Generate pedigree directly from inputs json structure.

Fixes "yaml2ped.py generating ped file with wrong format" #129.

README.md

@@ -266,7 +266,7 @@ The Docker image used by a particular step of the workflow can be identified by
 | pb-cpg-tools | <ul><li>[pb-CpG-tools v2.3.2](https://github.com/PacificBiosciences/pb-CpG-tools/releases/tag/v2.3.2)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/7481837d3b0f539adf4f64209a65cf28eebf3dba/docker/pb-cpg-tools) |
 | pbmm2 | <ul><li>[pbmm2 1.10.0](https://github.com/PacificBiosciences/pbmm2/releases/tag/v1.10.0)</li><li>[datamash 1.1.0](https://ftp.gnu.org/gnu/datamash/)</li><li>[pysam 0.16.0.1](https://github.com/pysam-developers/pysam/releases/tag/v0.16.0.1)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/pbmm2) |
 | pbsv | <ul><li>[pbsv 2.9.0](https://github.com/PacificBiosciences/pbsv/releases/tag/v2.9.0)</li><li>[htslib 1.14](https://github.com/samtools/htslib/releases/tag/1.14)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/f9e33a757e6d8cb15696ac930a2efd0fd7a885d8/docker/pbsv) |
-| pyyaml | <ul><li>[pyyaml 5.3.1](https://github.com/yaml/pyyaml/releases/tag/5.3.1)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/f72e862bca2f209b9909e6043ef0197975762f27/docker/pyyaml) |
+| wgs_tertiary image | | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/6b13cc246dd44e41903d17a660bb5432cdd18dbe/docker/wgs_tertiary) |
 | samtools | <ul><li>[samtools 1.14](https://github.com/samtools/samtools/releases/tag/1.14)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/samtools) |
 | slivar | <ul><li>[slivar 0.2.2](https://github.com/brentp/slivar/releases/tag/v0.2.2)</li><li>[bcftools 1.14](https://github.com/samtools/bcftools/releases/tag/1.14)</li><li>[vcfpy 0.13.3](https://github.com/bihealth/vcfpy/releases/tag/v0.13.3)</li><li>[pysam 0.19.1](https://github.com/pysam-developers/pysam/releases/tag/v0.19.1)</li></ul> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/slivar) |
 | svpack | <ul><li>[svpack 36180ae6](https://github.com/PacificBiosciences/svpack/tree/a82598ebc4013bf32e70295b83b380ada6302c4a)</li><li>[htslib 1.18](https://github.com/samtools/htslib/releases/tag/1.18)</li><li>[pysam 0.21.0](https://github.com/pysam-developers/pysam/releases/tag/v0.21.0)</li> | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/8edbc516abc0ff43ac279b48018003923721b054/docker/svpack) |

wdl-ci.config.json

@@ -707,29 +707,21 @@
       "name": "",
       "description": "",
       "tasks": {
-        "write_yaml_ped_phrank": {
+        "write_ped_phrank": {
           "key": "write_yaml_ped_phrank",
           "digest": "e4yxyjj6vw35pxz434pgfalxpa4xh72n",
           "tests": [
             {
               "inputs": {
                 "cohort_id": "hg005-small-cohort",
                 "cohort_json": "${resources_file_path}/cohort.json",
-                "hpo_terms": "${datasets_file_path}/hpo/hpoTerms.txt",
-                "hpo_dag": "${datasets_file_path}/hpo/hpoDag.txt",
-                "hpo_annotations": "${datasets_file_path}/hpo/ensembl.hpoPhenotype.tsv",
-                "ensembl_to_hgnc": "${datasets_file_path}/hpo/ensembl.hgncSymbol.tsv",
+                "phenotypes": [
+                  "HP:0001250",
+                  "HP:0001263"
+                ],
                 "runtime_attributes": "${default_runtime_attributes}"
               },
               "output_tests": {
-                "cohort_yaml": {
-                  "value": "${resources_file_path}/hg005-small-cohort.yml",
-                  "test_tasks": [
-                    "calculate_md5sum",
-                    "compare_file_basename",
-                    "check_yaml"
-                  ]
-                },
                 "pedigree": {
                   "value": "${resources_file_path}/hg005-small-cohort.ped",
                   "test_tasks": [

workflows/tertiary_analysis/tertiary_analysis.wdl

@@ -18,22 +18,19 @@ workflow tertiary_analysis {
 		RuntimeAttributes default_runtime_attributes
 	}
 
-	call write_yaml_ped_phrank {
+	call write_ped_phrank {
 		input:
 			cohort_id = cohort.cohort_id,
 			cohort_json = write_json(cohort),
-			hpo_terms = slivar_data.hpo_terms,
-			hpo_dag = slivar_data.hpo_dag,
-			hpo_annotations = slivar_data.hpo_annotations,
-			ensembl_to_hgnc = slivar_data.ensembl_to_hgnc,
+			phenotypes = cohort.phenotypes,
 			runtime_attributes = default_runtime_attributes
 	}
 
 	call slivar_small_variant {
 		input:
 			vcf = small_variant_vcf.data,
 			vcf_index = small_variant_vcf.data_index,
-			pedigree = write_yaml_ped_phrank.pedigree,
+			pedigree = write_ped_phrank.pedigree,
 			reference = reference.fasta.data,
 			reference_index = reference.fasta.data_index,
 			slivar_js = slivar_data.slivar_js,
@@ -42,7 +39,7 @@ workflow tertiary_analysis {
 			gff = select_first([reference.gff]),
 			lof_lookup = slivar_data.lof_lookup,
 			clinvar_lookup = slivar_data.clinvar_lookup,
-			phrank_lookup = write_yaml_ped_phrank.phrank_lookup,
+			phrank_lookup = write_ped_phrank.phrank_lookup,
 			runtime_attributes = default_runtime_attributes
 	}
 
@@ -63,10 +60,10 @@ workflow tertiary_analysis {
 	call slivar_svpack_tsv {
 		input:
 			filtered_vcf = svpack_filter_annotated.svpack_vcf,
-			pedigree = write_yaml_ped_phrank.pedigree,
+			pedigree = write_ped_phrank.pedigree,
 			lof_lookup = slivar_data.lof_lookup,
 			clinvar_lookup = slivar_data.clinvar_lookup,
-			phrank_lookup = write_yaml_ped_phrank.phrank_lookup,
+			phrank_lookup = write_ped_phrank.phrank_lookup,
 			runtime_attributes = default_runtime_attributes
 	}
 
@@ -89,20 +86,17 @@ workflow tertiary_analysis {
 	}
 }
 
-task write_yaml_ped_phrank {
+task write_ped_phrank {
 	input {
 		String cohort_id
 		File cohort_json
 
-		File hpo_terms
-		File hpo_dag
-		File hpo_annotations
-		File ensembl_to_hgnc
+		Array[String] phenotypes
 
 		RuntimeAttributes runtime_attributes
 	}
 
-	Int disk_size = ceil((size(hpo_terms, "GB") + size(hpo_dag, "GB") + size(hpo_annotations, "GB") + size(ensembl_to_hgnc, "GB")) * 2 + 20)
+	Int disk_size = 20
 
 	command <<<
 		set -euo pipefail
@@ -146,7 +140,7 @@ task write_yaml_ped_phrank {
 
 		def parse_family(family):
 				"""For a family struct, return a list of lists of PED fields for each sample."""
-				family_id = family["family_id"]
+				family_id = family["cohort_id"]
 				samples = []
 				for sample in family["samples"]:
 						samples.append(parse_sample(family_id, sample))
@@ -172,31 +166,32 @@ task write_yaml_ped_phrank {
 						sys.exit(0)
 				main()
 		EOF
-    
-		chmod +x json2ped.py
 
-		json2ped.py \
-			~{cohort_json} \
-			> ~{cohort_id}.ped
+		python3 ./json2ped.py ~{cohort_json} > ~{cohort_id}.ped
+
+		cat ~{cohort_id}.ped
+
+		# ENV HPO_TERMS_TSV "/opt/data/hpo/hpoTerms.txt"
+		# ENV HPO_DAG_TSV "/opt/data/hpo/hpoDag.txt"
+		# ENV ENSEMBL_TO_HPO_TSV "/opt/data/hpo/ensembl.hpoPhenotype.tsv"
+		# ENV ENSEMBL_TO_HGNC "/opt/data/genes/ensembl.hgncSymbol.tsv"
 
 		calculate_phrank.py \
-			~{hpo_terms} \
-			~{hpo_dag} \
-			~{hpo_annotations} \
-			~{ensembl_to_hgnc} \
-			~{cohort_id}.yml \
-			~{cohort_id} \
+			"${HPO_TERMS_TSV}" \
+			"${HPO_DAG_TSV}" \
+			"${ENSEMBL_TO_HPO_TSV}" \
+			"${ENSEMBL_TO_HGNC}" \
+			~{sep="," phenotypes} \
 			~{cohort_id}_phrank.tsv
 	>>>
 
 	output {
-		File cohort_yaml = "~{cohort_id}.yml"
 		File pedigree = "~{cohort_id}.ped"
 		File phrank_lookup = "~{cohort_id}_phrank.tsv"
 	}
 
 	runtime {
-		docker: "~{runtime_attributes.container_registry}/pyyaml@sha256:af6f0689a7412b1edf76bd4bf6434e7fa6a86192eebf19573e8618880d9c1dbb"
+		docker: "~{runtime_attributes.container_registry}/wgs_tertiary@sha256:46f14de75798b54a38055a364a23ca1c9497bf810fee860431b78abc553434f2"
 		cpu: 2
 		memory: "4 GB"
 		disk: disk_size + " GB"