Fix rank SVs with multiple families (#480)

* Fix rank SVs with multiple families * use updated genmod modules * fix tests
genomic-medicine-sweden · Nov 5, 2024 · c47f69a · c47f69a
1 parent 9953afa
commit c47f69a
Show file tree

Hide file tree

Showing 18 changed files with 133 additions and 84 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -80,6 +80,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#451](https://github.com/genomic-medicine-sweden/nallo/pull/451) - Simplified methylation subworkflow
 - [#474](https://github.com/genomic-medicine-sweden/nallo/pull/474) - Updated VEP and CADD channels to fix bugs introduced in [#443](https://github.com/genomic-medicine-sweden/nallo/pull/443)
 - [#479](https://github.com/genomic-medicine-sweden/nallo/pull/479) - Replaced bgzip tabix with bcftools sort in rank variants to fix [#457](https://github.com/genomic-medicine-sweden/nallo/issues/457)
+- [#480](https://github.com/genomic-medicine-sweden/nallo/pull/480) - Updated ranking of SVs to work with multiple families per project
 - [#484](https://github.com/genomic-medicine-sweden/nallo/pull/484) - Updated metro map and added SVG version
 - [#487](https://github.com/genomic-medicine-sweden/nallo/pull/487) - Changed CI tests to only run tests where changes have been made
 

diff --git a/conf/modules/general.config b/conf/modules/general.config
@@ -113,7 +113,14 @@ process {
 
     withName: '.*:NALLO:SOMALIER_PED' {
         publishDir = [
-            path: { "${params.outdir}/pedigree" },
+            path: { "${params.outdir}/pedigree/project/" },
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
+
+    withName: '.*:NALLO:SOMALIER_PED_FAMILY' {
+        publishDir = [
+            path: { "${params.outdir}/pedigree/family/" },
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }

diff --git a/docs/output.md b/docs/output.md
@@ -121,12 +121,13 @@ If the pipeline is run with phasing, the aligned reads will be happlotagged usin
 
 [somalier](https://github.com/brentp/somalier) checks relatedness and sex.
 
-| Path                                                  | Description                                 |
-| ----------------------------------------------------- | ------------------------------------------- |
-| `pedigree/{project}.ped`                              | PED file updated with somalier-inferred sex |
-| `qc/somalier/relate/{project}/{project}.html`         | HTML report                                 |
-| `qc/somalier/relate/{project}/{project}.pairs.tsv`    | Information about sample pairs              |
-| `/qc/somalier/relate/{project}/{project}.samples.tsv` | Information about individual samples        |
+| Path                                                  | Description                                             |
+| ----------------------------------------------------- | ------------------------------------------------------- |
+| `pedigree/{project}/{project}.ped`                    | PED file updated with somalier-inferred sex per project |
+| `pedigree/{family}/{family).ped`                      | PED file updated with somalier-inferred sex per family  |
+| `qc/somalier/relate/{project}/{project}.html`         | HTML report                                             |
+| `qc/somalier/relate/{project}/{project}.pairs.tsv`    | Information about sample pairs                          |
+| `/qc/somalier/relate/{project}/{project}.samples.tsv` | Information about individual samples                    |
 
 | Path                      | Description                                 |
 | ------------------------- | ------------------------------------------- |

diff --git a/modules.json b/modules.json
@@ -114,12 +114,12 @@
                     },
                     "genmod/models": {
                         "branch": "master",
-                        "git_sha": "91a84f951358143e93dc9e03470db4e6a4a7105c",
+                        "git_sha": "f888300c726e1f817a9f93a680866ff7e6c669f6",
                         "installed_by": ["modules"]
                     },
                     "genmod/score": {
                         "branch": "master",
-                        "git_sha": "91a84f951358143e93dc9e03470db4e6a4a7105c",
+                        "git_sha": "f888300c726e1f817a9f93a680866ff7e6c669f6",
                         "installed_by": ["modules"]
                     },
                     "gfastats": {

diff --git a/modules/local/create_pedigree_file/main.nf b/modules/local/create_pedigree_file/main.nf
@@ -1,5 +1,5 @@
 process CREATE_PEDIGREE_FILE {
-    tag "${project}"
+    tag "${meta.id}"
     label 'process_single'
 
     conda "conda-forge::python=3.8.3"
@@ -8,20 +8,20 @@ process CREATE_PEDIGREE_FILE {
         'biocontainers/python:3.8.3' }"
 
     input:
-    tuple val(project), val(meta)
+    tuple val(meta), val(metas)
 
     output:
-    tuple val(project), path("*.ped"), emit: ped
-    path "versions.yml"              , emit: versions
+    tuple val(meta), path("*.ped"), emit: ped
+    path "versions.yml"           , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def out   = new File(project + ".ped")
-    def samples = (meta.collect().size() > 1) ? meta.sort{ a, b ->
+    def prefix   = task.ext.prefix ?: "${meta.id}"
+    def samples = (metas.collect().size() > 1) ? metas.sort{ a, b ->
         // First sort on family_id, then on sample id
-        a.family_id <=> b.family_id ?: a.id <=> b.id } : meta
+        a.family_id <=> b.family_id ?: a.id <=> b.id } : metas
     outfile_text = ['#family_id', 'sample_id', 'father', 'mother', 'sex', 'phenotype'].join('\\t')
     def samples_list = []
     for(int i = 0; i<samples.size(); i++) {
@@ -32,7 +32,7 @@ process CREATE_PEDIGREE_FILE {
         }
     }
     """
-    echo -e "$outfile_text" >${project}.ped
+    echo -e "$outfile_text" > ${prefix}.ped
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -42,8 +42,9 @@ process CREATE_PEDIGREE_FILE {
     """
 
     stub:
+    def prefix   = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${project}.ped
+    touch ${prefix}.ped
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/modules/nf-core/genmod/models/main.nf b/modules/nf-core/genmod/models/main.nf
diff --git a/modules/nf-core/genmod/models/meta.yml b/modules/nf-core/genmod/models/meta.yml
diff --git a/modules/nf-core/genmod/models/tests/main.nf.test b/modules/nf-core/genmod/models/tests/main.nf.test
diff --git a/modules/nf-core/genmod/score/main.nf b/modules/nf-core/genmod/score/main.nf
diff --git a/modules/nf-core/genmod/score/meta.yml b/modules/nf-core/genmod/score/meta.yml
diff --git a/modules/nf-core/genmod/score/tests/main.nf.test b/modules/nf-core/genmod/score/tests/main.nf.test
diff --git a/subworkflows/local/rank_variants/main.nf b/subworkflows/local/rank_variants/main.nf
@@ -12,7 +12,7 @@ workflow RANK_VARIANTS {
 
     take:
     ch_vcf                // channel: [mandatory] [ val(meta), path(vcf) ]
-    ch_pedfile            // channel: [mandatory] [ val(meta), path(ped) ]
+    ch_ped                // channel: [mandatory] [ val(meta), path(ped) ]
     ch_reduced_penetrance // channel: [mandatory] [ val(meta), path(pentrance) ]
     ch_score_config       // channel: [mandatory] [ val(meta), path(ini) ]
 
@@ -22,16 +22,22 @@ workflow RANK_VARIANTS {
     GENMOD_ANNOTATE ( ch_vcf )
     ch_versions = ch_versions.mix(GENMOD_ANNOTATE.out.versions)
 
+    GENMOD_ANNOTATE.out.vcf
+        .join( ch_ped, failOnMismatch: true )
+        .set { genmod_models_in }
+
     GENMOD_MODELS (
-        GENMOD_ANNOTATE.out.vcf,
-        ch_pedfile.map { meta, ped -> ped },
+        genmod_models_in,
         ch_reduced_penetrance.map { meta, file -> file }
     )
     ch_versions = ch_versions.mix(GENMOD_MODELS.out.versions)
 
+    GENMOD_MODELS.out.vcf
+        .join( ch_ped, failOnMismatch: true )
+        .set { genmod_score_in }
+
     GENMOD_SCORE (
-        GENMOD_MODELS.out.vcf,
-        ch_pedfile.map { meta, ped -> ped },
+        genmod_score_in,
         ch_score_config.map { meta, file -> file }
     )
     ch_versions = ch_versions.mix(GENMOD_SCORE.out.versions)

diff --git a/subworkflows/local/rank_variants/tests/main.nf.test b/subworkflows/local/rank_variants/tests/main.nf.test
@@ -28,7 +28,7 @@ nextflow_workflow {
             process {
                 """
                 input[0] = [
-                    [ id: 'test', num_intervals:1 ],
+                    [ id: 'project', num_intervals:1 ],
                     file(params.pipelines_testdata_base_path + 'testdata/HG002_PacBio_Revio.fastq.gz', checkIfExists: true)
                 ]
                 input[1] = PREPARE_GENOME.out.fasta
@@ -46,7 +46,7 @@ nextflow_workflow {
                 input[0] = MINIMAP2_ALIGN.out.bam
                             .join(MINIMAP2_ALIGN.out.index)
                             .join(Channel.of([
-                                [ id: 'test', num_intervals:1 ],
+                                [ id: 'project', num_intervals:1 ],
                                 file(params.pipelines_testdata_base_path + 'reference/test_data.bed', checkIfExists: true)
                             ]))
                 input[1] = PREPARE_GENOME.out.fasta
@@ -95,9 +95,9 @@ nextflow_workflow {
             process {
                 """
                 input[0] = [
-                    'project',
+                    [id:'project'],
                     [
-                        [ id: 'test', project: 'project', maternal_id: '0', paternal_id: '0', family_id: 'family', sex: '2', phenotype: '2' ]
+                        [ id: 'project', project: 'project', maternal_id: '0', paternal_id: '0', family_id: 'family', sex: '2', phenotype: '2' ]
                     ]
                 ]
                 """
@@ -110,8 +110,8 @@ nextflow_workflow {
         when {
             workflow {
                 """
-                input[0] = ANNOTATE_CSQ_PLI.out.vcf
-                input[1] = CREATE_PEDIGREE_FILE.out.ped
+                input[0] = ANNOTATE_CSQ_PLI.out.vcf.map { meta, vcf -> [ [ id: 'test' ], vcf ] }
+                input[1] = CREATE_PEDIGREE_FILE.out.ped.map { meta, ped -> [ [ id: 'test' ], ped ] }
                 input[2] = Channel.of([
                     [ id: 'reduced_penetrance' ],
                     file(params.pipelines_testdata_base_path + 'reference/reduced_penetrance.tsv', checkIfExists: true)
@@ -142,8 +142,8 @@ nextflow_workflow {
         when {
             workflow {
                 """
-                input[0] = ANNOTATE_CSQ_PLI.out.vcf
-                input[1] = CREATE_PEDIGREE_FILE.out.ped
+                input[0] = ANNOTATE_CSQ_PLI.out.vcf.map { meta, vcf -> [ [ id: 'test' ], vcf ] }
+                input[1] = CREATE_PEDIGREE_FILE.out.ped.map { meta, ped -> [ [ id: 'test' ], ped ] }
                 input[2] = Channel.of([
                     [ id: 'reduced_penetrance' ],
                     file(params.pipelines_testdata_base_path + 'reference/reduced_penetrance.tsv', checkIfExists: true)

diff --git a/subworkflows/local/rank_variants/tests/main.nf.test.snap b/subworkflows/local/rank_variants/tests/main.nf.test.snap
@@ -15,21 +15,17 @@
                 "0": [
                     [
                         {
-                            "id": "test_data.bed",
-                            "project": null,
-                            "contains_affected": false
+                            "id": "test"
                         },
-                        "test_data.bed_sorted.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                        "test_sorted.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
                     ]
                 ],
                 "1": [
                     [
                         {
-                            "id": "test_data.bed",
-                            "project": null,
-                            "contains_affected": false
+                            "id": "test"
                         },
-                        "test_data.bed_sorted.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test_sorted.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "2": [
@@ -42,21 +38,17 @@
                 "tbi": [
                     [
                         {
-                            "id": "test_data.bed",
-                            "project": null,
-                            "contains_affected": false
+                            "id": "test"
                         },
-                        "test_data.bed_sorted.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test_sorted.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "vcf": [
                     [
                         {
-                            "id": "test_data.bed",
-                            "project": null,
-                            "contains_affected": false
+                            "id": "test"
                         },
-                        "test_data.bed_sorted.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                        "test_sorted.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
                     ]
                 ],
                 "versions": [
@@ -72,6 +64,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-11-01T13:03:00.102392544"
+        "timestamp": "2024-11-04T14:34:36.22073696"
     }
 }