Provide config for report + add params to this config

config/nxf_vcf.config

@@ -7,9 +7,9 @@ env {
   CMD_VEP = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vep-111.0.sif vep"
   CMD_FILTERVEP = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vep-111.0.sif filter_vep"
   CMD_STRANGER = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/stranger-0.8.1_v2.sif stranger"
-  CMD_VCFREPORT="apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-report-7.0.3.sif"
-  CMD_VCFDECISIONTREE = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-decision-tree-5.0.0.sif"
-  CMD_VCFINHERITANCEMATCHER = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-inheritance-matcher-3.2.1.sif"
+  CMD_VCFREPORT="apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-report-7.2.0.sif"
+  CMD_VCFDECISIONTREE = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-decision-tree-5.1.1.sif"
+  CMD_VCFINHERITANCEMATCHER = "apptainer exec --no-mount home --bind \${TMPDIR} ${APPTAINER_CACHEDIR}/vcf-inheritance-matcher-3.3.2.sif"
 
   // workaround for SAMtools https://github.com/samtools/samtools/issues/1366#issuecomment-769170935
   REF_PATH = ":"
@@ -66,7 +66,7 @@ params {
         expansionhunter_variant_catalog = "${projectDir}/resources/GRCh38/expansionhunter_variant_catalog.json"
         stranger_catalog = "${projectDir}/resources/GRCh38/variant_catalog_grch38_fixed.json"
         vep_custom_phylop = "${projectDir}/resources/GRCh38/hg38.phyloP100way.bw"
-        vep_plugin_clinvar = "${projectDir}/resources/GRCh38/clinvar_20241001-stripped.tsv.gz"
+        vep_plugin_clinvar = "${projectDir}/resources/GRCh38/clinvar_20241126-stripped.tsv.gz"
         vep_plugin_gnomad = "${projectDir}/resources/GRCh38/gnomad.total.v4.1.sites.stripped.tsv.gz"
         vep_plugin_spliceai_indel = "${projectDir}/resources/GRCh38/spliceai_scores.masked.indel.hg38.vcf.gz"
         vep_plugin_spliceai_snv = "${projectDir}/resources/GRCh38/spliceai_scores.masked.snv.hg38.vcf.gz"
@@ -111,7 +111,8 @@ params {
       include_crams = true
       max_records = ""
       max_samples = ""
-      template = "${projectDir}/resources/vip-report-template-v6.2.0.html"
+      template = "${projectDir}/resources/vip-report-template-v7.0.2.html"
+      config = "${projectDir}/resources/vcf_report_config.json"
 			metadata = "${projectDir}/resources/field_metadata.json"
 
       GRCh38 {

docs/advanced/report_templates.md

@@ -1,16 +1,20 @@
 # Report templates
+
 VIP outputs a standalone HTML report that can be viewed in any modern browser.
 The report is based on the input sample sheet information and the output variant `vcf` data.
 
 ## Default
+
 As a default VIP uses a report template that is suitable for most analysis:
 
 ![Example report](../img/report_example.png)
 
 *Above: default report template*
 
 ## Customization
-Using the `vcf.report.template` parameter (see [here](../usage/config.md#parameters)) it is possible to specify a different report template to create reports tailered to your needs. 
+
+Using the `vcf.report.template` parameter (see [here](../usage/config.md#parameters)) it is possible to specify a
+different report template to create reports tailered to your needs.
 
 The following repositories might be of interest when creating a new report template:
 
@@ -22,4 +26,11 @@ The following repositories might be of interest when creating a new report templ
 The `vip-report` tool creates reports based on a report template as described in the following repositories:
 
 - [vip-report](https://github.com/molgenis/vip-report)
-- [vip-utils](https://github.com/molgenis/vip-utils)
+- [vip-utils](https://github.com/molgenis/vip-utils)
+
+## Configuration
+
+A configuration .json file can be used in combination with a `vcf.report.template` to create reports that e.g. show
+specific variant content or variant filters. The allowed contents of a configuration .json file depends on the
+`vcf.report.template` used. For the default `vcf.report.template` the configuration options are
+described [here](https://github.com/molgenis/vip-report-template).    

docs/usage/config.md

@@ -74,7 +74,7 @@ Both the zipped and unzipped fasta should have an index.
 | sv.cutesv.min_read_len                         | 500            | Ignores reads that only report alignments with not longer than bp                                                                                                                    |
 | sv.cutesv.min_siglength                        | 10             | Minimum length of SV signal to be extracted                                                                                                                                          |
 | sv.cutesv.min_size                             | 30             | Minimum size of SV to be reported                                                                                                                                                    |
-| sv.cutesv.min_support                          | 2              | Minimum number of reads that support a SV to be reported. Please note that the default is lower than the default of cuteSV itself to prevent missed SV calls. |
+| sv.cutesv.min_support                          | 2              | Minimum number of reads that support a SV to be reported. Please note that the default is lower than the default of cuteSV itself to prevent missed SV calls.                        |
 | sv.cutesv.read_range                           | 1000           | The interval range for counting reads distribution                                                                                                                                   |
 | sv.cutesv.report_readid                        | false          | Enable to report supporting read ids for each SV                                                                                                                                     |
 | sv.cutesv.retain_work_dir                      | false          | Enable to retain temporary folder and files                                                                                                                                          |
@@ -142,6 +142,7 @@ Both the zipped and unzipped fasta should have an index.
 | vcf.report.include_crams                        | true        | allowed values: [true, false]. true: include cram files in the report for showing alignments in the genome browser, false: do not include the crams in the report, no aligments are shown in the genome browser. This will result in a smaller report size. |
 | vcf.report.max_records                          |             |                                                                                                                                                                                                                                                             |
 | vcf.report.max_samples                          |             |                                                                                                                                                                                                                                                             |
+| vcf.report.config                               |             | `vcf.report.template` configuration file                                                                                                                                                                                                                    |
 | vcf.report.template                             |             | for details, see [here](../advanced/report_templates.md)                                                                                                                                                                                                    |
 | vcf.report.GRCh38.genes                         | *installed* |                                                                                                                                                                                                                                                             |
 

install.sh

@@ -87,9 +87,9 @@ download_files() {
   urls+=("4d58cc7a4e3e497a245095a62562e27e" "images/spectre-0.2.1-patched_v2.sif")
   urls+=("8f6e06847776448e004df8b863571109" "images/straglr-1.4.4_vip_v3.sif")
   urls+=("9c69ac645e04b91c8f480289c536429c" "images/stranger-0.8.1_v2.sif")
-  urls+=("599813c5c0d547c955bd071ccdf220f8" "images/vcf-decision-tree-5.0.0.sif")
-  urls+=("f238b75e85e8a097447bad471369d0b2" "images/vcf-inheritance-matcher-3.2.1.sif")
-  urls+=("87b2d9031b1b8351d2da14dd0095fbea" "images/vcf-report-7.0.3.sif")
+  urls+=("8575e48d7da8a7f0728d08dc204e42a5" "images/vcf-decision-tree-5.1.1.sif")
+  urls+=("57a7329781d3cb0e5491c5f84fd49dcd" "images/vcf-inheritance-matcher-3.3.2.sif")
+  urls+=("9357590531fd4f1af1ab610ddafbdd3b" "images/vcf-report-7.2.0.sif")
   urls+=("7bffc236a7c65b2b2e2e5f7d64beaa87" "images/vep-111.0.sif")
   urls+=("82be3c18406e7c027ee4cec83a723d71" "nextflow-24.04.2-all")
   if [ "${assembly}" == "ALL" ] || [ "${assembly}" == "GRCh37" ]; then
@@ -110,8 +110,8 @@ download_files() {
   urls+=("498c22d840476a757be5f5b0e382f8d6" "resources/GRCh38/GRCh38_ncER_perc.bed.gz.tbi")
   urls+=("7cc9cafbdde0b00f8007bc2911310b50" "resources/GRCh38/capice_model_v5.1.2-v3.ubj")
   urls+=("03d4fb2f5fe500daa77c54455626f8f5" "resources/GRCh38/clinical_repeats.bed")
-  urls+=("52a5ef527d2509d2196329a67b447975" "resources/GRCh38/clinvar_20241001-stripped.tsv.gz")
-  urls+=("1231b9c88fb19034d313c4e003667238" "resources/GRCh38/clinvar_20241001-stripped.tsv.gz.tbi")
+  urls+=("8da13608d59915f031beade9c3981c2e" "resources/GRCh38/clinvar_20241126-stripped.tsv.gz")
+  urls+=("6b1ed6d55e870e37d2bed360abc26fe2" "resources/GRCh38/clinvar_20241126-stripped.tsv.gz.tbi")
   urls+=("72f12f9ee918878030022c46ec850038" "resources/GRCh38/expansionhunter_variant_catalog.json")
   urls+=("e4c68d0e98a9b5401542b2e8d5b05e82" "resources/GRCh38/gnomad.total.v4.1.sites.stripped.tsv.gz")
   urls+=("eebfca693425c159d87479fef26d3774" "resources/GRCh38/gnomad.total.v4.1.sites.stripped.tsv.gz.tbi")
@@ -147,7 +147,7 @@ download_files() {
   # update utils/install.sh when updating inheritance.tsv
   urls+=("df31eb0fe9ebd9ae26c8d6f5f7ba6e57" "resources/inheritance_20240115.tsv")
   urls+=("7138e76a38d6f67935699d06082ecacf" "resources/vep/cache/homo_sapiens_refseq_vep_111_GRCh38.tar.gz")
-  urls+=("78962f0c7c6fe5c63ef7c66b627c95a0" "resources/vip-report-template-v6.2.0.html")
+  urls+=("e5d17440fc84b49b2fba7a30b500ca93" "resources/vip-report-template-v7.0.2.html")
   # when modifying urls array, please keep list in 'ls -l' order
   for ((i = 0; i < ${#urls[@]}; i += 2)); do
     download_file "${base_url}" "${urls[i+1]}" "${urls[i+0]}" "${output_dir}" "${validate}"

modules/vcf/inheritance.nf

@@ -16,6 +16,7 @@ process inheritance {
     vcfOutIndex = "${vcfOut}.csi"
     vcfOutStats = "${vcfOut}.stats"
 
+    metadata = params.vcf.classify.metadata
     probands = meta.probands.collect{ proband -> proband.individual_id}.join(",")
     pedigree = "${meta.project.id}.ped"
     pedigreeContent = createPedigree(meta.project.samples)

modules/vcf/report.nf

@@ -1,5 +1,6 @@
 include { basename } from './utils'
 include { createPedigree } from '../utils'
+import groovy.json.JsonOutput
 
 process report {
   label 'vcf_report'
@@ -31,11 +32,14 @@ process report {
     crams = meta.crams ? meta.crams.collect { "${it.individual_id}=${it.cram}" }.join(",") : ""
     includeCrams = params.vcf.report.include_crams
 
+    configJsonStr = new File(params.vcf.report.config).getText('UTF-8').replaceFirst("\\{", "{\"vip\": {\"filter_field\": {\"type\": \"genotype\",\"name\": \"VIPC_S\"},\"params\":" + JsonOutput.toJson(params) + "},")
+
     probands = meta.probands.collect{ proband -> proband.individual_id }.join(",")
     hpoIds = meta.project.samples.findAll{ sample -> !sample.hpo_ids.isEmpty() }.collect{ sample -> [sample.individual_id, sample.hpo_ids.join(";")].join("/") }.join(",") 
     pedigree = "${meta.project.id}.ped"
     pedigreeContent = createPedigree(meta.project.samples)
 
+
     template 'report.sh'
 
   stub:

modules/vcf/templates/inheritance.sh

@@ -13,6 +13,7 @@ inheritance () {
   args+=("-jar" "/opt/vcf-inheritance-matcher/lib/vcf-inheritance-matcher.jar")
   args+=("--input" "!{vcf}_replaced.vcf.gz")
   args+=("--output" "!{vcfOut}_replaced.vcf.gz")
+  args+=("--metadata" "!{metadata}")
   if [ -n "!{pedigree}" ]; then
     args+=("--pedigree" "!{pedigree}")
   fi

modules/vcf/templates/report.sh

@@ -60,6 +60,10 @@ report() {
   if [ -n "!{template}" ]; then
     args+=("--template" "!{template}")
   fi
+  cat << EOF > "vip_report_config.json"
+!{configJsonStr}
+EOF
+  args+=("--template_config" "vip_report_config.json")
   if [ -n "!{crams}" ] && [[ "!{includeCrams}" == "true" ]]; then
     args+=("--cram" "!{crams}")
   fi

resources/decision_tree_GRCh38.json

@@ -65,7 +65,9 @@
             {
               "field": "INFO/CSQ/clinVar_CLNSIG",
               "operator": "contains_any",
-              "value": [ "Conflicting_interpretations_of_pathogenicity" ]
+              "value": [
+                "Conflicting_classifications_of_pathogenicity"
+              ]
             }
           ],
           "outcomeTrue": {
@@ -78,7 +80,10 @@
             {
               "field": "INFO/CSQ/clinVar_CLNSIG",
               "operator": "contains_any",
-              "value": [ "Likely_pathogenic", "Pathogenic" ]
+              "value": [
+                "Likely_pathogenic",
+                "Pathogenic"
+              ]
             }
           ],
           "outcomeTrue": {
@@ -91,7 +96,9 @@
             {
               "field": "INFO/CSQ/clinVar_CLNSIG",
               "operator": "contains_any",
-              "value": [ "Uncertain_significance" ]
+              "value": [
+                "Uncertain_significance"
+              ]
             }
           ],
           "outcomeTrue": {
@@ -104,7 +111,10 @@
             {
               "field": "INFO/CSQ/clinVar_CLNSIG",
               "operator": "contains_any",
-              "value": [ "Likely_benign", "Benign" ]
+              "value": [
+                "Likely_benign",
+                "Benign"
+              ]
             }
           ],
           "outcomeTrue": {