From f96984cebd34673f8df3039c261d8521548a43b2 Mon Sep 17 00:00:00 2001
From: Daniel Danis <daniel.gordon.danis@protonmail.com>
Date: Mon, 13 Jan 2025 22:18:05 +0100
Subject: [PATCH 1/3] Add Python test data files.

---
 python/data/v1/README.md        |   9 +
 python/data/v1/cohort.json      | 251 ++++++++++++++++++++++++++
 python/data/v1/cohort.pb        |  80 ++++++++
 python/data/v1/family.json      | 268 +++++++++++++++++++++++++++
 python/data/v1/family.pb        |  83 +++++++++
 python/data/v1/phenopacket.json | 189 +++++++++++++++++++
 python/data/v1/phenopacket.pb   |  60 ++++++
 python/data/v2/cohort.json      | 294 ++++++++++++++++++++++++++++++
 python/data/v2/cohort.pb        | Bin 0 -> 3099 bytes
 python/data/v2/family.json      | 311 ++++++++++++++++++++++++++++++++
 python/data/v2/family.pb        | Bin 0 -> 3130 bytes
 python/data/v2/phenopacket.json | 220 ++++++++++++++++++++++
 python/data/v2/phenopacket.pb   |  71 ++++++++
 python/tests/conftest.py        |  21 +++
 python/tests/test_io.py         | 120 ++++++++++++
 15 files changed, 1977 insertions(+)
 create mode 100644 python/data/v1/README.md
 create mode 100644 python/data/v1/cohort.json
 create mode 100644 python/data/v1/cohort.pb
 create mode 100644 python/data/v1/family.json
 create mode 100644 python/data/v1/family.pb
 create mode 100644 python/data/v1/phenopacket.json
 create mode 100644 python/data/v1/phenopacket.pb
 create mode 100644 python/data/v2/cohort.json
 create mode 100644 python/data/v2/cohort.pb
 create mode 100644 python/data/v2/family.json
 create mode 100644 python/data/v2/family.pb
 create mode 100644 python/data/v2/phenopacket.json
 create mode 100644 python/data/v2/phenopacket.pb
 create mode 100644 python/tests/test_io.py

diff --git a/python/data/v1/README.md b/python/data/v1/README.md
new file mode 100644
index 0000000..f312473
--- /dev/null
+++ b/python/data/v1/README.md
@@ -0,0 +1,9 @@
+# README
+
+The files in this folder correspond to comprehensive, albeit medically invalid, phenopacket elements: 
+- phenopacket
+- family, or
+- cohort.
+
+The content corresponds to the output of `TestData.V1.comprehensive*()` as of Oct 27th, 2022
+(see [TestData](https://github.com/phenopackets/phenopacket-tools/blob/main/phenopacket-tools-test/src/main/java/org/phenopackets/phenopackettools/test/TestData.java) in phenopacket-tools).
diff --git a/python/data/v1/cohort.json b/python/data/v1/cohort.json
new file mode 100644
index 0000000..17ab00c
--- /dev/null
+++ b/python/data/v1/cohort.json
@@ -0,0 +1,251 @@
+{
+  "id": "comprehensive-cohort-id",
+  "description": "A description of the example cohort.",
+  "members": [{
+    "id": "comprehensive-phenopacket-id",
+    "subject": {
+      "id": "14 year-old boy",
+      "alternateIds": ["boy", "patient", "proband"],
+      "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+      "ageAtCollection": {
+        "age": "P14Y"
+      },
+      "sex": "MALE",
+      "karyotypicSex": "XY",
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      }
+    },
+    "phenotypicFeatures": [{
+      "type": {
+        "id": "HP:0001558",
+        "label": "Decreased fetal movement"
+      },
+      "classOfOnset": {
+        "id": "HP:0011461",
+        "label": "Fetal onset"
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0031910",
+        "label": "Abnormal cranial nerve physiology"
+      },
+      "negated": true,
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0011463",
+        "label": "Macroscopic hematuria"
+      },
+      "modifiers": [{
+        "id": "HP:0031796",
+        "label": "Recurrent"
+      }],
+      "ageOfOnset": {
+        "age": "P14Y"
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0001270",
+        "label": "Motor delay"
+      },
+      "severity": {
+        "id": "HP:0012825",
+        "label": "Mild"
+      },
+      "classOfOnset": {
+        "id": "HP:0011463",
+        "label": "Childhood onset"
+      }
+    }],
+    "biosamples": [{
+      "id": "biosample-id",
+      "individualId": "14 year-old boy",
+      "description": "Muscle biopsy of 14 year-old boy",
+      "sampledTissue": {
+        "id": "UBERON:0003403",
+        "label": "skin of forearm"
+      },
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      },
+      "ageOfIndividualAtCollection": {
+        "age": "P14Y"
+      },
+      "histologicalDiagnosis": {
+        "id": "NCIT:C38757",
+        "label": "Negative Finding"
+      },
+      "tumorProgression": {
+        "id": "NCIT:C3677",
+        "label": "Benign Neoplasm"
+      },
+      "tumorGrade": {
+        "id": "NCIT:C28076",
+        "label": "Disease Grade Qualifier"
+      },
+      "diagnosticMarkers": [{
+        "id": "NCIT:C68748",
+        "label": "HER2/Neu Positive"
+      }]
+    }],
+    "genes": [{
+      "id": "HGNC1:3688",
+      "symbol": "FGFR1"
+    }],
+    "variants": [{
+      "hgvsAllele": {
+        "hgvs": "NM_001848.2:c.877G\u003eA"
+      },
+      "zygosity": {
+        "id": "GENO:0000135",
+        "label": "heterozygous"
+      }
+    }],
+    "diseases": [{
+      "term": {
+        "id": "OMIM:101600",
+        "label": "PFEIFFER SYNDROME"
+      },
+      "classOfOnset": {
+        "id": "HP:0003577",
+        "label": "Congenital onset"
+      }
+    }],
+    "htsFiles": [{
+      "uri": "file://data/genomes/P000001C",
+      "description": "Whole genome sequencing VCF output",
+      "htsFormat": "VCF",
+      "genomeAssembly": "GRCh38.p13",
+      "individualToSampleIdentifiers": {
+        "14 year-old boy": "P000001C"
+      }
+    }],
+    "metaData": {
+      "created": "2022-10-03T16:39:04.000123456Z",
+      "createdBy": "Peter R.",
+      "submittedBy": "PhenopacketLab",
+      "resources": [{
+        "id": "hp",
+        "name": "human phenotype ontology",
+        "url": "http://purl.obolibrary.org/obo/hp.owl",
+        "version": "2018-03-08",
+        "namespacePrefix": "HP",
+        "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+      }, {
+        "id": "geno",
+        "name": "Genotype Ontology",
+        "url": "http://purl.obolibrary.org/obo/geno.owl",
+        "version": "19-03-2018",
+        "namespacePrefix": "GENO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+      }, {
+        "id": "pubmed",
+        "name": "PubMed",
+        "namespacePrefix": "PMID",
+        "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+      }, {
+        "id": "ncit",
+        "name": "NCI Thesaurus",
+        "url": "http://purl.obolibrary.org/obo/ncit.owl",
+        "version": "20-03-2020",
+        "namespacePrefix": "NCIT",
+        "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+      }],
+      "phenopacketSchemaVersion": "1.0.0",
+      "externalReferences": [{
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }]
+    }
+  }, {
+    "subject": {
+      "id": "MOTHER",
+      "sex": "FEMALE"
+    }
+  }, {
+    "subject": {
+      "id": "FATHER",
+      "sex": "MALE"
+    }
+  }],
+  "htsFiles": [{
+    "uri": "file://data/genomes/FAM000001",
+    "description": "Whole genome sequencing VCF output",
+    "htsFormat": "VCF",
+    "genomeAssembly": "GRCh38.p13",
+    "individualToSampleIdentifiers": {
+      "14 year-old boy": "P000001C",
+      "MOTHER": "P000001M",
+      "FATHER": "P000001F"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "1.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v1/cohort.pb b/python/data/v1/cohort.pb
new file mode 100644
index 0000000..5c57f5e
--- /dev/null
+++ b/python/data/v1/cohort.pb
@@ -0,0 +1,80 @@
+
+comprehensive-cohort-id$A description of the example cohort.ò
+comprehensive-phenopacket-id\
+14 year-old boyboypatientprobandÀÄd"
+P14Y08B
+NCBITaxon:9606homo sapiensï
&
+
+HP:0001558Decreased fetal movementJ
+
+HP:0011461Fetal onsetR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ß
/
+
+HP:0031910!Abnormal cranial nerve physiology
R©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ò
#
+
+HP:0011463Macroscopic hematuria*
+
+HP:0031796	Recurrent2
+P14YR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.N
+
+HP:0001270Motor delay"
+
+HP:0012825MildJ
+
+HP:0011463Childhood onset"–
+biosample-id14 year-old boy Muscle biopsy of 14 year-old boy"!
+UBERON:0003403skin of forearm2
+NCBITaxon:9606homo sapiens:
+P14YJ
+NCIT:C38757Negative FindingR
+
+NCIT:C3677Benign NeoplasmZ&
+NCIT:C28076Disease Grade Qualifierb 
+NCIT:C68748HER2/Neu Positive*
+
+HGNC1:3688FGFR126NM_001848.2:c.877G>A2
+GENO:0000135heterozygous:B
+ 
+OMIM:101600PFEIFFER SYNDROME"
+
+HP:0003577Congenital onsetBm
+file://data/genomes/P000001C"Whole genome sequencing VCF output"
+GRCh38.p13*
+14 year-old boyP000001CJÁ
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_21.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
+
+MOTHER0

+
+FATHER0"–

+file://data/genomes/FAM000001"Whole genome sequencing VCF output"
+GRCh38.p13*
+14 year-old boyP000001C*
+MOTHERP000001M*
+FATHERP000001F*Á
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_21.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
\ No newline at end of file
diff --git a/python/data/v1/family.json b/python/data/v1/family.json
new file mode 100644
index 0000000..b7ad2d7
--- /dev/null
+++ b/python/data/v1/family.json
@@ -0,0 +1,268 @@
+{
+  "id": "comprehensive-family-id",
+  "proband": {
+    "id": "comprehensive-phenopacket-id",
+    "subject": {
+      "id": "14 year-old boy",
+      "alternateIds": ["boy", "patient", "proband"],
+      "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+      "ageAtCollection": {
+        "age": "P14Y"
+      },
+      "sex": "MALE",
+      "karyotypicSex": "XY",
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      }
+    },
+    "phenotypicFeatures": [{
+      "type": {
+        "id": "HP:0001558",
+        "label": "Decreased fetal movement"
+      },
+      "classOfOnset": {
+        "id": "HP:0011461",
+        "label": "Fetal onset"
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0031910",
+        "label": "Abnormal cranial nerve physiology"
+      },
+      "negated": true,
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0011463",
+        "label": "Macroscopic hematuria"
+      },
+      "modifiers": [{
+        "id": "HP:0031796",
+        "label": "Recurrent"
+      }],
+      "ageOfOnset": {
+        "age": "P14Y"
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0001270",
+        "label": "Motor delay"
+      },
+      "severity": {
+        "id": "HP:0012825",
+        "label": "Mild"
+      },
+      "classOfOnset": {
+        "id": "HP:0011463",
+        "label": "Childhood onset"
+      }
+    }],
+    "biosamples": [{
+      "id": "biosample-id",
+      "individualId": "14 year-old boy",
+      "description": "Muscle biopsy of 14 year-old boy",
+      "sampledTissue": {
+        "id": "UBERON:0003403",
+        "label": "skin of forearm"
+      },
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      },
+      "ageOfIndividualAtCollection": {
+        "age": "P14Y"
+      },
+      "histologicalDiagnosis": {
+        "id": "NCIT:C38757",
+        "label": "Negative Finding"
+      },
+      "tumorProgression": {
+        "id": "NCIT:C3677",
+        "label": "Benign Neoplasm"
+      },
+      "tumorGrade": {
+        "id": "NCIT:C28076",
+        "label": "Disease Grade Qualifier"
+      },
+      "diagnosticMarkers": [{
+        "id": "NCIT:C68748",
+        "label": "HER2/Neu Positive"
+      }]
+    }],
+    "genes": [{
+      "id": "HGNC1:3688",
+      "symbol": "FGFR1"
+    }],
+    "variants": [{
+      "hgvsAllele": {
+        "hgvs": "NM_001848.2:c.877G\u003eA"
+      },
+      "zygosity": {
+        "id": "GENO:0000135",
+        "label": "heterozygous"
+      }
+    }],
+    "diseases": [{
+      "term": {
+        "id": "OMIM:101600",
+        "label": "PFEIFFER SYNDROME"
+      },
+      "classOfOnset": {
+        "id": "HP:0003577",
+        "label": "Congenital onset"
+      }
+    }],
+    "htsFiles": [{
+      "uri": "file://data/genomes/P000001C",
+      "description": "Whole genome sequencing VCF output",
+      "htsFormat": "VCF",
+      "genomeAssembly": "GRCh38.p13",
+      "individualToSampleIdentifiers": {
+        "14 year-old boy": "P000001C"
+      }
+    }],
+    "metaData": {
+      "created": "2022-10-03T16:39:04.000123456Z",
+      "createdBy": "Peter R.",
+      "submittedBy": "PhenopacketLab",
+      "resources": [{
+        "id": "hp",
+        "name": "human phenotype ontology",
+        "url": "http://purl.obolibrary.org/obo/hp.owl",
+        "version": "2018-03-08",
+        "namespacePrefix": "HP",
+        "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+      }, {
+        "id": "geno",
+        "name": "Genotype Ontology",
+        "url": "http://purl.obolibrary.org/obo/geno.owl",
+        "version": "19-03-2018",
+        "namespacePrefix": "GENO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+      }, {
+        "id": "pubmed",
+        "name": "PubMed",
+        "namespacePrefix": "PMID",
+        "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+      }, {
+        "id": "ncit",
+        "name": "NCI Thesaurus",
+        "url": "http://purl.obolibrary.org/obo/ncit.owl",
+        "version": "20-03-2020",
+        "namespacePrefix": "NCIT",
+        "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+      }],
+      "phenopacketSchemaVersion": "1.0.0",
+      "externalReferences": [{
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }]
+    }
+  },
+  "relatives": [{
+    "subject": {
+      "id": "MOTHER",
+      "sex": "FEMALE"
+    }
+  }, {
+    "subject": {
+      "id": "FATHER",
+      "sex": "MALE"
+    }
+  }],
+  "pedigree": {
+    "persons": [{
+      "individualId": "14 year-old boy",
+      "paternalId": "FATHER",
+      "maternalId": "MOTHER",
+      "sex": "MALE",
+      "affectedStatus": "AFFECTED"
+    }, {
+      "individualId": "MOTHER",
+      "sex": "FEMALE",
+      "affectedStatus": "UNAFFECTED"
+    }, {
+      "individualId": "FATHER",
+      "sex": "MALE",
+      "affectedStatus": "UNAFFECTED"
+    }]
+  },
+  "htsFiles": [{
+    "uri": "file://data/genomes/FAM000001",
+    "description": "Whole genome sequencing VCF output",
+    "htsFormat": "VCF",
+    "genomeAssembly": "GRCh38.p13",
+    "individualToSampleIdentifiers": {
+      "14 year-old boy": "P000001C",
+      "MOTHER": "P000001M",
+      "FATHER": "P000001F"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "1.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v1/family.pb b/python/data/v1/family.pb
new file mode 100644
index 0000000..fb13105
--- /dev/null
+++ b/python/data/v1/family.pb
@@ -0,0 +1,83 @@
+
+comprehensive-family-idò
+comprehensive-phenopacket-id\
+14 year-old boyboypatientprobandÀÄd"
+P14Y08B
+NCBITaxon:9606homo sapiensï
&
+
+HP:0001558Decreased fetal movementJ
+
+HP:0011461Fetal onsetR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ß
/
+
+HP:0031910!Abnormal cranial nerve physiology
R©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ò
#
+
+HP:0011463Macroscopic hematuria*
+
+HP:0031796	Recurrent2
+P14YR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.N
+
+HP:0001270Motor delay"
+
+HP:0012825MildJ
+
+HP:0011463Childhood onset"–
+biosample-id14 year-old boy Muscle biopsy of 14 year-old boy"!
+UBERON:0003403skin of forearm2
+NCBITaxon:9606homo sapiens:
+P14YJ
+NCIT:C38757Negative FindingR
+
+NCIT:C3677Benign NeoplasmZ&
+NCIT:C28076Disease Grade Qualifierb 
+NCIT:C68748HER2/Neu Positive*
+
+HGNC1:3688FGFR126NM_001848.2:c.877G>A2
+GENO:0000135heterozygous:B
+ 
+OMIM:101600PFEIFFER SYNDROME"
+
+HP:0003577Congenital onsetBm
+file://data/genomes/P000001C"Whole genome sequencing VCF output"
+GRCh38.p13*
+14 year-old boyP000001CJÁ
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_21.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
+
+MOTHER0

+
+FATHER0"C
+%14 year-old boyFATHER"MOTHER(0
+MOTHER(
0

+FATHER(0
*–

+file://data/genomes/FAM000001"Whole genome sequencing VCF output"
+GRCh38.p13*
+14 year-old boyP000001C*
+MOTHERP000001M*
+FATHERP000001F2Á
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_21.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
\ No newline at end of file
diff --git a/python/data/v1/phenopacket.json b/python/data/v1/phenopacket.json
new file mode 100644
index 0000000..e6848a9
--- /dev/null
+++ b/python/data/v1/phenopacket.json
@@ -0,0 +1,189 @@
+{
+  "id": "comprehensive-phenopacket-id",
+  "subject": {
+    "id": "14 year-old boy",
+    "alternateIds": ["boy", "patient", "proband"],
+    "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+    "ageAtCollection": {
+      "age": "P14Y"
+    },
+    "sex": "MALE",
+    "karyotypicSex": "XY",
+    "taxonomy": {
+      "id": "NCBITaxon:9606",
+      "label": "homo sapiens"
+    }
+  },
+  "phenotypicFeatures": [{
+    "type": {
+      "id": "HP:0001558",
+      "label": "Decreased fetal movement"
+    },
+    "classOfOnset": {
+      "id": "HP:0011461",
+      "label": "Fetal onset"
+    },
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0031910",
+      "label": "Abnormal cranial nerve physiology"
+    },
+    "negated": true,
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0011463",
+      "label": "Macroscopic hematuria"
+    },
+    "modifiers": [{
+      "id": "HP:0031796",
+      "label": "Recurrent"
+    }],
+    "ageOfOnset": {
+      "age": "P14Y"
+    },
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0001270",
+      "label": "Motor delay"
+    },
+    "severity": {
+      "id": "HP:0012825",
+      "label": "Mild"
+    },
+    "classOfOnset": {
+      "id": "HP:0011463",
+      "label": "Childhood onset"
+    }
+  }],
+  "biosamples": [{
+    "id": "biosample-id",
+    "individualId": "14 year-old boy",
+    "description": "Muscle biopsy of 14 year-old boy",
+    "sampledTissue": {
+      "id": "UBERON:0003403",
+      "label": "skin of forearm"
+    },
+    "taxonomy": {
+      "id": "NCBITaxon:9606",
+      "label": "homo sapiens"
+    },
+    "ageOfIndividualAtCollection": {
+      "age": "P14Y"
+    },
+    "histologicalDiagnosis": {
+      "id": "NCIT:C38757",
+      "label": "Negative Finding"
+    },
+    "tumorProgression": {
+      "id": "NCIT:C3677",
+      "label": "Benign Neoplasm"
+    },
+    "tumorGrade": {
+      "id": "NCIT:C28076",
+      "label": "Disease Grade Qualifier"
+    },
+    "diagnosticMarkers": [{
+      "id": "NCIT:C68748",
+      "label": "HER2/Neu Positive"
+    }]
+  }],
+  "genes": [{
+    "id": "HGNC1:3688",
+    "symbol": "FGFR1"
+  }],
+  "variants": [{
+    "hgvsAllele": {
+      "hgvs": "NM_001848.2:c.877G\u003eA"
+    },
+    "zygosity": {
+      "id": "GENO:0000135",
+      "label": "heterozygous"
+    }
+  }],
+  "diseases": [{
+    "term": {
+      "id": "OMIM:101600",
+      "label": "PFEIFFER SYNDROME"
+    },
+    "classOfOnset": {
+      "id": "HP:0003577",
+      "label": "Congenital onset"
+    }
+  }],
+  "htsFiles": [{
+    "uri": "file://data/genomes/P000001C",
+    "description": "Whole genome sequencing VCF output",
+    "htsFormat": "VCF",
+    "genomeAssembly": "GRCh38.p13",
+    "individualToSampleIdentifiers": {
+      "14 year-old boy": "P000001C"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "1.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v1/phenopacket.pb b/python/data/v1/phenopacket.pb
new file mode 100644
index 0000000..8fe66cc
--- /dev/null
+++ b/python/data/v1/phenopacket.pb
@@ -0,0 +1,60 @@
+
+comprehensive-phenopacket-id\
+14 year-old boyboypatientprobandÀÄd"
+P14Y08B
+NCBITaxon:9606homo sapiensï
&
+
+HP:0001558Decreased fetal movementJ
+
+HP:0011461Fetal onsetR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ß
/
+
+HP:0031910!Abnormal cranial nerve physiology
R©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ò
#
+
+HP:0011463Macroscopic hematuria*
+
+HP:0031796	Recurrent2
+P14YR©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.N
+
+HP:0001270Motor delay"
+
+HP:0012825MildJ
+
+HP:0011463Childhood onset"–
+biosample-id14 year-old boy Muscle biopsy of 14 year-old boy"!
+UBERON:0003403skin of forearm2
+NCBITaxon:9606homo sapiens:
+P14YJ
+NCIT:C38757Negative FindingR
+
+NCIT:C3677Benign NeoplasmZ&
+NCIT:C28076Disease Grade Qualifierb 
+NCIT:C68748HER2/Neu Positive*
+
+HGNC1:3688FGFR126NM_001848.2:c.877G>A2
+GENO:0000135heterozygous:B
+ 
+OMIM:101600PFEIFFER SYNDROME"
+
+HP:0003577Congenital onsetBm
+file://data/genomes/P000001C"Whole genome sequencing VCF output"
+GRCh38.p13*
+14 year-old boyP000001CJÁ
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_21.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
\ No newline at end of file
diff --git a/python/data/v2/cohort.json b/python/data/v2/cohort.json
new file mode 100644
index 0000000..e59170a
--- /dev/null
+++ b/python/data/v2/cohort.json
@@ -0,0 +1,294 @@
+{
+  "id": "comprehensive-cohort-id",
+  "description": "A description of the example cohort.",
+  "members": [{
+    "id": "comprehensive-phenopacket-id",
+    "subject": {
+      "id": "14 year-old boy",
+      "alternateIds": ["boy", "patient", "proband"],
+      "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+      "timeAtLastEncounter": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "sex": "MALE",
+      "karyotypicSex": "XY",
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      }
+    },
+    "phenotypicFeatures": [{
+      "type": {
+        "id": "HP:0001558",
+        "label": "Decreased fetal movement"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0011461",
+          "label": "Fetal onset"
+        }
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0031910",
+        "label": "Abnormal cranial nerve physiology"
+      },
+      "excluded": true,
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0011463",
+        "label": "Macroscopic hematuria"
+      },
+      "modifiers": [{
+        "id": "HP:0031796",
+        "label": "Recurrent"
+      }],
+      "onset": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0001270",
+        "label": "Motor delay"
+      },
+      "severity": {
+        "id": "HP:0012825",
+        "label": "Mild"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0011463",
+          "label": "Childhood onset"
+        }
+      }
+    }],
+    "biosamples": [{
+      "id": "biosample-id",
+      "individualId": "14 year-old boy",
+      "description": "Muscle biopsy of 14 year-old boy",
+      "sampledTissue": {
+        "id": "UBERON:0003403",
+        "label": "skin of forearm"
+      },
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      },
+      "timeOfCollection": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "histologicalDiagnosis": {
+        "id": "NCIT:C38757",
+        "label": "Negative Finding"
+      },
+      "tumorProgression": {
+        "id": "NCIT:C3677",
+        "label": "Benign Neoplasm"
+      },
+      "tumorGrade": {
+        "id": "NCIT:C28076",
+        "label": "Disease Grade Qualifier"
+      },
+      "diagnosticMarkers": [{
+        "id": "NCIT:C68748",
+        "label": "HER2/Neu Positive"
+      }],
+      "materialSample": {
+        "id": "EFO:0009655",
+        "label": "abnormal sample"
+      }
+    }],
+    "interpretations": [{
+      "id": "comprehensive-phenopacket-id",
+      "progressStatus": "SOLVED",
+      "diagnosis": {
+        "disease": {
+          "id": "OMIM:101600",
+          "label": "PFEIFFER SYNDROME"
+        },
+        "genomicInterpretations": [{
+          "subjectOrBiosampleId": "14 year-old boy",
+          "interpretationStatus": "CAUSATIVE",
+          "variantInterpretation": {
+            "variationDescriptor": {
+              "expressions": [{
+                "syntax": "hgvs",
+                "value": "NM_001848.2:c.877G\u003eA"
+              }],
+              "allelicState": {
+                "id": "GENO:0000135",
+                "label": "heterozygous"
+              }
+            }
+          }
+        }]
+      }
+    }],
+    "diseases": [{
+      "term": {
+        "id": "OMIM:101600",
+        "label": "PFEIFFER SYNDROME"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0003577",
+          "label": "Congenital onset"
+        }
+      }
+    }],
+    "files": [{
+      "uri": "file://data/genomes/P000001C",
+      "individualToFileIdentifiers": {
+        "14 year-old boy": "P000001C"
+      },
+      "fileAttributes": {
+        "genomeAssembly": "GRCh38.p13",
+        "fileFormat": "vcf",
+        "description": "Whole genome sequencing VCF output"
+      }
+    }],
+    "metaData": {
+      "created": "2022-10-03T16:39:04.000123456Z",
+      "createdBy": "Peter R.",
+      "submittedBy": "PhenopacketLab",
+      "resources": [{
+        "id": "hp",
+        "name": "human phenotype ontology",
+        "url": "http://purl.obolibrary.org/obo/hp.owl",
+        "version": "2018-03-08",
+        "namespacePrefix": "HP",
+        "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+      }, {
+        "id": "geno",
+        "name": "Genotype Ontology",
+        "url": "http://purl.obolibrary.org/obo/geno.owl",
+        "version": "19-03-2018",
+        "namespacePrefix": "GENO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+      }, {
+        "id": "pubmed",
+        "name": "PubMed",
+        "namespacePrefix": "PMID",
+        "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+      }, {
+        "id": "ncit",
+        "name": "NCI Thesaurus",
+        "url": "http://purl.obolibrary.org/obo/ncit.owl",
+        "version": "20-03-2020",
+        "namespacePrefix": "NCIT",
+        "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+      }],
+      "phenopacketSchemaVersion": "2.0.0",
+      "externalReferences": [{
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }]
+    }
+  }, {
+    "subject": {
+      "id": "MOTHER",
+      "dateOfBirth": "1970-01-01T00:00:00Z",
+      "timeAtLastEncounter": {
+      },
+      "sex": "FEMALE",
+      "taxonomy": {
+      }
+    }
+  }, {
+    "subject": {
+      "id": "FATHER",
+      "dateOfBirth": "1970-01-01T00:00:00Z",
+      "timeAtLastEncounter": {
+      },
+      "sex": "MALE",
+      "taxonomy": {
+      }
+    }
+  }],
+  "files": [{
+    "uri": "file://data/genomes/FAM000001",
+    "individualToFileIdentifiers": {
+      "14 year-old boy": "P000001C",
+      "MOTHER": "P000001M",
+      "FATHER": "P000001F"
+    },
+    "fileAttributes": {
+      "genomeAssembly": "GRCh38.p13",
+      "fileFormat": "vcf",
+      "description": "Whole genome sequencing VCF output"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "2.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v2/cohort.pb b/python/data/v2/cohort.pb
new file mode 100644
index 0000000000000000000000000000000000000000..0679cfa09cdfea17ce246282ad8dae72315c188f
GIT binary patch
literal 3099
zcmeHJ-EJF26pmAqhDn<^BT&mWZKq2qlBKNoC$=|MRpB^xe$=&%8$j&^(d_QnyL5MF
z*`0N|z2q&*4Tvjv1+GBig16uWxIy9pn6cyZ4{EL|RqBo7%$#$+Ip3V`8-q&@4daA(
zBuf1;*>tE!6SnEQ@MaUaBy|!$W<HG&9U|rtL>}QV4hWjYDbf$?VB`4;F)u}9>^vls
zGGBr<Z42cDCz~{Ikxg@WPJEn?G4n~p_?Lv*IC7<><zId~UvlMTump;IZR@_eXf7UJ
z1FPNE&cP9WM5D%bO|8KT9t|l<am>?G>8}F31;Bp4p{lA@t(x%iE^!iqQ{ti_VK_h`
z9g~nF=~tu=P9rsKtERz~&SalPDPcQ56~HH8rQPa@LaJ&QP{SGHWT2E`HYtG8ERH!l
zyt17mmSBfqn{$znAxTK&5J<qqzICwMFjP}D4NaGhTD`lqriQ|d7ZEfD1iOATLX4sv
z!n}ZlD9kxs%*)Y<&pckt$r4_TA&-QZWr>d)2qT9##P<ZeBK=W-mD5fPZCg{}jiw#Z
zB;?IH366aJHzLWHpxDb(p9XZ4UoN~+9sXT_A3k$e27KSbPC`?M#=i5EnewGG8tU6M
z`0ijvo_;n&Z&cfTIGa#a)9Wf+u_)sc=#l{EGMo{jn|c)%EkAJe>(bTPDj#VBuC+YA
z>{05X$yk?vUIZ6xpQaPl3R%CXMj2UI>hLM%QE{3Joxh;h@(r;1*-m@V>k4TYTPlZ1
zANmtZ7*Z~^B%G(x!P#{@xDHmjt%IXR%P{NJIxKa`h%1B7YR8X+GHl+^X+W)Bhif||
z@<$Qs5*i0M4ZpfI%hye{UW1o*{Zxn@?IqYH=+g`b{?I4MHw82cteN#K6Rz*K2YRJT
zGSsK3FA%>iT;qc8Oa#AOt5)F}o~dX`m;R*iYI7@{lTHA~=~)L>LsPYys>1btr+v`r
zv<K+k{qF9dXSLzImn^VUl<!El^$k$;M&lH|*R_thdzo9NqBk7Htk?JMG?NW*VXxht
z`jKW-x$hB168bnF(JXE3&Igu|bnSFHRHMqtEVXDf;(Q8MoQ%idJKo{Y4@jd@aWTUc
zzDq-rR{FvNRjmcDymWTBJlm8u!0I%inWiMPgB*grLCZ5tCDsgS9RN|fBaDf`b7N;H
zX<+4<HwDUHc$81xv<6Da*BN(F;f|lTI*4X0&e(%rivTSD`2C+xmP-72;NXG;G*G0~
z{?mu%F1F<yEP64#>}4U2xbg8uSRNDJCz}|c^pVF{%=?V9Bv7bL1K&<?k}EVBRrtRZ
zFIMPDAOoFW#HMO&s%Cj{zpu-4()Rnu@?%gGJ;3$78ES8a`th7}kvGNFwgsv{FBiqV
z>o@15ilAfpHdu-?J0vb#>Swk^+;UMoLDTG%_j_`3qC}4ED^U<Ck?$!ZI_4yZl!`nC
zMb0>b7rErnkw;RTC0Q!XJGID}u{Axlu9k~JwsTJ{f{yifbVXIv#%p>nAuNF<t9QgL
zKw6L&)WYF{G+FC3&(;<X7v$dy;Of7rq0_XcdU&NAAe@1mNyHLsQ;@T@&g+m(`K@gJ
NOXqK8^FM!P{sR?zzQF(h

literal 0
HcmV?d00001

diff --git a/python/data/v2/family.json b/python/data/v2/family.json
new file mode 100644
index 0000000..b29f296
--- /dev/null
+++ b/python/data/v2/family.json
@@ -0,0 +1,311 @@
+{
+  "id": "comprehensive-family-id",
+  "proband": {
+    "id": "comprehensive-phenopacket-id",
+    "subject": {
+      "id": "14 year-old boy",
+      "alternateIds": ["boy", "patient", "proband"],
+      "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+      "timeAtLastEncounter": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "sex": "MALE",
+      "karyotypicSex": "XY",
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      }
+    },
+    "phenotypicFeatures": [{
+      "type": {
+        "id": "HP:0001558",
+        "label": "Decreased fetal movement"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0011461",
+          "label": "Fetal onset"
+        }
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0031910",
+        "label": "Abnormal cranial nerve physiology"
+      },
+      "excluded": true,
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0011463",
+        "label": "Macroscopic hematuria"
+      },
+      "modifiers": [{
+        "id": "HP:0031796",
+        "label": "Recurrent"
+      }],
+      "onset": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "evidence": [{
+        "evidenceCode": {
+          "id": "ECO:0000033",
+          "label": "author statement supported by traceable reference"
+        },
+        "reference": {
+          "id": "PMID:30808312",
+          "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+        }
+      }]
+    }, {
+      "type": {
+        "id": "HP:0001270",
+        "label": "Motor delay"
+      },
+      "severity": {
+        "id": "HP:0012825",
+        "label": "Mild"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0011463",
+          "label": "Childhood onset"
+        }
+      }
+    }],
+    "biosamples": [{
+      "id": "biosample-id",
+      "individualId": "14 year-old boy",
+      "description": "Muscle biopsy of 14 year-old boy",
+      "sampledTissue": {
+        "id": "UBERON:0003403",
+        "label": "skin of forearm"
+      },
+      "taxonomy": {
+        "id": "NCBITaxon:9606",
+        "label": "homo sapiens"
+      },
+      "timeOfCollection": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      },
+      "histologicalDiagnosis": {
+        "id": "NCIT:C38757",
+        "label": "Negative Finding"
+      },
+      "tumorProgression": {
+        "id": "NCIT:C3677",
+        "label": "Benign Neoplasm"
+      },
+      "tumorGrade": {
+        "id": "NCIT:C28076",
+        "label": "Disease Grade Qualifier"
+      },
+      "diagnosticMarkers": [{
+        "id": "NCIT:C68748",
+        "label": "HER2/Neu Positive"
+      }],
+      "materialSample": {
+        "id": "EFO:0009655",
+        "label": "abnormal sample"
+      }
+    }],
+    "interpretations": [{
+      "id": "comprehensive-phenopacket-id",
+      "progressStatus": "SOLVED",
+      "diagnosis": {
+        "disease": {
+          "id": "OMIM:101600",
+          "label": "PFEIFFER SYNDROME"
+        },
+        "genomicInterpretations": [{
+          "subjectOrBiosampleId": "14 year-old boy",
+          "interpretationStatus": "CAUSATIVE",
+          "variantInterpretation": {
+            "variationDescriptor": {
+              "expressions": [{
+                "syntax": "hgvs",
+                "value": "NM_001848.2:c.877G\u003eA"
+              }],
+              "allelicState": {
+                "id": "GENO:0000135",
+                "label": "heterozygous"
+              }
+            }
+          }
+        }]
+      }
+    }],
+    "diseases": [{
+      "term": {
+        "id": "OMIM:101600",
+        "label": "PFEIFFER SYNDROME"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0003577",
+          "label": "Congenital onset"
+        }
+      }
+    }],
+    "files": [{
+      "uri": "file://data/genomes/P000001C",
+      "individualToFileIdentifiers": {
+        "14 year-old boy": "P000001C"
+      },
+      "fileAttributes": {
+        "genomeAssembly": "GRCh38.p13",
+        "fileFormat": "vcf",
+        "description": "Whole genome sequencing VCF output"
+      }
+    }],
+    "metaData": {
+      "created": "2022-10-03T16:39:04.000123456Z",
+      "createdBy": "Peter R.",
+      "submittedBy": "PhenopacketLab",
+      "resources": [{
+        "id": "hp",
+        "name": "human phenotype ontology",
+        "url": "http://purl.obolibrary.org/obo/hp.owl",
+        "version": "2018-03-08",
+        "namespacePrefix": "HP",
+        "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+      }, {
+        "id": "geno",
+        "name": "Genotype Ontology",
+        "url": "http://purl.obolibrary.org/obo/geno.owl",
+        "version": "19-03-2018",
+        "namespacePrefix": "GENO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+      }, {
+        "id": "pubmed",
+        "name": "PubMed",
+        "namespacePrefix": "PMID",
+        "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+      }, {
+        "id": "ncit",
+        "name": "NCI Thesaurus",
+        "url": "http://purl.obolibrary.org/obo/ncit.owl",
+        "version": "20-03-2020",
+        "namespacePrefix": "NCIT",
+        "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+      }],
+      "phenopacketSchemaVersion": "2.0.0",
+      "externalReferences": [{
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }]
+    }
+  },
+  "relatives": [{
+    "subject": {
+      "id": "MOTHER",
+      "dateOfBirth": "1970-01-01T00:00:00Z",
+      "timeAtLastEncounter": {
+      },
+      "sex": "FEMALE",
+      "taxonomy": {
+      }
+    }
+  }, {
+    "subject": {
+      "id": "FATHER",
+      "dateOfBirth": "1970-01-01T00:00:00Z",
+      "timeAtLastEncounter": {
+      },
+      "sex": "MALE",
+      "taxonomy": {
+      }
+    }
+  }],
+  "pedigree": {
+    "persons": [{
+      "individualId": "14 year-old boy",
+      "paternalId": "FATHER",
+      "maternalId": "MOTHER",
+      "sex": "MALE",
+      "affectedStatus": "AFFECTED"
+    }, {
+      "individualId": "MOTHER",
+      "sex": "FEMALE",
+      "affectedStatus": "UNAFFECTED"
+    }, {
+      "individualId": "FATHER",
+      "sex": "MALE",
+      "affectedStatus": "UNAFFECTED"
+    }]
+  },
+  "files": [{
+    "uri": "file://data/genomes/FAM000001",
+    "individualToFileIdentifiers": {
+      "14 year-old boy": "P000001C",
+      "MOTHER": "P000001M",
+      "FATHER": "P000001F"
+    },
+    "fileAttributes": {
+      "genomeAssembly": "GRCh38.p13",
+      "fileFormat": "vcf",
+      "description": "Whole genome sequencing VCF output"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "2.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v2/family.pb b/python/data/v2/family.pb
new file mode 100644
index 0000000000000000000000000000000000000000..cb79a8f1d57b5e59b2b16ad510aa23ce9e1de853
GIT binary patch
literal 3130
zcmeHJ-EJF26pmfvhDn<^BT&mWZKn$@$Wqq(6WbfBsz@9=Nmc*g22guJG`l<YF5TT(
zc4r;7m%K%}0dWPdz!gYb@D{uPH%L4HGj=wG7HY04RqBoHIdjhW=A1d-HwKq%8bmR1
zNtk$3vN^_q=VzOq1HW4b8~@ykxD$=A{fIE(@EKUswopcJyh(irSu}&^#K-vvGmnIf
z|A?uDLq{qv|MbiGiX$(BGAIqTtp{q+EZ)5aR{QPU!z2794O`m{wE-`<G@vNK5f4wK
zKML>`00+aCs;XMOZo<oZ#EuD0h=az2VIKu_N&=3gUy<H9_0+Vjh6Y!<vwa#Sgzf%N
z03U*tPJ18{sj6W>4X4bdF-jO_vjiwfqlm_gXSOoLVr&y^`2@veOkxt+1QKv@*gM>7
z8LFw8hNeqL?ZLgqj)sDiC-G>Ae1aV>oFGQgE@7@u0u*GtUChnUiN{=?%uZvTjUkr=
zn5D6YTL>eY7sU4jydwQpfVI;~3~gIe;f)<Dq;bHDwPPH5{5vG^l%UAX5|8?Hl3gym
zQWgGLfbah8t_=8g58E+KY#Mp?)6P^cowcF4-GFb7^5*GhL-b0OJ%ss$s+!(Z;YyD(
zK7kJLaVEpOA-bv8VX5c&j(%Obnp^ou8*r`da<faRgJxr0{jmrxSRPGq5cx##@mV&?
zsFx--pJMJ6B^jb)^bB9CH^A!0yPeUXFQ{Q`sT?MG<b}d@OgYu!U=d44XV>xYI#}tq
z506@H!)(@@u+k?J&I~@QT`v^Ouy{eI4vl6LuI-Z0n}n!OXyoH0`21ELubXPK0Wa-&
zi6A@LkFi70M=AEbu}9*s3MhAMn9VH{t{-$pdaX}VG^B|q5Wg;5<Am?d2*2H^*Wnt@
zSu}5#{-p3?ajTq@P5{Rl^bUJ1P1PEz3fG6-&SAIP8KL_R`g@~6uLJKtCxMlcd`G&i
zZ-A0JnI`b9e(#v8m$_vsddpVKW^@0}PP_pw?05QeJ<^Oi*FC~WOdn?xnkKEi#lRAh
zuANSYYSei%D{UH1ct3?I&c<W(4X<$Q`J`2=Ihf%Z-=zUbYD1xcs@8^Ao;y2S&NrnE
zusRReNfHuReg?t*sO=i25^09C4uDAA6~e^exv4#tG_c~3#E!j4h#{0ebt#{`c@C72
zFH)|eLLEP8cM(lll(L6EmjGD){@dT5lq>vs;NYSOXrxH1!>13;J#5JtD7q26?4|(@
zx$yBqSQZgpCz}bNbkk)l;&n!8>?_owzGuZa&J-F?YJ6F9BZZ#$GSK-&Y^uhlYF3K}
zLtS1Fb}&4aAA^#p0j}@osDm8!{RQD7ZjP&M3siw#Es1;A-&+tWoQ~z&pd6)EKpa>e
zrdE$Q)slFE=FthS_vGY632n<$LO)PK&s8RL%9|iUYVs76c*hyM$SH@8T$124P7`U-
zsYOiQt@){SwOSIiU3hBYbgaLjE2^TlUebFBVFi?XgCi~h(vrNS7Va)dGh27(%vQX+
zB)7rM=k!r3&z<Dc1RoStE~zkI71V-Q&3*V@q55k9T>Upnb$5DmQoWE<5auU6<5^GG
Z<^X55?#tkw{+fILB^Ix__doxu{snF*zsdjr

literal 0
HcmV?d00001

diff --git a/python/data/v2/phenopacket.json b/python/data/v2/phenopacket.json
new file mode 100644
index 0000000..89d29db
--- /dev/null
+++ b/python/data/v2/phenopacket.json
@@ -0,0 +1,220 @@
+{
+  "id": "comprehensive-phenopacket-id",
+  "subject": {
+    "id": "14 year-old boy",
+    "alternateIds": ["boy", "patient", "proband"],
+    "dateOfBirth": "1970-01-02T10:17:36.000000100Z",
+    "timeAtLastEncounter": {
+      "age": {
+        "iso8601duration": "P14Y"
+      }
+    },
+    "sex": "MALE",
+    "karyotypicSex": "XY",
+    "taxonomy": {
+      "id": "NCBITaxon:9606",
+      "label": "homo sapiens"
+    }
+  },
+  "phenotypicFeatures": [{
+    "type": {
+      "id": "HP:0001558",
+      "label": "Decreased fetal movement"
+    },
+    "onset": {
+      "ontologyClass": {
+        "id": "HP:0011461",
+        "label": "Fetal onset"
+      }
+    },
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0031910",
+      "label": "Abnormal cranial nerve physiology"
+    },
+    "excluded": true,
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0011463",
+      "label": "Macroscopic hematuria"
+    },
+    "modifiers": [{
+      "id": "HP:0031796",
+      "label": "Recurrent"
+    }],
+    "onset": {
+      "age": {
+        "iso8601duration": "P14Y"
+      }
+    },
+    "evidence": [{
+      "evidenceCode": {
+        "id": "ECO:0000033",
+        "label": "author statement supported by traceable reference"
+      },
+      "reference": {
+        "id": "PMID:30808312",
+        "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+      }
+    }]
+  }, {
+    "type": {
+      "id": "HP:0001270",
+      "label": "Motor delay"
+    },
+    "severity": {
+      "id": "HP:0012825",
+      "label": "Mild"
+    },
+    "onset": {
+      "ontologyClass": {
+        "id": "HP:0011463",
+        "label": "Childhood onset"
+      }
+    }
+  }],
+  "biosamples": [{
+    "id": "biosample-id",
+    "individualId": "14 year-old boy",
+    "description": "Muscle biopsy of 14 year-old boy",
+    "sampledTissue": {
+      "id": "UBERON:0003403",
+      "label": "skin of forearm"
+    },
+    "taxonomy": {
+      "id": "NCBITaxon:9606",
+      "label": "homo sapiens"
+    },
+    "timeOfCollection": {
+      "age": {
+        "iso8601duration": "P14Y"
+      }
+    },
+    "histologicalDiagnosis": {
+      "id": "NCIT:C38757",
+      "label": "Negative Finding"
+    },
+    "tumorProgression": {
+      "id": "NCIT:C3677",
+      "label": "Benign Neoplasm"
+    },
+    "tumorGrade": {
+      "id": "NCIT:C28076",
+      "label": "Disease Grade Qualifier"
+    },
+    "diagnosticMarkers": [{
+      "id": "NCIT:C68748",
+      "label": "HER2/Neu Positive"
+    }],
+    "materialSample": {
+      "id": "EFO:0009655",
+      "label": "abnormal sample"
+    }
+  }],
+  "interpretations": [{
+    "id": "comprehensive-phenopacket-id",
+    "progressStatus": "SOLVED",
+    "diagnosis": {
+      "disease": {
+        "id": "OMIM:101600",
+        "label": "PFEIFFER SYNDROME"
+      },
+      "genomicInterpretations": [{
+        "subjectOrBiosampleId": "14 year-old boy",
+        "interpretationStatus": "CAUSATIVE",
+        "variantInterpretation": {
+          "variationDescriptor": {
+            "expressions": [{
+              "syntax": "hgvs",
+              "value": "NM_001848.2:c.877G\u003eA"
+            }],
+            "allelicState": {
+              "id": "GENO:0000135",
+              "label": "heterozygous"
+            }
+          }
+        }
+      }]
+    }
+  }],
+  "diseases": [{
+    "term": {
+      "id": "OMIM:101600",
+      "label": "PFEIFFER SYNDROME"
+    },
+    "onset": {
+      "ontologyClass": {
+        "id": "HP:0003577",
+        "label": "Congenital onset"
+      }
+    }
+  }],
+  "files": [{
+    "uri": "file://data/genomes/P000001C",
+    "individualToFileIdentifiers": {
+      "14 year-old boy": "P000001C"
+    },
+    "fileAttributes": {
+      "genomeAssembly": "GRCh38.p13",
+      "fileFormat": "vcf",
+      "description": "Whole genome sequencing VCF output"
+    }
+  }],
+  "metaData": {
+    "created": "2022-10-03T16:39:04.000123456Z",
+    "createdBy": "Peter R.",
+    "submittedBy": "PhenopacketLab",
+    "resources": [{
+      "id": "hp",
+      "name": "human phenotype ontology",
+      "url": "http://purl.obolibrary.org/obo/hp.owl",
+      "version": "2018-03-08",
+      "namespacePrefix": "HP",
+      "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+    }, {
+      "id": "geno",
+      "name": "Genotype Ontology",
+      "url": "http://purl.obolibrary.org/obo/geno.owl",
+      "version": "19-03-2018",
+      "namespacePrefix": "GENO",
+      "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+    }, {
+      "id": "pubmed",
+      "name": "PubMed",
+      "namespacePrefix": "PMID",
+      "iriPrefix": "https://www.ncbi.nlm.nih.gov/pubmed/"
+    }, {
+      "id": "ncit",
+      "name": "NCI Thesaurus",
+      "url": "http://purl.obolibrary.org/obo/ncit.owl",
+      "version": "20-03-2020",
+      "namespacePrefix": "NCIT",
+      "iriPrefix": "http://purl.obolibrary.org/obo/NCIT_"
+    }],
+    "phenopacketSchemaVersion": "2.0.0",
+    "externalReferences": [{
+      "id": "PMID:30808312",
+      "description": "COL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report."
+    }]
+  }
+}
\ No newline at end of file
diff --git a/python/data/v2/phenopacket.pb b/python/data/v2/phenopacket.pb
new file mode 100644
index 0000000..3acd16a
--- /dev/null
+++ b/python/data/v2/phenopacket.pb
@@ -0,0 +1,71 @@
+
+comprehensive-phenopacket-id^
+14 year-old boyboypatientprobandÀÄd"
+
+P14Y08J
+NCBITaxon:9606homo sapiensñ
&
+
+HP:0001558Decreased fetal movement2
+
+HP:0011461Fetal onsetB©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ß
/
+
+HP:0031910!Abnormal cranial nerve physiology
B©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.ô
#
+
+HP:0011463Macroscopic hematuria*
+
+HP:0031796	Recurrent2
+
+P14YB©

+@
+ECO:00000331author statement supported by traceable referencee
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.P
+
+HP:0001270Motor delay"
+
+HP:0012825Mild2
+
+HP:0011463Childhood onset*º
+biosample-id14 year-old boy" Muscle biopsy of 14 year-old boy*!
+UBERON:0003403skin of forearmJ
+NCBITaxon:9606homo sapiensR
+
+P14YZ
+NCIT:C38757Negative Findingb
+
+NCIT:C3677Benign Neoplasmj&
+NCIT:C28076Disease Grade Qualifier‚
 
+NCIT:C68748HER2/Neu Positiveš

+EFO:0009655abnormal sample2™

+comprehensive-phenopacket-idw
+ 
+OMIM:101600PFEIFFER SYNDROMES
+14 year-old boy"><2
+hgvsNM_001848.2:c.877G>Ar
+GENO:0000135heterozygous:D
+ 
+OMIM:101600PFEIFFER SYNDROME 
+
+HP:0003577Congenital onsetRŸ

+file://data/genomes/P000001C
+14 year-old boyP000001C
+genomeAssembly
+GRCh38.p13
+
+fileFormatvcf1
+description"Whole genome sequencing VCF outputZÁ
+
+¨ ì™ÀÄPeter R.PhenopacketLab"y
+hphuman phenotype ontology%http://purl.obolibrary.org/obo/hp.owl"
+2018-03-08*HP2"http://purl.obolibrary.org/obo/HP_"z
+genoGenotype Ontology'http://purl.obolibrary.org/obo/geno.owl"
+19-03-2018*GENO2$http://purl.obolibrary.org/obo/GENO_"<
+pubmedPubMed*PMID2$https://www.ncbi.nlm.nih.gov/pubmed/"v
+ncit
NCI Thesaurus'http://purl.obolibrary.org/obo/ncit.owl"
+20-03-2020*NCIT2$http://purl.obolibrary.org/obo/NCIT_22.0.0:e
+
PMID:30808312TCOL6A1 mutation leading to Bethlem myopathy with recurrent hematuria: a case report.
\ No newline at end of file
diff --git a/python/tests/conftest.py b/python/tests/conftest.py
index d27777b..99be183 100644
--- a/python/tests/conftest.py
+++ b/python/tests/conftest.py
@@ -3,8 +3,29 @@
 import pytest
 
 
+@pytest.fixture(scope="session")
+def fpath_python_src_dir(
+    fpath_test_dir: str,
+) -> str:
+    return os.path.realpath(
+        os.path.join(
+            fpath_test_dir,
+            os.pardir,
+        )
+    )
+
+
 @pytest.fixture(scope='session')
 def fpath_test_dir() -> str:
     # When running `pytest` from the top-level Python folder (`phenopacket-schema/python`)
     # this path will evaluate to the `tests` folder.
     return os.path.dirname(__file__)
+
+
+@pytest.fixture(scope="session")
+def fpath_test_data_dir(
+    fpath_python_src_dir: str,
+) -> str:
+    # When running `pytest` from the top-level Python folder (`phenopacket-schema/python`)
+    # this path will evaluate to the `data` folder.
+    return os.path.join(fpath_python_src_dir, "data")
diff --git a/python/tests/test_io.py b/python/tests/test_io.py
new file mode 100644
index 0000000..d9d814a
--- /dev/null
+++ b/python/tests/test_io.py
@@ -0,0 +1,120 @@
+import os
+
+import pytest
+
+
+from google.protobuf.json_format import Parse
+
+
+class TestV1IO:
+    @pytest.fixture(scope="class")
+    def fpath_v1_data(
+        self,
+        fpath_test_data_dir: str,
+    ) -> str:
+        return os.path.join(
+            fpath_test_data_dir,
+            "v1",
+        )
+
+    def test_phenopacket(
+        self,
+        fpath_v1_data: str,
+    ):
+        from phenopackets.schema.v1.phenopackets_pb2 import Phenopacket
+
+        phenopacket_pb = Phenopacket()
+        with open(os.path.join(fpath_v1_data, "phenopacket.pb"), "rb") as fh:
+            phenopacket_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v1_data, "phenopacket.json"), "rb") as fh:
+            phenopacket_json = Parse(fh.read(), message=Phenopacket())
+
+        assert phenopacket_pb == phenopacket_json
+
+    def test_family(
+        self,
+        fpath_v1_data: str,
+    ):
+        from phenopackets.schema.v1.phenopackets_pb2 import Family
+
+        family_pb = Family()
+        with open(os.path.join(fpath_v1_data, "family.pb"), "rb") as fh:
+            family_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v1_data, "family.json"), "rb") as fh:
+            family_json = Parse(fh.read(), message=Family())
+
+        assert family_pb == family_json
+
+    def test_cohort(
+        self,
+        fpath_v1_data: str,
+    ):
+        from phenopackets.schema.v1.phenopackets_pb2 import Cohort
+
+        cohort_pb = Cohort()
+        with open(os.path.join(fpath_v1_data, "cohort.pb"), "rb") as fh:
+            cohort_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v1_data, "cohort.json"), "rb") as fh:
+            cohort_json = Parse(fh.read(), message=Cohort())
+
+        assert cohort_pb == cohort_json
+
+
+class TestV2IO:
+    @pytest.fixture(scope="class")
+    def fpath_v2_data(
+        self,
+        fpath_test_data_dir: str,
+    ) -> str:
+        return os.path.join(
+            fpath_test_data_dir,
+            "v2",
+        )
+
+    def test_phenopacket(
+        self,
+        fpath_v2_data: str,
+    ):
+        from phenopackets.schema.v2.phenopackets_pb2 import Phenopacket
+
+        phenopacket_pb = Phenopacket()
+        with open(os.path.join(fpath_v2_data, "phenopacket.pb"), "rb") as fh:
+            phenopacket_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v2_data, "phenopacket.json"), "rb") as fh:
+            phenopacket_json = Parse(fh.read(), message=Phenopacket())
+
+        assert phenopacket_pb == phenopacket_json
+
+    def test_family(
+        self,
+        fpath_v2_data: str,
+    ):
+        from phenopackets.schema.v2.phenopackets_pb2 import Family
+
+        family_pb = Family()
+        with open(os.path.join(fpath_v2_data, "family.pb"), "rb") as fh:
+            family_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v2_data, "family.json"), "rb") as fh:
+            family_json = Parse(fh.read(), message=Family())
+
+        assert family_pb == family_json
+
+    def test_cohort(
+        self,
+        fpath_v2_data: str,
+    ):
+        from phenopackets.schema.v2.phenopackets_pb2 import Cohort
+
+        cohort_pb = Cohort()
+        with open(os.path.join(fpath_v2_data, "cohort.pb"), "rb") as fh:
+            cohort_pb.ParseFromString(fh.read())
+
+        with open(os.path.join(fpath_v2_data, "cohort.json"), "rb") as fh:
+            cohort_json = Parse(fh.read(), message=Cohort())
+
+        assert cohort_pb == cohort_json

From b4ff6779255f075d46bfa8315d984e163f6c282f Mon Sep 17 00:00:00 2001
From: Daniel Danis <daniel.gordon.danis@protonmail.com>
Date: Mon, 13 Jan 2025 23:35:04 +0100
Subject: [PATCH 2/3] Allow using protobuf `<=5.2.9` in Python.

---
 python/pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/pyproject.toml b/python/pyproject.toml
index f3cab23..6825873 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -33,7 +33,7 @@ keywords = [
 ]
 
 dependencies = [
-    "protobuf>=3.20.2,<4.0.0",
+    "protobuf>=3.20.2,<=5.29.3",  # Last tested Python version
 ]
 
 [project.optional-dependencies]

From 9007275d67e3341f5e343948edc8ceb92f2e0a25 Mon Sep 17 00:00:00 2001
From: Daniel Danis <daniel.gordon.danis@protonmail.com>
Date: Tue, 22 Jul 2025 12:46:12 +0200
Subject: [PATCH 3/3] Allow using protobuf `<7.0.0`.

---
 python/pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/python/pyproject.toml b/python/pyproject.toml
index 6825873..2d93b9e 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -33,7 +33,7 @@ keywords = [
 ]
 
 dependencies = [
-    "protobuf>=3.20.2,<=5.29.3",  # Last tested Python version
+    "protobuf>=3.20.2,<7.0.0",  # Last tested Python version
 ]
 
 [project.optional-dependencies]