add back regulatory

genomic-medicine-sweden · Oct 11, 2024 · 6f8ef42 · 6f8ef42
1 parent 00f48d2
commit 6f8ef42
Show file tree

Hide file tree

Showing 5 changed files with 20 additions and 49 deletions.
diff --git a/assets/svdb_query_vcf_schema.json b/assets/svdb_query_vcf_schema.json
@@ -1,5 +1,5 @@
 {
-    "$schema": "http://json-schema.org/draft-07/schema",
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
     "$id": "https://raw.githubusercontent.com/nf-core/raredisease/master/assets/mobile_element_references_schema.json",
     "title": "Schema for SVDB query - VCF",
     "description": "Schema for the SVDB query database input, VCF version",

diff --git a/conf/modules/annotate_svs.config b/conf/modules/annotate_svs.config
@@ -34,7 +34,7 @@ process {
             '--exclude_predicted --force_overwrite --format vcf',
             '--hgvs --humdiv --max_sv_size 248387328',
             '--no_progress --numbers --per_gene --polyphen p',
-            '--protein --offline --sift p', // Add back regulatory with VEP 113
+            '--protein --offline --sift p --regulatory',
             '--symbol --tsl --uniprot --vcf',
             '--no_stats'
         ].join(' ') }

diff --git a/conf/test.config b/conf/test.config
@@ -10,14 +10,6 @@
 ----------------------------------------------------------------------------------------
 */
 
-process {
-    resourceLimits = [
-        cpus: 4,
-        memory: '15.GB',
-        time: '1.h'
-    ]
-}
-
 params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
@@ -60,7 +52,7 @@ params {
 
 // Impose same minimum Nextflow version as in nextflow.config
 manifest {
-    nextflowVersion = '!>=23.04.0'
+    nextflowVersion = '!>=24.04.2'
 }
 
 // Disable all Nextflow reporting options
@@ -70,16 +62,25 @@ trace    { enabled = false }
 dag      { enabled = false }
 
 process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
     withLabel: 'process_high' {
         cpus = 4
+        memory = '15.GB'
     }
     withLabel: 'process_medium' {
         cpus = 2
+        memory = '7.GB'
     }
     withLabel: 'process_low' {
         cpus = 1
+        memory = '3.GB'
     }
     withLabel: 'process_single' {
         cpus = 1
+        memory = '3.GB'
     }
 }
diff --git a/docs/parameters.md b/docs/parameters.md
@@ -38,6 +38,7 @@ Define where the pipeline should find input data and save output data.
 | `tandem_repeats` | A tandem repeat BED file for sniffles | `string` |  |  |  |
 | `trgt_repeats` | A BED file with repeats to be genotyped with TRGT | `string` |  |  |  |
 | `snp_db` | A csv file with echtvar databases to annotate SNVs with | `string` |  |  |  |
+| `svdb_dbs` | 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` |  |  |  |
 | `variant_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` |  |  |  |
 | `vep_cache` | A path to the VEP cache location | `string` |  |  |  |
@@ -48,7 +49,7 @@ Define where the pipeline should find input data and save output data.
 | `reduced_penetrance` | A file with gene ids that have reduced penetrance. For use with genmod. | `string` |  |  |  |
 | `score_config_snv` | A SNV rank model config file for genmod. | `string` |  |  |  |
 | `somalier_sites` | A VCF of known polymorphic sites for somalier | `string` |  |  |  |
-| `pipelines_testdata_base_path` | Base URL or local path to location of pipeline test dataset files | `string` | https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/1f4e062926fc10f70a38e917e5771edb333e89bf/ |  | True |
+| `pipelines_testdata_base_path` | Base URL or local path to location of pipeline test dataset files | `string` | https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/7be7114cb132be8cae9343f225bcf42ec11ecc1b/ |  | True |
 
 ## Reference genome options
 
@@ -110,31 +111,3 @@ Workflow options specific to genomic-medicine-sweden/nallo
 | `extra_vep_options` | Extra options to VEP, used for test profile. | `string` |  |  | True |
 | `extra_paraphase_options` | Extra options to Paraphase, used for test profile. | `string` |  |  | True |
 | `extra_hifiasm_options` | Extra options to hifiasm, used for test profile. | `string` |  |  | True |
-
-## File inputs
-
-The different files that are required. Some are only required by certain workflows, see the usage documentation.
-
-| Parameter | Description | Type | Default | Required | Hidden |
-|-----------|-----------|-----------|-----------|-----------|-----------|
-| `cadd_prescored` | Path to a directory containing prescored indels for CADD. <details><summary>Help</summary><small>This folder contains the compressed files and indexes that would otherwise be in data/prescored folder as described in https://github.com/kircherlab/CADD-scripts/#manual-installation.</small></details>| `string` |  |  |  |
-| `cadd_resources` | Path to a directory containing CADD annotations. <details><summary>Help</summary><small>This folder contains the uncompressed files that would otherwise be in data/annotation folder as described in https://github.com/kircherlab/CADD-scripts/#manual-installation.</small></details>| `string` |  |  |  |
-| `par_regions` | Provide a bed file of chrX and chrY PAR regions for dipcall and DeepVariant | `string` |  |  |  |
-| `tandem_repeats` | A tandem repeat BED file for sniffles | `string` |  |  |  |
-| `trgt_repeats` | A BED file with repeats to be genotyped with TRGT | `string` |  |  |  |
-| `snp_db` | A csv file with echtvar databases to annotate SNVs with | `string` |  |  |  |
-| `svdb_dbs` | 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` |  |  |  |
-| `variant_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` |  |  |  |
-| `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` |  |  |  |
-| `hificnv_xy` | A BED file containing expected copy number regions for XY samples. | `string` |  |  |  |
-| `hificnv_xx` | A BED file containing expected copy number regions for XX samples. | `string` |  |  |  |
-| `hificnv_exclude` | A BED file specifying regions to exclude with HiFiCNV, such as centromeres. | `string` |  |  |  |
-| `reduced_penetrance` | A file with gene ids that have reduced penetrance. For use with genmod. | `string` |  |  |  |
-| `score_config_snv` | A SNV rank model config file for genmod. | `string` |  |  |  |
-| `somalier_sites` | A VCF of known polymorphic sites for somalier | `string` |  |  |  |
-| `validationFailUnrecognisedParams` | Validation of parameters fails when an unrecognised parameter is found. <details><summary>Help</summary><small>By default, when an unrecognised parameter is found, it returns a warning.</small></details>| `boolean` |  |  | True |
-| `validationLenientMode` | Validation of parameters in lenient more. <details><summary>Help</summary><small>Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode).</small></details>| `boolean` |  |  | True |
-| `pipelines_testdata_base_path` | Base URL or local path to location of pipeline test dataset files | `string` | https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/7be7114cb132be8cae9343f225bcf42ec11ecc1b/ |  | True |
->>>>>>> d3a25c2 (docs and split)
diff --git a/tests/nextflow.config b/tests/nextflow.config
@@ -5,14 +5,11 @@ params {
     // Base directory for genomic-medicine-sweden/nallo test data
     pipelines_testdata_base_path = 'https://raw.githubusercontent.com/genomic-medicine-sweden/test-datasets/7be7114cb132be8cae9343f225bcf42ec11ecc1b/'
 
-    max_cpus   = 4
-    max_memory = '15.GB'
-    max_time   = '6.h'
 }
 
 // Impose same minimum Nextflow version as the pipeline for testing
 manifest {
-    nextflowVersion = '!>=23.04.0'
+    nextflowVersion = '!>=24.04.2'
 }
 
 // Disable all Nextflow reporting options
@@ -22,25 +19,25 @@ trace    { enabled = false }
 dag      { enabled = false }
 
 process {
-
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
     withLabel: 'process_high' {
         cpus = 4
         memory = '15.GB'
     }
-
     withLabel: 'process_medium' {
         cpus = 2
         memory = '7.GB'
     }
-
     withLabel: 'process_low' {
         cpus = 1
         memory = '3.GB'
     }
-
     withLabel: 'process_single' {
         cpus = 1
         memory = '3.GB'
     }
-
 }