add gwas notebook

notebooks/gwas.ipynb

@@ -0,0 +1,100 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "from pathlib import Path\n",
+    "from py2neo import Graph\n",
+    "from pandas import DataFrame\n",
+    "graph = Graph(\"bolt://localhost:7687\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## For GWAS SNPs, what are the associated phenotypes and which IMPC alleles share these phenotypes?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# SNP -> Disease -> Phenotype -> IMPC association\n",
+    "\n",
+    "phenotype_matches_via_disease = DataFrame(graph.run(\"\"\"\n",
+    "MATCH (snp:`gwas:SNP`)-[:`gwas:associated_with`]->(disease:GraphNode)\n",
+    "    -[:(`biolink:has_phenotype`|`ro:causally_related_to`|`ro:has_characteristic`)]->(phenotype:GraphNode)<-[:`biolink:has_phenotype`]-(mouse_assoc:`impc:GenePhenotypeAssociation`)-[:`impc:mouseAlleleId`]->(mouse_allele:`impc:Allele`)\n",
+    "RETURN snp.id[0] as snp_id, disease.`grebi:name`[0] as disease, phenotype.`grebi:name`[0] as phenotype, mouse_assoc.`grebi:name`[0] as mouse_gene, mouse_allele.`impc:symbol`[0] as mouse_allele\n",
+    "\"\"\").data())\n",
+    "\n",
+    "phenotype_matches_via_disease.to_csv(\"gwas_disease_phenotype_impc.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "# SNP -> Phenotype -> IMPC association\n",
+    "\n",
+    "direct_phenotype_matches = DataFrame(graph.run(\"\"\"\n",
+    "MATCH (snp:`gwas:SNP`)-[:`gwas:associated_with`]->(trait:GraphNode)\n",
+    "    <-[:`biolink:has_phenotype`]-(mouse_assoc:`impc:GenePhenotypeAssociation`)-[:`impc:mouseAlleleId`]->(mouse_allele:`impc:Allele`)\n",
+    "RETURN snp.id[0] as snp_id, trait.`grebi:name`[0] as trait, mouse_assoc.`grebi:name`[0] as mouse_gene, mouse_allele.`impc:symbol`[0] as mouse_allele\n",
+    "\"\"\").data())\n",
+    "\n",
+    "direct_phenotype_matches.to_csv(\"gwas_phenotype_impc.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# SNP -> Disease -> Phenotype -> IMPC association\n",
+    "\n",
+    "phenotype_matches_via_disease = DataFrame(graph.run(\"\"\"\n",
+    "MATCH (snp:`gwas:SNP`)-[:`gwas:associated_with`]->(disease:GraphNode)\n",
+    "    -[:(`biolink:has_phenotype`|`ro:causally_related_to`|`ro:has_characteristic`)]->(phenotype:GraphNode)<-[:`biolink:has_phenotype`]-(mouse_assoc:`impc:GenePhenotypeAssociation`)-[:`impc:mouseAlleleId`]->(mouse_allele:`impc:Allele`)\n",
+    "RETURN snp.id[0] as snp_id, disease.`grebi:name`[0] as disease, phenotype.`grebi:name`[0] as phenotype, mouse_assoc.`grebi:name`[0] as mouse_gene, mouse_allele.`impc:symbol`[0] as mouse_allele\n",
+    "\"\"\").data())\n",
+    "\n",
+    "phenotype_matches_via_disease.to_csv(\"gwas_disease_phenotype_impc.csv\", index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}