Merge branch 'dev' into dev

LaurenceKuhl · Dec 14, 2023 · bfcc005 · bfcc005
2 parents 0e4573f + e0fd8d3
commit bfcc005
Show file tree

Hide file tree

Showing 12 changed files with 148 additions and 50 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -28,6 +28,7 @@ jobs:
           - "latest-everything"
         ANALYSIS:
           - "test_screening"
+          - "test_screening_paired"
           - "test_targeted"
           - "test_umis"
     steps:

diff --git a/conf/modules.config b/conf/modules.config
@@ -100,7 +100,6 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
         ext.prefix = 'count_table'
-
     }
 
     withName: MAGECK_MLE {
@@ -131,7 +130,12 @@ process {
     }
 
     withName: CUTADAPT {
-        ext.args = '-g file:overrepresented.fasta -N'
+        if(params.analysis == 'targeted') {
+            ext.args = '-g file:overrepresented.fasta -N'
+        }
+        if(params.analysis == 'screening' && params.cutadapt) {
+            ext.args = "-a ${params.cutadapt}"
+        }
         publishDir = [
             path: { "${params.outdir}/preprocessing/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
             mode: params.publish_dir_mode,

diff --git a/conf/test_screening_paired.config b/conf/test_screening_paired.config
@@ -0,0 +1,26 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/crisprseq -profile test_screening,<conda/docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test screening profile paired-end'
+    config_profile_description = 'Minimal test dataset to check pipeline function for paired-end data'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input             = 'https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/samplesheet_test_paired.csv'
+    analysis          = 'screening'
+    library           = "https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/brunello_target_sequence.txt"
+}
diff --git a/conf/test_targeted.config b/conf/test_targeted.config
@@ -25,4 +25,7 @@ params {
 
     // Aligner
     aligner = 'minimap2'
+
+    // Steps
+    overrepresented = true
 }
diff --git a/docs/output/screening.md b/docs/output/screening.md
@@ -16,6 +16,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 - [Preprocessing](#preprocessing)
   - [FastQC](#fastqc) - Read Quality Control
+  - [cutadapt](#cutadapt) - Trimming reads from fastq files
 - [Counting](#counting)
   - [MAGeCK count](#mageck-count) - Mapping reads to reference
 - [CNV correction](#cnv-correction))
@@ -42,6 +43,20 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
+### cutadapt
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `cutadapt/`
+  - `*.log`: log file of the command ran and the output
+  - `*.trim.fastq.gz`: trimmed fastq files
+
+</details>
+
+[cutadapt](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/). Cutadapt finds and removes adapter sequences, primers, poly-A tails and other types of unwanted sequence from your high-throughput sequencing reads. MAGeCK count normally automatically detects adapter sequences and trims, however if trimming lengths are different, cutadapt can be used, as mentioned [here](https://sourceforge.net/p/mageck/wiki/advanced_tutorial/).
+For further reading and documentation see the [cutadapt helper page](https://cutadapt.readthedocs.io/en/stable/guide.html).
+
 ## Counting
 
 ### MAGeCK count

diff --git a/docs/usage/screening.md b/docs/usage/screening.md
@@ -52,15 +52,17 @@ After the alignment step, the pipeline currently supports 3 algorithms to detect
 
 MAGeCK RRA performs robust ranking aggregation to identify genes that are consistently ranked highly across multiple replicate screens. To run MAGeCK rra, `--rra_contrasts` contains two columns : treatment and reference. These two columns should be separated with a dot comma (;) and contain the `csv` extension. You can also integrate several samples/conditions by comma separating them. Please find an example here below :
 
-| treatment               | reference           |
-| ----------------------- | ------------------- |
-| treatment1              | control1            |
-| treatment1,treatment2   | control1,control2   |
-| ----------------------- | ------------------- |
-| treatment1              | control1            |
+| reference         | treatment             |
+| ----------------- | --------------------- |
+| control1          | treatment1            |
+| control1,control2 | treatment1,treatment2 |
 
 A full example can be found [here](https://raw.githubusercontent.com/nf-core/test-datasets/crisprseq/testdata/full_test/samplesheet_full.csv).
 
+### cutadapt
+
+MAGeCK is normally able to automatically determine the trimming length and sgRNA length, in most cases. Therefore, you don't need to go to this step unless MAGeCK fails to do so by itself. If the nucleotide length in front of sgRNA varies between different reads, you can use cutadapt to remove the adaptor sequences by using the flag `--cutadapt ADAPTER`.
+
 ### MAGeCK mle
 
 MAGeCK MLE uses a maximum likelihood estimation approach to estimate the effects of gene knockout on cell fitness. It models the read count data of guide RNAs targeting each gene and estimates the dropout probability for each gene. MAGeCK mle requires a design matrix. The design matrix is a `txt` file indicating the effects of different conditions on different samples.

diff --git a/modules/nf-core/cutadapt/main.nf b/modules/nf-core/cutadapt/main.nf
diff --git a/modules/nf-core/mageck/count/mageck-count.diff b/modules/nf-core/mageck/count/mageck-count.diff
diff --git a/modules/nf-core/mageck/count/main.nf b/modules/nf-core/mageck/count/main.nf
diff --git a/nextflow.config b/nextflow.config
@@ -16,6 +16,7 @@ params {
     protospacer                = null
     library                    = null
     crisprcleanr               = null
+    cutadapt                   = null
     rra_contrasts              = null
     mle_design_matrix          = null
     count_table                = null
@@ -192,12 +193,13 @@ profiles {
         executor.cpus          = 4
         executor.memory        = 8.GB
     }
-    test                { includeConfig 'conf/test_targeted.config' }
-    test_targeted       { includeConfig 'conf/test_targeted.config' }
-    test_full           { includeConfig 'conf/test_full.config' }
-    test_umis           { includeConfig 'conf/test_umis.config' }
-    test_screening_full { includeConfig 'conf/test_screening_full.config' }
-    test_screening      { includeConfig 'conf/test_screening.config' }
+    test                  { includeConfig 'conf/test_targeted.config' }
+    test_targeted         { includeConfig 'conf/test_targeted.config' }
+    test_full             { includeConfig 'conf/test_full.config' }
+    test_umis             { includeConfig 'conf/test_umis.config' }
+    test_screening_full   { includeConfig 'conf/test_screening_full.config' }
+    test_screening        { includeConfig 'conf/test_screening.config' }
+    test_screening_paired { includeConfig 'conf/test_screening_paired.config' }
 }
 
 // Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -10,7 +10,7 @@
             "type": "object",
             "fa_icon": "fas fa-terminal",
             "description": "Define where the pipeline should find input data and save output data.",
-            "required": ["input", "outdir", "analysis"],
+            "required": ["outdir", "analysis"],
             "properties": {
                 "input": {
                     "type": "string",
@@ -183,6 +183,10 @@
                     "type": "string",
                     "description": "sgRNA library annotation for crisprcleanR"
                 },
+                "cutadapt": {
+                    "type": "string",
+                    "description": "cutadapt adapter for screening analysis"
+                },
                 "min_reads": {
                     "type": "number",
                     "description": "a filter threshold value for sgRNAs, based on their average counts in the control sample",

diff --git a/workflows/crisprseq_screening.nf b/workflows/crisprseq_screening.nf
@@ -55,6 +55,7 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil
 // MODULE: Installed directly from nf-core/modules
 //
 include { FASTQC                      } from '../modules/nf-core/fastqc/main'
+include { CUTADAPT                    } from '../modules/nf-core/cutadapt/main'
 include { MULTIQC                     } from '../modules/nf-core/multiqc/main'
 include { MAGECK_COUNT                } from '../modules/nf-core/mageck/count/main'
 include { MAGECK_MLE                  } from '../modules/nf-core/mageck/mle/main'
@@ -87,36 +88,70 @@ workflow CRISPRSEQ_SCREENING {
         Channel.fromSamplesheet("input")
         .map{ meta, fastq_1, fastq_2, x, y, z ->
             // x (reference), y (protospacer), and z (template) are part of the targeted workflows and we don't need them
-        return   [ meta + [ single_end:fastq_2?false:true ], fastq_2?[ fastq_1, fastq_2 ]:[ fastq_1 ] ]
-        }
+        return   [ meta + [ single_end:fastq_2?false:true ], fastq_2?[ fastq_1, fastq_2 ]:[ fastq_1 ] ]        }
         .set { ch_input }
 
+
         //
         // MODULE: Run FastQC
         //
         FASTQC (
             ch_input
         )
+        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
 
-        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+        empty_channel = Channel.value([[]])
+        ch_input_cutadapt = ch_input.combine(Channel.value([[]]))
 
+    if(params.cutadapt) {
+        CUTADAPT(
+            ch_input_cutadapt
+        )
+        ch_versions = ch_versions.mix(CUTADAPT.out.versions)
+
+        CUTADAPT.out.reads
+        .map{ meta, fastq  ->
+            [meta, [fastq]]
+        }
+        .set { ch_input }
+        }
+
+        // this is to concatenate everything for mageck count
 
         ch_input
-        .map { meta, fastq  ->
-            [meta.condition, fastq, meta.single_end]
+        .map { meta, fastqs  ->
+            if(fastqs.size() == 1){
+                [meta.condition, [fastqs[0]], meta.single_end, []]
+            } else {
+                [meta.condition, [fastqs[0]], meta.single_end, [fastqs[1]]]
+            }
         }
+        // if one element is paired-end and the other single-end throw an error
+        // otherwise just concatenate the conditions and the fastqs
         .reduce { a, b ->
             if(a[2] != b[2] ) {
                 error "Your samplesheet contains a mix of single-end and paired-end data. This is not supported."
             }
-            return ["${a[0]},${b[0]}", a[1] + b[1], b[2]]
+            return ["${a[0]},${b[0]}", a[1] + b[1], b[2] ,a[3] + b[3]]
         }
-        .map { condition, fastqs, single_end ->
-            [[id: condition, single_end: single_end], fastqs]
+        .map { condition, fastqs_1, single_end, fastqs_2 ->
+            [[id: condition, single_end: single_end], fastqs_1, fastqs_2]
         }
+        .last()
         .set { joined }
 
+        //
+        // MODULE: Run FastQC
+        //
+        FASTQC (
+            ch_input
+        )
+
+
+        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+
+
 
         //
         // MODULE: Run mageck count