Sort inputs when creating PED-files, so the output it always the same (…

…#366)
genomic-medicine-sweden · Sep 12, 2024 · a8874db · a8874db
1 parent 47d48a5
commit a8874db
Show file tree

Hide file tree

Showing 11 changed files with 222 additions and 71 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
 - [#352](https://github.com/genomic-medicine-sweden/nallo/pull/352) - Added (hidden) `params.extra_<tool>_options` for the test profile to modkit, vep, paraphase and hifiasm
 - [#356](https://github.com/genomic-medicine-sweden/nallo/pull/356) - Added missing SNV and PED file to output documentation
 - [#363](https://github.com/genomic-medicine-sweden/nallo/pull/363) - Added Zenodo link
+- [#366](https://github.com/genomic-medicine-sweden/nallo/pull/366) - Added sorting of samples when creating PED files, so the output is always the same
 
 ### `Changed`
 

diff --git a/modules/local/create_pedigree_file.nf → modules/local/create_pedigree_file/main.nf b/modules/local/create_pedigree_file.nf → modules/local/create_pedigree_file/main.nf
@@ -8,7 +8,7 @@ process CREATE_PEDIGREE_FILE {
         'biocontainers/python:3.8.3' }"
 
     input:
-    tuple val(project), val(samples)
+    tuple val(project), val(meta)
 
     output:
     tuple val(project), path("*.ped"), emit: ped
@@ -19,6 +19,9 @@ process CREATE_PEDIGREE_FILE {
 
     script:
     def out   = new File(project + ".ped")
+    def samples = (meta.collect().size() > 1) ? meta.sort{ a, b ->
+        // First sort on family_id, then on sample id
+        a.family_id <=> b.family_id ?: a.id <=> b.id } : meta
     outfile_text = ['#family_id', 'sample_id', 'father', 'mother', 'sex', 'phenotype'].join('\\t')
     def samples_list = []
     for(int i = 0; i<samples.size(); i++) {

diff --git a/modules/local/create_pedigree_file/tests/main.nf.test b/modules/local/create_pedigree_file/tests/main.nf.test
@@ -0,0 +1,67 @@
+nextflow_process {
+
+    name "Test Process CREATE_PEDIGREE_FILE"
+    script "../main.nf"
+    process "CREATE_PEDIGREE_FILE"
+
+    tag "modules"
+    tag "modules_local"
+    tag "create_pedigree_file"
+
+    test("create_pedigree_file - one sample") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [ 'project',
+                    [
+                        [id:'HG002.Revio', family_id:'family', paternal_id:0, maternal_id:0, sex:0, phenotype:2, project:'project', n_files:1, single_end:true]
+                    ]
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    path(process.out.ped.get(0).get(1)).readLines(),
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+    test("create_pedigree_file - multiple samples") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [ 'test',
+                    [
+                        [id:'HG002_Revio_AB', family_id:'FAM2', paternal_id:0, maternal_id:0, sex:0, phenotype:1, project:'test', n_files:1, single_end:true],
+                        [id:'HG002_Revio_AA', family_id:'FAM2', paternal_id:0, maternal_id:0, sex:0, phenotype:1, project:'test', n_files:1, single_end:true],
+                        [id:'HG002_Revio_B', family_id:'FAM1', paternal_id:0, maternal_id:0, sex:0, phenotype:1, project:'test', n_files:2, single_end:true],
+                        [id:'HG002_Revio_A', family_id:'FAM1', paternal_id:0, maternal_id:0, sex:0, phenotype:2, project:'test', n_files:1, single_end:true],
+                        [id:'HG002_Revio_B', family_id:'FAM1', paternal_id:0, maternal_id:0, sex:0, phenotype:1, project:'test', n_files:2, single_end:true]
+                    ]
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    path(process.out.ped.get(0).get(1)).readLines(),
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+}
diff --git a/modules/local/create_pedigree_file/tests/main.nf.test.snap b/modules/local/create_pedigree_file/tests/main.nf.test.snap
@@ -0,0 +1,37 @@
+{
+    "create_pedigree_file - one sample": {
+        "content": [
+            [
+                "#family_id\tsample_id\tfather\tmother\tsex\tphenotype",
+                "family\tHG002.Revio\t0\t0\t0\t2"
+            ],
+            [
+                "versions.yml:md5,c0d2b2d33f1c465351d65e149ae88f0c"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-09-12T10:24:34.60478278"
+    },
+    "create_pedigree_file - multiple samples": {
+        "content": [
+            [
+                "#family_id\tsample_id\tfather\tmother\tsex\tphenotype",
+                "FAM1\tHG002_Revio_A\t0\t0\t0\t2",
+                "FAM1\tHG002_Revio_B\t0\t0\t0\t1",
+                "FAM2\tHG002_Revio_AA\t0\t0\t0\t1",
+                "FAM2\tHG002_Revio_AB\t0\t0\t0\t1"
+            ],
+            [
+                "versions.yml:md5,c0d2b2d33f1c465351d65e149ae88f0c"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.3"
+        },
+        "timestamp": "2024-09-12T10:40:54.71628575"
+    }
+}
diff --git a/nf-test.config b/nf-test.config
@@ -5,7 +5,7 @@ config {
     }
     testsDir "."
     workDir ".nf-test"
-    configFile "conf/test.config"
+    configFile "tests/nextflow.config"
     profile "docker"
 
 }
diff --git a/subworkflows/local/call_svs/tests/main.nf.test b/subworkflows/local/call_svs/tests/main.nf.test
@@ -2,8 +2,8 @@ nextflow_workflow {
 
     name "Test Workflow CALL_SVS"
     script "../main.nf"
-    workflow "CALL_SVS"
     config "./nextflow.config"
+    workflow "CALL_SVS"
 
     setup {
             run("GUNZIP") {

diff --git a/subworkflows/local/call_svs/tests/main.nf.test.snap b/subworkflows/local/call_svs/tests/main.nf.test.snap
@@ -727,7 +727,7 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-06T11:29:28.671005178"
+        "timestamp": "2024-09-12T12:13:14.38085716"
     },
     "1 sample - [bam, bai], fasta, fai, [] -stub": {
         "content": [
@@ -822,7 +822,7 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-05T19:07:34.521780648"
+        "timestamp": "2024-09-12T12:37:08.560198215"
     },
     "1 sample - [bam, bai], fasta, fai, bed -stub": {
         "content": [
@@ -917,7 +917,7 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-05T19:07:45.413681853"
+        "timestamp": "2024-09-12T12:37:19.687620805"
     },
     "1 sample - [bam, bai], fasta, fai, bed": {
         "content": [
@@ -1158,7 +1158,7 @@
                 "##INFO=<ID=PHASE,Number=.,Type=String,Description=\"Phasing information derived from supporting reads, represented as list of: HAPLOTYPE,PHASESET,HAPLOTYPE_SUPPORT,PHASESET_SUPPORT,HAPLOTYPE_FILTER,PHASESET_FILTER\">",
                 "##bcftools_viewVersion=1.20+htslib-1.20"
             ],
-            "13d352d7a4dd922085f653a3da950bce",
+            "5924013e8c1835d7bb0502ee85f2128d",
             [
                 "##contig=<ID=chr1,length=248956422>",
                 "##contig=<ID=chr2,length=242193529>",
@@ -1396,7 +1396,7 @@
                 "##INFO=<ID=PHASE,Number=.,Type=String,Description=\"Phasing information derived from supporting reads, represented as list of: HAPLOTYPE,PHASESET,HAPLOTYPE_SUPPORT,PHASESET_SUPPORT,HAPLOTYPE_FILTER,PHASESET_FILTER\">",
                 "##bcftools_viewVersion=1.20+htslib-1.20"
             ],
-            "28ed9eefcf5bb27fed8c55f615219f33",
+            "8df5ad12540b4e0982bb74d5b268795d",
             [
                 "versions.yml:md5,2188f00d20a376929f9f35f824e94667",
                 "versions.yml:md5,572bfd042014333af194207291d12b95",
@@ -1408,7 +1408,7 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-05T14:17:59.191541065"
+        "timestamp": "2024-09-12T12:12:58.045416708"
     },
     "2 samples - [bam, bai], fasta, fai, [] -stub": {
         "content": [
@@ -1461,7 +1461,7 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-06T11:30:02.189652169"
+        "timestamp": "2024-09-12T12:13:55.632583291"
     },
     "1 sample - [bam, bai], fasta, fai, []": {
         "content": [
@@ -1702,7 +1702,7 @@
                 "##INFO=<ID=PHASE,Number=.,Type=String,Description=\"Phasing information derived from supporting reads, represented as list of: HAPLOTYPE,PHASESET,HAPLOTYPE_SUPPORT,PHASESET_SUPPORT,HAPLOTYPE_FILTER,PHASESET_FILTER\">",
                 "##bcftools_viewVersion=1.20+htslib-1.20"
             ],
-            "5cdf920b1f44a66de3a28ead8d3efb24",
+            "79676a9dd690e37560b5841b67dfa28",
             [
                 "##contig=<ID=chr1,length=248956422>",
                 "##contig=<ID=chr2,length=242193529>",
@@ -1940,7 +1940,7 @@
                 "##INFO=<ID=PHASE,Number=.,Type=String,Description=\"Phasing information derived from supporting reads, represented as list of: HAPLOTYPE,PHASESET,HAPLOTYPE_SUPPORT,PHASESET_SUPPORT,HAPLOTYPE_FILTER,PHASESET_FILTER\">",
                 "##bcftools_viewVersion=1.20+htslib-1.20"
             ],
-            "fe2e9b5e8f54e993c262331759006346",
+            "bd51c062a29bbb8823a17b95f8162f44",
             [
                 "versions.yml:md5,2188f00d20a376929f9f35f824e94667",
                 "versions.yml:md5,572bfd042014333af194207291d12b95",
@@ -1952,6 +1952,6 @@
             "nf-test": "0.8.4",
             "nextflow": "24.04.3"
         },
-        "timestamp": "2024-09-05T14:17:46.151263963"
+        "timestamp": "2024-09-12T12:12:44.978644444"
     }
-}
+}
diff --git a/tests/main.nf.test b/tests/main.nf.test
@@ -4,6 +4,7 @@ nextflow_pipeline {
     script "../main.nf"
     profile "test"
     tag "PIPELINE"
+    config "../conf/test.config"
 
     test("test profile") {
         tag "samplesheet"