Merge pull request #165 from Plant-Food-Research-Open/hic/filter

Added parameter `hic_samtools_ext_args`
Plant-Food-Research-Open · Oct 25, 2024 · 26025a4 · 26025a4
2 parents abd4695 + c1f83cc
commit 26025a4
Show file tree

Hide file tree

Showing 6 changed files with 24 additions and 8 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 4. Now using nf-test for pipeline level testing [#153](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/153)
 5. Added `text/html` as content mime type for the report file [#146](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/146)
 6. Added a sequence labels table below the HiC contact map [#147](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/147)
+7. Added parameter `hic_samtools_ext_args` and set its default value to `-F 3852` [#159](https://github.com/Plant-Food-Research-Open/assemblyqc/issues/159)
 
 ### `Fixed`
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -328,7 +328,10 @@ process {
 
     withName: '.*:FQ2HIC:FASTQ_BWA_MEM_SAMBLASTER:SAMBLASTER' {
         ext.prefix = { "${meta.id}.on.${meta.ref_id}.samblaster" }
-        ext.args3 = '-h -F 2316'
+        ext.args3 = [
+            '-h',
+            params.hic_samtools_ext_args ? params.hic_samtools_ext_args.split("\\s(?=-+)") : ''
+        ].flatten().unique(false).join(' ').trim()
     }
 
     withName: '.*:FQ2HIC:AGP2ASSEMBLY' {

diff --git a/docs/parameters.md b/docs/parameters.md
@@ -67,12 +67,13 @@ A Nextflow pipeline which evaluates assembly quality with multiple QC tools and
 
 ## HiC options
 
-| Parameter            | Description                                                                              | Type      | Default                                           | Required | Hidden |
-| -------------------- | ---------------------------------------------------------------------------------------- | --------- | ------------------------------------------------- | -------- | ------ |
-| `hic`                | HiC reads path provided as a SRA ID or as paired reads such as 'hic_reads{1,2}.fastq.gz' | `string`  |                                                   |          |        |
-| `hic_skip_fastp`     | Skip HiC read trimming                                                                   | `boolean` |                                                   |          |        |
-| `hic_skip_fastqc`    | Skip HiC read QC                                                                         | `boolean` |                                                   |          |        |
-| `hic_fastp_ext_args` | Additional parameters for fastp trimming                                                 | `string`  | --qualified_quality_phred 20 --length_required 50 |          |        |
+| Parameter               | Description                                                                              | Type      | Default                                           | Required | Hidden |
+| ----------------------- | ---------------------------------------------------------------------------------------- | --------- | ------------------------------------------------- | -------- | ------ |
+| `hic`                   | HiC reads path provided as a SRA ID or as paired reads such as 'hic_reads{1,2}.fastq.gz' | `string`  |                                                   |          |        |
+| `hic_skip_fastp`        | Skip HiC read trimming                                                                   | `boolean` |                                                   |          |        |
+| `hic_skip_fastqc`       | Skip HiC read QC                                                                         | `boolean` |                                                   |          |        |
+| `hic_fastp_ext_args`    | Additional parameters for fastp trimming                                                 | `string`  | --qualified_quality_phred 20 --length_required 50 |          |        |
+| `hic_samtools_ext_args` | Additional parameters for samtools view command run after samblaster                     | `string`  | -F 3852                                           |          |        |
 
 ## Synteny options
 

diff --git a/nextflow.config b/nextflow.config
@@ -53,6 +53,7 @@ params {
     hic_skip_fastp                      = false
     hic_skip_fastqc                     = false
     hic_fastp_ext_args                  = '--qualified_quality_phred 20 --length_required 50'
+    hic_samtools_ext_args               = '-F 3852'
 
     // Synteny options
     synteny_skip                        = true

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -237,6 +237,12 @@
                     "default": "--qualified_quality_phred 20 --length_required 50",
                     "description": "Additional parameters for fastp trimming",
                     "fa_icon": "fas fa-terminal"
+                },
+                "hic_samtools_ext_args": {
+                    "type": "string",
+                    "default": "-F 3852",
+                    "fa_icon": "fas fa-terminal",
+                    "description": "Additional parameters for samtools view command run after samblaster"
                 }
             }
         },

diff --git a/tests/README.md b/tests/README.md
@@ -16,7 +16,11 @@ nextflow run plant-food-research-open/assemblyqc -r main -profile singularity,te
 
 ## nf-test and Continuous Integration (CI)
 
-The GitHub [CI action](../.github/workflows/ci.yml) included with the pipeline continuously tests the pipeline using [nf-test](https://www.nf-test.com).
+The GitHub [CI action](../.github/workflows/ci.yml) included with the pipeline continuously tests the pipeline using [nf-test](https://www.nf-test.com). Many components included with the pipeline such as [minimap2/align](../modules/nf-core/minimap2/align) include their own [tests](../modules/nf-core/minimap2/align/tests/main.nf.test) with test data from nf-core.
+
+## Testing with a Large Dataset at Plant&Food
+
+Before each release, the functionality of the entire pipeline is tested with a large dataset on the on-prem SLURM-based HPC at The New Zealand Institute of Plant and Food Research.
 
 ## Testing Merqury Datasets