Skip to content

Commit

Permalink
HROB
Browse files Browse the repository at this point in the history
  • Loading branch information
@pnrobinson
pnrobinson committed Jan 6, 2025
1 parent 6b3899e commit 7335935
Show file tree
Hide file tree
Showing 5 changed files with 911 additions and 0 deletions.
336 changes: 336 additions & 0 deletions notebooks/HROB/HROB_ODG11_individuals.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,336 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# HROB\n",
"[ovarian dysgenesis-11 (ODG11)](https://omim.org/entry/620897) is caused by homozygous or compound heterozygous mutation in the HROB 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": 2,
"metadata": {},
"outputs": [],
"source": [
"template = \"input/HROB_ODG11_individuals.xlsx\"\n",
"created_by = \"0000-0002-0736-9199\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"HPO version 2024-12-12\n",
"Created encoders for 25 fields\n",
"Importing OMIM:620897, Ovarian dysgenesis 11, HGNC:28460, HROB, NM_001171251.3\n",
"[INFO] encoding variant \"c.421del\"\n",
"https://rest.variantvalidator.org/VariantValidator/variantvalidator/hg38/NM_001171251.3%3Ac.421del/NM_001171251.3?content-type=application%2Fjson\n",
"[INFO] encoding variant \"c.1351C>T\"\n",
"https://rest.variantvalidator.org/VariantValidator/variantvalidator/hg38/NM_001171251.3%3Ac.1351C>T/NM_001171251.3?content-type=application%2Fjson\n",
"[INFO] encoding variant \"c.718C>T\"\n",
"https://rest.variantvalidator.org/VariantValidator/variantvalidator/hg38/NM_001171251.3%3Ac.718C>T/NM_001171251.3?content-type=application%2Fjson\n",
"We output 3 GA4GH phenopackets to the directory phenopackets\n"
]
}
],
"source": [
"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>Errors found with 2 of 3 phenopackets.</p>\n",
"<table style=\"border: 2px solid black; align: \"left\">\n",
"<caption>Error counts</caption>\n",
"<tr><th style=\"text-align: left;font-weight: bold;\">Level</th><th style=\"text-align: left;font-weight: bold;\">Error category</th><th style=\"text-align: left;font-weight: bold;\">Count</th></tr>\n",
"<tr><td style=\"text-align: left;\">WARNING</td><td style=\"text-align: left;\">REDUNDANT</td><td style=\"text-align: left;\">2</td></tr>\n",
"</table>\n",
"<p>A total of 2 issues were fixed and no individual was removed from the cohort.</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>3 phenopackets - PMID:34707299 (n=1); PMID:38105698 (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;\">nan (FEMALE; P33Y)</td><td style=\"text-align: left;\">Ovarian dysgenesis 11 (OMIM:620897)</td><td style=\"text-align: left;\">NM_001171251.3:c.421del (homozygous)</td><td style=\"text-align: left;\">Delayed puberty (HP:0000823): onset ; Primary amenorrhea (HP:0000786): onset ; Elevated circulating follicle stimulating hormone level (HP:0008232): onset ; Decreased serum estradiol (HP:0008214): onset ; excluded: Delayed menarche (HP:0012569): onset </td></tr>\n",
"<tr><td style=\"text-align: left;\">proband (FEMALE; P13Y6M)</td><td style=\"text-align: left;\">Ovarian dysgenesis 11 (OMIM:620897)</td><td style=\"text-align: left;\"><ul> <li>NM_001171251.3:c.718C>T (heterozygous)</li> <li>NM_001171251.3:c.1351C>T (heterozygous)</li> </ul></td><td style=\"text-align: left;\">Delayed menarche (HP:0012569): onset ; Elevated circulating luteinizing hormone level (HP:0011969): onset ; Elevated circulating follicle stimulating hormone level (HP:0008232): onset ; Decreased circulating antimullerian hormone circulation (HP:0031103): onset ; Aplasia of the ovary (HP:0010463): onset ; excluded: Primary amenorrhea (HP:0000786): onset </td></tr>\n",
"<tr><td style=\"text-align: left;\">nan (FEMALE; P11Y6M)</td><td style=\"text-align: left;\">Ovarian dysgenesis 11 (OMIM:620897)</td><td style=\"text-align: left;\"><ul> <li>NM_001171251.3:c.718C>T (heterozygous)</li> <li>NM_001171251.3:c.1351C>T (heterozygous)</li> </ul></td><td style=\"text-align: left;\">Delayed menarche (HP:0012569): onset ; Elevated circulating luteinizing hormone level (HP:0011969): onset ; Elevated circulating follicle stimulating hormone level (HP:0008232): onset ; Decreased circulating antimullerian hormone circulation (HP:0031103): onset ; Aplasia of the ovary (HP:0010463): onset ; excluded: Primary amenorrhea (HP:0000786): onset </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 3 GA4GH phenopackets.\n",
"[INFO] Extracted 3 from 3 phenopackets with OMIM:620897\n",
"\n",
"\tOvarian dysgenesis 11 (OMIM:620897): n=3\n",
"We found a total of 8 unique HPO terms\n",
"Extracted disease: Ovarian dysgenesis 11 (OMIM:620897)\n",
"Wrote HPOA disease file to OMIM-620897.tab\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>#diseaseID</th>\n",
" <th>diseaseName</th>\n",
" <th>phenotypeID</th>\n",
" <th>phenotypeName</th>\n",
" <th>onsetID</th>\n",
" <th>onsetName</th>\n",
" <th>frequency</th>\n",
" <th>sex</th>\n",
" <th>negation</th>\n",
" <th>modifier</th>\n",
" <th>description</th>\n",
" <th>publication</th>\n",
" <th>evidence</th>\n",
" <th>biocuration</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OMIM:620897</td>\n",
" <td>Ovarian dysgenesis 11</td>\n",
" <td>HP:0000823</td>\n",
" <td>Delayed puberty</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>1/1</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PMID:34707299</td>\n",
" <td>PCS</td>\n",
" <td>ORCID:0000-0002-0736-9199[2025-01-06]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OMIM:620897</td>\n",
" <td>Ovarian dysgenesis 11</td>\n",
" <td>HP:0000786</td>\n",
" <td>Primary amenorrhea</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>1/1</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PMID:34707299</td>\n",
" <td>PCS</td>\n",
" <td>ORCID:0000-0002-0736-9199[2025-01-06]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OMIM:620897</td>\n",
" <td>Ovarian dysgenesis 11</td>\n",
" <td>HP:0008232</td>\n",
" <td>Elevated circulating follicle stimulating horm...</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>1/1</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PMID:34707299</td>\n",
" <td>PCS</td>\n",
" <td>ORCID:0000-0002-0736-9199[2025-01-06]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>OMIM:620897</td>\n",
" <td>Ovarian dysgenesis 11</td>\n",
" <td>HP:0008214</td>\n",
" <td>Decreased serum estradiol</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>1/1</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PMID:34707299</td>\n",
" <td>PCS</td>\n",
" <td>ORCID:0000-0002-0736-9199[2025-01-06]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>OMIM:620897</td>\n",
" <td>Ovarian dysgenesis 11</td>\n",
" <td>HP:0012569</td>\n",
" <td>Delayed menarche</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>0/1</td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td></td>\n",
" <td>PMID:34707299</td>\n",
" <td>PCS</td>\n",
" <td>ORCID:0000-0002-0736-9199[2025-01-06]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" #diseaseID diseaseName phenotypeID \\\n",
"0 OMIM:620897 Ovarian dysgenesis 11 HP:0000823 \n",
"1 OMIM:620897 Ovarian dysgenesis 11 HP:0000786 \n",
"2 OMIM:620897 Ovarian dysgenesis 11 HP:0008232 \n",
"3 OMIM:620897 Ovarian dysgenesis 11 HP:0008214 \n",
"4 OMIM:620897 Ovarian dysgenesis 11 HP:0012569 \n",
"\n",
" phenotypeName onsetID onsetName \\\n",
"0 Delayed puberty \n",
"1 Primary amenorrhea \n",
"2 Elevated circulating follicle stimulating horm... \n",
"3 Decreased serum estradiol \n",
"4 Delayed menarche \n",
"\n",
" frequency sex negation modifier description publication evidence \\\n",
"0 1/1 PMID:34707299 PCS \n",
"1 1/1 PMID:34707299 PCS \n",
"2 1/1 PMID:34707299 PCS \n",
"3 1/1 PMID:34707299 PCS \n",
"4 0/1 PMID:34707299 PCS \n",
"\n",
" biocuration \n",
"0 ORCID:0000-0002-0736-9199[2025-01-06] \n",
"1 ORCID:0000-0002-0736-9199[2025-01-06] \n",
"2 ORCID:0000-0002-0736-9199[2025-01-06] \n",
"3 ORCID:0000-0002-0736-9199[2025-01-06] \n",
"4 ORCID:0000-0002-0736-9199[2025-01-06] "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pmid = \"PMID:34707299\"\n",
"df = timporter.create_hpoa_from_phenopackets(pmid=pmid, mode_of_inheritance=Moi.AR, target=\"OMIM:620897\")\n",
"df.head()"
]
}
],
"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": "3.12.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Binary file added notebooks/HROB/input/HROB_ODG11_individuals.xlsx
View file
Binary file not shown.
Loading

0 comments on commit 7335935

Please sign in to comment.