    grouped_reports = SEQINSPECTOR.out.grouped_reports  // channel: /path/to/multiqc_report.html
 
 }
 /*

modules.json

@@ -12,7 +12,7 @@
                     },
                     "multiqc": {
                         "branch": "master",
-                        "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
+                        "git_sha": "19ca321db5d8bd48923262c2eca6422359633491",
                         "installed_by": ["modules"]
                     }
                 }