Merge pull request #40 from TheJacksonLaboratory/G3-235-create-docume…

…ntation-on-how-to-search-for-genesets-with-a-disease-name-via-the-g-3-api Adding first pass at finding genesets document
TheJacksonLaboratory · May 29, 2024 · e7caf4f · e7caf4f
2 parents 38d5fa2 + 94c821d
commit e7caf4f
Show file tree

Hide file tree

Showing 3 changed files with 320 additions and 1 deletion.
diff --git a/docs/tutorial/finding-genesets.ipynb b/docs/tutorial/finding-genesets.ipynb
@@ -0,0 +1,318 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Dependencies and Set Up",
+   "id": "d6d91fc15ac330d8"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "!pip install geneweaver-client",
+   "id": "d932df03b02fc0e8"
+  },
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2024-05-28T13:24:21.132102Z",
+     "start_time": "2024-05-28T13:24:20.315733Z"
+    }
+   },
+   "source": "from geneweaver.client.auth import login",
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:15:34.037708Z",
+     "start_time": "2024-05-28T14:15:14.743965Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "login()",
+   "id": "6a4553c34d73a6c7",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1. On your computer or mobile device navigate to:  https://geneweaver.auth0.com/activate?user_code=VPPC-FWSQ\n",
+      "2. Enter the following code:  VPPC-FWSQ\n",
+      "Authenticated!\n",
+      "- Id Token: eyJhbGciOi...\n"
+     ]
+    }
+   ],
+   "execution_count": 2
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:18:35.250326Z",
+     "start_time": "2024-05-28T14:18:35.224788Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "from geneweaver.client.auth import get_access_token",
+   "id": "9a222f2e97f34647",
+   "outputs": [],
+   "execution_count": 4
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Finding Cancer Related Genesets",
+   "id": "15f75595e4344685"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:19:16.611744Z",
+     "start_time": "2024-05-28T14:19:16.598106Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "import requests",
+   "id": "5fed1b8b6ec94259",
+   "outputs": [],
+   "execution_count": 6
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:27:23.944721Z",
+     "start_time": "2024-05-28T14:27:22.740834Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "result = requests.get(\n",
+    "    \"https://geneweaver.jax.org/api/genesets\",\n",
+    "    params={\n",
+    "        \"search_text\": \"cancer\",\n",
+    "        \"curation_tier\": \"Tier I\",\n",
+    "        \"limit\": 10\n",
+    "    },\n",
+    "    headers={\"Authorization\": f\"Bearer {get_access_token()}\"}\n",
+    ")\n",
+    "result.ok"
+   ],
+   "id": "868214fa2ab3f9cd",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 56
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:27:24.698625Z",
+     "start_time": "2024-05-28T14:27:24.696627Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "cancer_genesets = result.json()[\"data\"]",
+   "id": "8a0a7ef040973dfe",
+   "outputs": [],
+   "execution_count": 57
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:27:25.889802Z",
+     "start_time": "2024-05-28T14:27:25.887410Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "for i in cancer_genesets:\n",
+    "    print(i[\"name\"])"
+   ],
+   "id": "b40c7fce9c826e32",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MP:0010337 increased chronic lymphocytic leukemia incidence\n",
+      "MSigDB Geneset - MORF_ZNF10\n",
+      "MSigDB Geneset - KRAS.LUNG.BREAST_UP.V1_UP\n",
+      "MSigDB Geneset - MORF_HDAC2\n",
+      "MSigDB Geneset - GCM_PTPRD\n",
+      "GWAS Catalog Data for breast carcinoma in 10,052 European ancestry cases, 12,575 European ancestry controls\n",
+      "MSigDB Geneset - MORF_TFDP2\n",
+      "GWAS Catalog Data for response to platinum based chemotherapy, non-small cell lung carcinoma in 327 European ancestry individuals\n",
+      "MSigDB Geneset - MORF_PML\n",
+      "MSigDB Geneset - GCM_ERCC4\n"
+     ]
+    }
+   ],
+   "execution_count": 58
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Finding GWAS Cancer Related Genesets",
+   "id": "1c8f32c85d7e2e24"
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:28:38.858820Z",
+     "start_time": "2024-05-28T14:28:37.607796Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "result = requests.get(\n",
+    "    \"https://geneweaver.jax.org/api/genesets\",\n",
+    "    params={\n",
+    "        \"search_text\": \"gwas & cancer\",\n",
+    "        \"curation_tier\": \"Tier I\",\n",
+    "        \"limit\": 10\n",
+    "    },\n",
+    "    headers={\"Authorization\": f\"Bearer {get_access_token()}\"}\n",
+    ")\n",
+    "result.ok"
+   ],
+   "id": "e9ba2ac7c4b68831",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 60
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:28:38.861832Z",
+     "start_time": "2024-05-28T14:28:38.859816Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "gwas_cancer_genesets = result.json()[\"data\"]",
+   "id": "b173bc8938da9893",
+   "outputs": [],
+   "execution_count": 61
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:28:38.864681Z",
+     "start_time": "2024-05-28T14:28:38.862696Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "for i in gwas_cancer_genesets:\n",
+    "    print(i[\"name\"])"
+   ],
+   "id": "f4396390d053338b",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "GWAS Catalog Data for breast carcinoma in 10,052 European ancestry cases, 12,575 European ancestry controls\n",
+      "GWAS Catalog Data for response to platinum based chemotherapy, non-small cell lung carcinoma in 327 European ancestry individuals\n",
+      "GWAS Catalog Data for lung carcinoma in 2,331 Han Chinese ancestry lung cancer cases, 1,006 Han Chinese ancestry non-cardia gastric cancer cases, 2,031 Han Chinese ancestry esophageal squamous-cell carcinoma cases, 4,006 Han Chinese ancestry controls\n",
+      "GWAS Catalog Data for lung carcinoma, squamous cell carcinoma, gastric carcinoma in 2,331 Han Chinese ancestry lung cancer cases, 1,006 Han Chinese ancestry non-cardia gastric cancer cases, 2,031 Han Chinese ancestry esophageal squamous-cell carcinoma cases, 4,006 Han Chinese ancestry controls\n",
+      "GWAS Catalog Data for estrogen-receptor negative breast cancer in 4,939 European ancestry cases, 14,352 European ancestry controls\n",
+      "GWAS Catalog Data for breast carcinoma in 899 European ancestry cases, 804 European ancestry controls\n",
+      "GWAS Catalog Data for breast carcinoma in 1,426 European ancestry cases, 1,301 European ancestry controls\n",
+      "GWAS Catalog Data for ovarian carcinoma in 1,817 European ancestry cases, 2,353 European ancestry controls\n",
+      "GWAS Catalog Data for breast carcinoma in 1,367 Sardinian cases, 1,658 Sardinian controls\n",
+      "GWAS Catalog Data for endometrial carcinoma in 4,907 European ancestry cases, 11,945 European ancestry controls\n"
+     ]
+    }
+   ],
+   "execution_count": 62
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-05-28T14:29:22.658230Z",
+     "start_time": "2024-05-28T14:29:22.655886Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "for i in gwas_cancer_genesets:\n",
+    "    print(f\"GS{i['id']} has {i['count']} genes\")"
+   ],
+   "id": "30e29e4ca07bfa24",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "GS267835 has 98 genes\n",
+      "GS270261 has 1 genes\n",
+      "GS268187 has 3 genes\n",
+      "GS268186 has 3 genes\n",
+      "GS271027 has 30 genes\n",
+      "GS269914 has 1 genes\n",
+      "GS270401 has 7 genes\n",
+      "GS270122 has 2 genes\n",
+      "GS267760 has 2 genes\n",
+      "GS268492 has 8 genes\n"
+     ]
+    }
+   ],
+   "execution_count": 66
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "eeb496d3d034ca3a"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -100,6 +100,7 @@ nav:
       - tutorial/index.md
       - Client Login: tutorial/geneweaver_client_login.ipynb
       - Map Gene IDs: tutorial/map-gene-ids.ipynb
+      - Finding Genesets: tutorial/finding-genesets.ipynb
       - NCI-60 Example Workflow: tutorial/nci_60_example_01.ipynb
 #      - Geneweaver Command Line Interface:
 #          - tutorial/geneweaver_command_line.md

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "geneweaver-docs"
-version = "0.0.1a0"
+version = "0.0.2a0"
 description = ""
 authors = ["Alexander Berger <alexander.berger@jax.org>"]
 readme = "README.md"