review suggestions

genomic-medicine-sweden · Nov 14, 2024 · 42694e9 · 42694e9
1 parent 04cff8a
commit 42694e9
Show file tree

Hide file tree

Showing 9 changed files with 71 additions and 71 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -62,7 +62,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#411](https://github.com/genomic-medicine-sweden/nallo/pull/411) - Updated longphase module to most recent version. ([#409](https://github.com/genomic-medicine-sweden/nallo/issues/409)).
 - [#416](https://github.com/genomic-medicine-sweden/nallo/pull/416) - Updated WhatsHap to 2.3 and added the `--use-supplementary` flag to use supplementary reads for phasing by default. Changed modules to use biocontainers instead of custom containers. ([#296](https://github.com/genomic-medicine-sweden/nallo/issues/296))
 - [#417](https://github.com/genomic-medicine-sweden/nallo/pull/417) - Updated SNV annotation tests to use correct configuration, and snapshot the md5sum, and summary of the variants
-- [#418](https://github.com/genomic-medicine-sweden/nallo/pull/418) - Changed the default value of `--parallel_alignments` from 1 to 8, meaning the pipeline will perform parallel alignment by default
+- [#418](https://github.com/genomic-medicine-sweden/nallo/pull/418) - Changed the default value of `--alignment_processes` from 1 to 8, meaning the pipeline will perform parallel alignment by default
 - [#422](https://github.com/genomic-medicine-sweden/nallo/pull/422) - Updated nf-core/tools template to v3.0.1
 - [#423](https://github.com/genomic-medicine-sweden/nallo/pull/423) - Updated metro map
 - [#428](https://github.com/genomic-medicine-sweden/nallo/pull/428) - Changed from using bcftools to SVDB for SV merging
@@ -125,25 +125,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `--validationSkipDuplicateCheck` |                                   |
 | `--validationS3PathCheck`        |                                   |
 | `--monochromeLogs`               | `--monochrome_logs`               |
-| `skip_short_variant_calling`     | `skip_snv_calling`                |
-| `skip_assembly_wf`               | `skip_genome_assembly`            |
-| `skip_mapping_wf`                | `skip_alignment`                  |
-| `skip_methylation_wf`            | `skip_methylation_analysis`       |
-| `skip_phasing_wf`                | `skip_phasing`                    |
-| `variant_caller`                 | `snv_caller`                      |
-| `parallel_snv`                   | `snv_calling_processes`           |
-| `cadd_prescored`                 | `cadd_prescored_indels`           |
-| `snp_db`                         | `echtvar_snv_databases`           |
-| `variant_catalog`                | `stranger_repeat_catalog`         |
-| `bed`                            | `target_bed`                      |
-| `hificnv_xy`                     | `hificnv_expected_xy_cn`          |
-| `hificnv_xx`                     | `hificnv_expected_xx_cn`          |
-| `hificnv_exclude`                | `hificnv_excluded_regions`        |
-| `reduced_penetrance`             | `genmod_reduced_penetrance`       |
-| `score_config_snv`               | `genmod_score_config_snvs`        |
-| `score_config_sv`                | `genmod_score_config_svs`         |
-| `parallel_alignments`            | `alignment_processes`            |
-| `svdb_dbs`                       | `svdb_sv_databases`               |
+| `--skip_short_variant_calling`   | `--skip_snv_calling`              |
+| `--skip_assembly_wf`             | `--skip_genome_assembly`          |
+| `--skip_mapping_wf`              | `--skip_alignment`                |
+| `--skip_methylation_wf`          | `--skip_methylation_pileups`      |
+| `--skip_phasing_wf`              | `--skip_phasing`                  |
+| `--variant_caller`               | `--snv_caller`                    |
+| `--parallel_snv`                 | `--snv_calling_processes`         |
+| `--cadd_prescored`               | `--cadd_prescored_indels`         |
+| `--snp_db`                       | `--echtvar_snv_databases`         |
+| `--variant_catalog`              | `--stranger_repeat_catalog`       |
+| `--bed`                          | `--target_regions`                |
+| `--hificnv_xy`                   | `--hificnv_expected_xy_cn`        |
+| `--hificnv_xx`                   | `--hificnv_expected_xx_cn`        |
+| `--hificnv_exclude`              | `--hificnv_excluded_regions`      |
+| `--reduced_penetrance`           | `--genmod_reduced_penetrance`     |
+| `--score_config_snv`             | `--genmod_score_config_snvs`      |
+| `--score_config_sv`              | `--genmod_score_config_svs`       |
+| `--alignment_processes`          | `--alignment_processes`           |
+| `--svdb_dbs`                     | `--svdb_sv_databases`             |
 
 > [!NOTE]
 > Parameter has been updated if both old and new parameter information is present.
@@ -247,7 +247,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#317](https://github.com/genomic-medicine-sweden/nallo/pull/317) - Changed so that `--reduced_penetrance` and `--score_config_snv` is required by rank variants and not SNV annotation
 - [#318](https://github.com/genomic-medicine-sweden/nallo/pull/318) - Updated docs and schema to clarify pipeline usage
 - [#321](https://github.com/genomic-medicine-sweden/nallo/pull/321) - Changed the input to BUILD_INTERVALS to have `meta.id` when building intervals from reference
-- [#323](https://github.com/genomic-medicine-sweden/nallo/pull/323) - Changed `parallel_alignment` to `parallel_alignments` in CI tests as well
+- [#323](https://github.com/genomic-medicine-sweden/nallo/pull/323) - Changed `parallel_alignment` to `alignment_processes` in CI tests as well
 - [#330](https://github.com/genomic-medicine-sweden/nallo/pull/330) - Updated README and version bump
 - [#332](https://github.com/genomic-medicine-sweden/nallo/pull/332) - Changed the PED file input to genmod to include inferred sex from somalier
 - [#333](https://github.com/genomic-medicine-sweden/nallo/pull/333) - Updated TRGT to 0.7.0 and added `meta.id` as output sample name
@@ -282,7 +282,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 |                    | `--skip_aligned_read_qc`   |
 |                    | `--cadd_resources`         |
 |                    | `--cadd_prescored`         |
-| `--split_fastq`    | `--parallel_alignments`    |
+| `--split_fastq`    | `--alignment_processes`    |
 | `--extra_gvcfs`    |                            |
 | `--extra_snfs`     |                            |
 | `--dipcall_par`    | `--par_regions`            |

diff --git a/conf/modules/qc_aligned_reads.config b/conf/modules/qc_aligned_reads.config
@@ -41,7 +41,7 @@ process {
         ext.args = { [
             '--fast-mode',
             '--no-per-base',
-            params.target_bed ? '' : '--by 500'
+            params.target_regions ? '' : '--by 500'
         ].join(' ') }
         publishDir = [
             path: { "${params.outdir}/qc/mosdepth/${meta.id}" },

diff --git a/conf/test.config b/conf/test.config
@@ -23,7 +23,7 @@ params {
     // References
     fasta                     = params.pipelines_testdata_base_path + 'reference/hg38.test.fa.gz'
     input                     = params.pipelines_testdata_base_path + 'testdata/samplesheet.csv'
-    target_bed                = params.pipelines_testdata_base_path + 'reference/test_data.bed'
+    target_regions            = params.pipelines_testdata_base_path + 'reference/test_data.bed'
     hificnv_expected_xy_cn    = params.pipelines_testdata_base_path + 'reference/expected_cn.hg38.XY.bed'
     hificnv_expected_xx_cn    = params.pipelines_testdata_base_path + 'reference/expected_cn.hg38.XX.bed'
     hificnv_excluded_regions  = params.pipelines_testdata_base_path + 'reference/empty.bed'
@@ -37,7 +37,7 @@ params {
     genmod_reduced_penetrance = params.pipelines_testdata_base_path + 'reference/reduced_penetrance.tsv'
     genmod_score_config_snvs  = params.pipelines_testdata_base_path + 'reference/rank_model_snv.ini'
     genmod_score_config_svs   = params.pipelines_testdata_base_path + 'reference/rank_model_svs.ini'
-    variant_consequences_snv  = params.pipelines_testdata_base_path + 'reference/variant_consequences_v2.txt'
+    variant_consequences_snvs = params.pipelines_testdata_base_path + 'reference/variant_consequences_v2.txt'
     variant_consequences_svs  = params.pipelines_testdata_base_path + 'reference/variant_consequences_v2.txt'
     somalier_sites            = params.pipelines_testdata_base_path + 'reference/somalier_sites.vcf.gz'
 

diff --git a/docs/parameters.md b/docs/parameters.md
@@ -12,7 +12,7 @@ Allows skipping certain parts of the pipeline
 | `skip_snv_calling` | Skip short variant calling | `boolean` | False |  |  |
 | `skip_genome_assembly` | Skip genome assembly and assembly variant calling | `boolean` | False |  |  |
 | `skip_alignment` | Skip read mapping (alignment) | `boolean` | False |  |  |
-| `skip_methylation_analysis` | Skip generation of methylation pileups | `boolean` | False |  |  |
+| `skip_methylation_pileups` | Skip generation of methylation pileups | `boolean` | False |  |  |
 | `skip_repeat_calling` | Skip tandem repeat calling | `boolean` | False |  |  |
 | `skip_repeat_annotation` | Skip tandem repeat annotation | `boolean` | False |  |  |
 | `skip_phasing` | Skip phasing of variants and haplotagging of reads | `boolean` | False |  |  |
@@ -40,10 +40,10 @@ Define where the pipeline should find input data and save output data.
 | `echtvar_snv_databases` | A csv file with echtvar databases to annotate SNVs with | `string` |  |  |  |
 | `svdb_sv_databases` | Databases used for structural variant annotation in vcf format. <details><summary>Help</summary><small>Path to comma-separated file containing information about the databases used for structural variant annotation.</small></details>| `string` |  |  |  |
 | `stranger_repeat_catalog` | A variant catalog json-file for stranger | `string` |  |  |  |
-| `variant_consequences_snv` | File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SNVs. For more information check https://ensembl.org/info/genome/variation/prediction/predicted_data.html | `string` |  |  |  |
+| `variant_consequences_snvs` | File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SNVs. For more information check https://ensembl.org/info/genome/variation/prediction/predicted_data.html | `string` |  |  |  |
 | `variant_consequences_svs` | File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SVs. For more information check https://ensembl.org/info/genome/variation/prediction/predicted_data.html | `string` |  |  |  |
 | `vep_cache` | A path to the VEP cache location | `string` |  |  |  |
-| `bed` | A BED file with regions of interest, used to limit short variant calling. | `string` |  |  |  |
+| `target_regions` | A BED file with regions of interest, used to limit variant calling. | `string` |  |  |  |
 | `hificnv_expected_xy_cn` | A BED file containing expected copy number regions for XY samples. | `string` |  |  |  |
 | `hificnv_expected_xx_cn` | A BED file containing expected copy number regions for XX samples. | `string` |  |  |  |
 | `hificnv_excluded_regions` | A BED file specifying regions to exclude with HiFiCNV, such as centromeres. | `string` |  |  |  |

diff --git a/docs/usage.md b/docs/usage.md
@@ -89,7 +89,7 @@ This pipeline comes with three different presets that should be set with the `--
     The selected preset will turn off subworkflows:
 
     - `--skip_genome_assembly` and `--skip_repeat_wf` will be set to `true` for `ONT_R10`
-    - `--skip_methylation_analysis` will be set to `true` for `pacbio`
+    - `--skip_methylation_pileups` will be set to `true` for `pacbio`
 
 ## Subworkflows
 
@@ -117,7 +117,7 @@ For example, `nextflow run genomic-medicine-sweden/nallo -profile docker --outdi
 
 ```
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-  --skip_alignment is active, the pipeline has to be run with: --skip_qc --skip_genome_assembly --skip_call_paralogs --skip_snv_calling --skip_snv_annotation --skip_cnv_calling --skip_phasing --skip_rank_variants --skip_repeat_calling --skip_repeat_annotation --skip_methylation_analysis
+  --skip_alignment is active, the pipeline has to be run with: --skip_qc --skip_genome_assembly --skip_call_paralogs --skip_snv_calling --skip_snv_annotation --skip_cnv_calling --skip_phasing --skip_rank_variants --skip_repeat_calling --skip_repeat_annotation --skip_methylation_pileups
   ...
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 ```
@@ -202,7 +202,7 @@ Turned off with `--skip_phasing`.
 
 This subworkflow relies on mapping and short variant calling subworkflows, but requires no additional files.
 
-Turned off with `--skip_methylation_analysis`.
+Turned off with `--skip_methylation_pileups`.
 
 ### Repeat calling
 
@@ -228,14 +228,14 @@ Turned off with `--skip_repeat_annotation`.
 
 This subworkflow relies on the mapping and short variant calling, and requires the following additional files:
 
-<!-- TODO: genmod_score_config_snvs, genmod_reduced_penetrance and variant_consequences_snv should link to real examples -->
+<!-- TODO: genmod_score_config_snvs, genmod_reduced_penetrance and variant_consequences_snvs should link to real examples -->
 
 | Parameter                            | Description                                                                                                                                                                                                                                                                                                                                                                   |
 | ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `vep_cache`                          | VEP cache matching your reference genome, either as a `.tar.gz` archive or path to a directory (e.g. [homo_sapiens_vep_110_GRCh38.tar.gz](https://ftp.ensembl.org/pub/release-110/variation/vep/homo_sapiens_vep_110_GRCh38.tar.gz))                                                                                                                                          |
 | `vep_plugin_files` <sup>1</sup>      | A csv file with VEP plugin files, pLI and LoFtool are required. Example provided below.                                                                                                                                                                                                                                                                                       |
 | `echtvar_snv_databases` <sup>2</sup> |  A csv file with annotation databases from ([`echtvar encode`](https://github.com/brentp/echtvar))                                                                                                                                                                                                                                                                            |
-| `variant_consequences_snv`           | A list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://ensembl.org/info/genome/variation/prediction/predicted_data.html) |
+| `variant_consequences_snvs`          | A list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic and mitochondrial SNVs. Sample file [here](https://github.com/nf-core/test-datasets/blob/raredisease/reference/variant_consequences_v2.txt). You can learn more about these terms [here](https://ensembl.org/info/genome/variation/prediction/predicted_data.html) |
 
 <sup>1</sup> Example file for input with `--vep_plugin_files`
 
@@ -311,7 +311,7 @@ This subworkflow ranks SVs, and relies on the mapping, SV calling and SV annotat
 
 ## Other highlighted parameters
 
-- Limit SNV calling to regions in BED file (`--bed`).
+- Limit SNV calling to regions in BED file (`--target_bed`).
 - By default SNV-calling is split into 13 parallel processes, this speeds up the variant calling significantly. Limit this by setting `--snv_calling_processes` to a different number.
 - By default the pipeline splits the input files into eight pieces, performs parallel alignment and then merges the files. This can be changed to a different number with `--alignment_processes`, or turned off by supplying a value of 1. Parallel alignment comes with some additional overhead, but can speed up the pipeline significantly.
 

diff --git a/nextflow.config b/nextflow.config
@@ -11,7 +11,7 @@ params {
 
     // Input options
     input                        = null
-    target_bed                   = null
+    target_regions                   = null
     cadd_resources               = null
     cadd_prescored_indels        = null
     par_regions                  = null
@@ -23,7 +23,7 @@ params {
     genmod_score_config_svs      = null
     echtvar_snv_databases        = null
     svdb_sv_databases            = null
-    variant_consequences_snv     = null
+    variant_consequences_snvs     = null
     variant_consequences_svs     = null
     vep_cache                    = null
     vep_plugin_files             = null
@@ -37,7 +37,7 @@ params {
     skip_call_paralogs           = false
     skip_cnv_calling             = false
     skip_alignment               = false
-    skip_methylation_analysis    = params.preset == 'pacbio' ? true : false
+    skip_methylation_pileups    = params.preset == 'pacbio' ? true : false
     skip_phasing                 = false
     skip_qc                      = false
     skip_rank_variants           = false

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -35,7 +35,7 @@
                     "fa_icon": "fas fa-fast-forward",
                     "default": false
                 },
-                "skip_methylation_analysis": {
+                "skip_methylation_pileups": {
                     "type": "boolean",
                     "description": "Skip generation of methylation pileups",
                     "fa_icon": "fas fa-fast-forward",
@@ -184,7 +184,7 @@
                     "format": "file-path",
                     "exists": true
                 },
-                "variant_consequences_snv": {
+                "variant_consequences_snvs": {
                     "type": "string",
                     "description": "File containing list of SO terms listed in the order of severity from most severe to lease severe for annotating genomic SNVs. For more information check https://ensembl.org/info/genome/variation/prediction/predicted_data.html",
                     "fa_icon": "fas fa-file-csv"
@@ -200,7 +200,7 @@
                     "format": "path",
                     "exists": true
                 },
-                "target_bed": {
+                "target_regions": {
                     "type": "string",
                     "pattern": "^\\S+\\.bed$",
                     "format": "file-path",
@@ -465,7 +465,7 @@
                 "vep_plugin_files": {
                     "type": "string",
                     "mimetype": "text/csv",
-                    "description": "A csv file with vep_plugin_files as header, and then paths to vep plugin files. Paths to pLI_values.txt and LoFtool_scores.txt are required.",
+                    "description": "A csv file with vep_files as header, and then paths to vep plugin files. Paths to pLI_values.txt and LoFtool_scores.txt are required.",
                     "schema": "assets/vep_plugin_files_schema.json"
                 },
                 "deepvariant_model_type": {