SPATA22

monarch-initiative · Dec 26, 2024 · c174eeb · c174eeb
1 parent b89dcdf
commit c174eeb
Show file tree

Hide file tree

Showing 4 changed files with 501 additions and 0 deletions.
diff --git a/notebooks/SPATA22/SPATA22_POF25_individuals.ipynb b/notebooks/SPATA22/SPATA22_POF25_individuals.ipynb
@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# PSATA22\n",
+    "[premature ovarian failure-25 (POF25)](https://omim.org/entry/621002) is caused by homozygous or compound heterozygous mutation in the SPATA22 gene."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using pyphetools version 0.9.115\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyphetools.creation import TemplateImporter, Moi\n",
+    "from pyphetools.visualization import IndividualTable, QcVisualizer\n",
+    "from IPython.display import display, HTML\n",
+    "import pyphetools\n",
+    "print(f\"Using pyphetools version {pyphetools.__version__}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "HPO version 2024-12-12\n",
+      "Created encoders for 23 fields\n",
+      "Importing OMIM:621002, Premature ovarian failure 25, HGNC:30705, SPATA22,  NM_001170698.2\n",
+      "We output 2 GA4GH phenopackets to the directory phenopackets\n"
+     ]
+    }
+   ],
+   "source": [
+    "template = \"input/SPATA22_POF25_individuals.xlsx\"\n",
+    "created_by = \"0000-0002-0736-9199\"\n",
+    "timporter = TemplateImporter(template=template,  created_by=created_by)\n",
+    "individual_list, cvalidator = timporter.import_phenopackets_from_template()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h2>Cohort validation</h2>\n",
+       "<p>No errors found for the cohort with 2 individuals</p>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "qc = QcVisualizer(cohort_validator=cvalidator)\n",
+    "display(HTML(qc.to_summary_html()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table style=\"border: 2px solid black; align: \"left\">\n",
+       "<caption>2 phenopackets - PMID:35285020 (n=2)</caption>\n",
+       "<tr><th style=\"text-align: left;font-weight: bold;\">Individual</th><th style=\"text-align: left;font-weight: bold;\">Disease</th><th style=\"text-align: left;font-weight: bold;\">Genotype</th><th style=\"text-align: left;font-weight: bold;\">Phenotypic features</th></tr>\n",
+       "<tr><td style=\"text-align: left;\">IV-2 IV-1 (FEMALE)</td><td style=\"text-align: left;\">Premature ovarian failure 25 (OMIM:621002)</td><td style=\"text-align: left;\">NM_001170698.2:c.400C>T (homozygous)</td><td style=\"text-align: left;\">Premature ovarian insufficiency (HP:0008209): onset ; Elevated circulating follicle stimulating hormone level (HP:0008232): onset ; Decreased circulating antimullerian hormone circulation (HP:0031103): onset ; Female infertility (HP:0008222): onset ; excluded: Autoimmunity (HP:0002960): onset <br/><b>TimeElement(element=Age(iso8601duration=P14Y))</b>: Irregular menstruation (HP:0000858): onset age {\n",
+       "  iso8601duration: \"P14Y\"\n",
+       "}\n",
+       "</td></tr>\n",
+       "<tr><td style=\"text-align: left;\">sister IV-2 (FEMALE)</td><td style=\"text-align: left;\">Premature ovarian failure 25 (OMIM:621002)</td><td style=\"text-align: left;\">NM_001170698.2:c.400C>T (homozygous)</td><td style=\"text-align: left;\">Premature ovarian insufficiency (HP:0008209): onset ; Elevated circulating follicle stimulating hormone level (HP:0008232): onset ; Decreased circulating antimullerian hormone circulation (HP:0031103): onset ; Female infertility (HP:0008222): onset ; excluded: Autoimmunity (HP:0002960): onset <br/><b>TimeElement(element=Age(iso8601duration=P13Y))</b>: Irregular menstruation (HP:0000858): onset age {\n",
+       "  iso8601duration: \"P13Y\"\n",
+       "}\n",
+       "</td></tr>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "table = IndividualTable(cvalidator.get_error_free_individual_list())\n",
+    "display(HTML(table.to_html()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[pyphetools] Ingested 5 GA4GH phenopackets.\n",
+      "[INFO] Extracted 2 from 5 phenopackets with OMIM:621002\n",
+      "\n",
+      "\tPremature ovarian failure 25 (OMIM:621002): n=2\n",
+      "We found a total of 6 unique HPO terms\n",
+      "Extracted disease: Premature ovarian failure 25 (OMIM:621002)\n",
+      "Wrote HPOA disease file to OMIM-621002.tab\n"
+     ]
+    }
+   ],
+   "source": [
+    "pmid = \"PMID:35285020\"\n",
+    "df = timporter.create_hpoa_from_phenopackets(pmid=pmid, mode_of_inheritance=Moi.AR, target=\"OMIM:621002\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ps24venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/notebooks/SPATA22/input/SPATA22_POF25_individuals.xlsx b/notebooks/SPATA22/input/SPATA22_POF25_individuals.xlsx
diff --git a/notebooks/SPATA22/phenopackets/PMID_35285020_IV-2IV-1.json b/notebooks/SPATA22/phenopackets/PMID_35285020_IV-2IV-1.json
@@ -0,0 +1,171 @@
+{
+  "id": "PMID_35285020_IV_2_IV_1",
+  "subject": {
+    "id": "IV-2 IV-1",
+    "vitalStatus": {
+      "status": "ALIVE"
+    },
+    "sex": "FEMALE"
+  },
+  "phenotypicFeatures": [
+    {
+      "type": {
+        "id": "HP:0000858",
+        "label": "Irregular menstruation"
+      },
+      "onset": {
+        "age": {
+          "iso8601duration": "P14Y"
+        }
+      }
+    },
+    {
+      "type": {
+        "id": "HP:0008209",
+        "label": "Premature ovarian insufficiency"
+      }
+    },
+    {
+      "type": {
+        "id": "HP:0008232",
+        "label": "Elevated circulating follicle stimulating hormone level"
+      }
+    },
+    {
+      "type": {
+        "id": "HP:0031103",
+        "label": "Decreased circulating antimullerian hormone circulation"
+      }
+    },
+    {
+      "type": {
+        "id": "HP:0008222",
+        "label": "Female infertility"
+      }
+    },
+    {
+      "type": {
+        "id": "HP:0002960",
+        "label": "Autoimmunity"
+      },
+      "excluded": true
+    }
+  ],
+  "interpretations": [
+    {
+      "id": "IV-2 IV-1",
+      "progressStatus": "SOLVED",
+      "diagnosis": {
+        "disease": {
+          "id": "OMIM:621002",
+          "label": "Premature ovarian failure 25"
+        },
+        "genomicInterpretations": [
+          {
+            "subjectOrBiosampleId": "IV-2 IV-1",
+            "interpretationStatus": "CAUSATIVE",
+            "variantInterpretation": {
+              "variationDescriptor": {
+                "id": "var_hNMlDzxxGVdPAjMNRZWVvBkNx",
+                "geneContext": {
+                  "valueId": "HGNC:30705",
+                  "symbol": "SPATA22"
+                },
+                "expressions": [
+                  {
+                    "syntax": "hgvs.c",
+                    "value": "NM_001170698.2:c.400C>T"
+                  },
+                  {
+                    "syntax": "hgvs.g",
+                    "value": "NC_000017.11:g.3449079G>A"
+                  }
+                ],
+                "vcfRecord": {
+                  "genomeAssembly": "hg38",
+                  "chrom": "chr17",
+                  "pos": "3449079",
+                  "ref": "G",
+                  "alt": "A"
+                },
+                "moleculeContext": "genomic",
+                "allelicState": {
+                  "id": "GENO:0000136",
+                  "label": "homozygous"
+                }
+              }
+            }
+          }
+        ]
+      }
+    }
+  ],
+  "diseases": [
+    {
+      "term": {
+        "id": "OMIM:621002",
+        "label": "Premature ovarian failure 25"
+      },
+      "onset": {
+        "ontologyClass": {
+          "id": "HP:0011462",
+          "label": "Young adult onset"
+        }
+      }
+    }
+  ],
+  "metaData": {
+    "created": "2024-12-26T08:44:55.618757963Z",
+    "createdBy": "ORCID:0000-0002-0736-9199",
+    "resources": [
+      {
+        "id": "geno",
+        "name": "Genotype Ontology",
+        "url": "http://purl.obolibrary.org/obo/geno.owl",
+        "version": "2022-03-05",
+        "namespacePrefix": "GENO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/GENO_"
+      },
+      {
+        "id": "hgnc",
+        "name": "HUGO Gene Nomenclature Committee",
+        "url": "https://www.genenames.org",
+        "version": "06/01/23",
+        "namespacePrefix": "HGNC",
+        "iriPrefix": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/"
+      },
+      {
+        "id": "omim",
+        "name": "An Online Catalog of Human Genes and Genetic Disorders",
+        "url": "https://www.omim.org",
+        "version": "January 4, 2023",
+        "namespacePrefix": "OMIM",
+        "iriPrefix": "https://www.omim.org/entry/"
+      },
+      {
+        "id": "so",
+        "name": "Sequence types and features ontology",
+        "url": "http://purl.obolibrary.org/obo/so.obo",
+        "version": "2021-11-22",
+        "namespacePrefix": "SO",
+        "iriPrefix": "http://purl.obolibrary.org/obo/SO_"
+      },
+      {
+        "id": "hp",
+        "name": "human phenotype ontology",
+        "url": "http://purl.obolibrary.org/obo/hp.owl",
+        "version": "2024-12-12",
+        "namespacePrefix": "HP",
+        "iriPrefix": "http://purl.obolibrary.org/obo/HP_"
+      }
+    ],
+    "phenopacketSchemaVersion": "2.0",
+    "externalReferences": [
+      {
+        "id": "PMID:35285020",
+        "reference": "https://pubmed.ncbi.nlm.nih.gov/35285020",
+        "description": "Bi-allelic SPATA22 variants cause premature ovarian insufficiency and nonobstructive azoospermia due to meiotic arrest"
+      }
+    ]
+  }
+}