File size: 2,969 Bytes
032c0ea |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ubuntu/miniconda3/envs/rapids_singlecell/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from datasets import load_dataset\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"drug_metadata = pd.DataFrame(load_dataset(\"tahoebio/Tahoe-100M\",\"drug_metadata\", split=\"train\"))\n",
"drug_metadata = drug_metadata.loc[drug_metadata[\"targets\"].notna()]\n",
"target_to_drug = dict(zip(drug_metadata[\"targets\"], drug_metadata[\"drug\"]))\n",
"cell_metadata = pd.DataFrame(load_dataset(\"tahoebio/Tahoe-100M\",\"cell_line_metadata\", split=\"train\"))\n",
"depmap = pd.read_csv(\"../CRISPRGeneDependency.csv\", index_col=0)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"depmap_to_tahoe = dict(zip(cell_metadata[\"Cell_ID_DepMap\"], cell_metadata[\"Cell_ID_Cellosaur\"]))\n",
"depmap.index = depmap.index.map(depmap_to_tahoe)\n",
"depmap = depmap.loc[depmap.index.notna()]\n",
"depmap.columns = depmap.columns.map(lambda x: x.split(\" \")[0])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"depmap = depmap.reset_index().melt(id_vars='index')\n",
"depmap[\"drug\"] = depmap[\"variable\"].map(target_to_drug)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"depmap = depmap.dropna(subset=[\"drug\"])\n",
"depmap[\"drug_cellline\"] = depmap[\"drug\"] + \"_\" + depmap[\"index\"]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"depmap.index = depmap[\"drug_cellline\"]\n",
"depmap[\"depmap_dependency_score\"] = depmap[\"value\"]\n",
"depmap[[\"depmap_dependency_score\"]].to_csv(\"data_for_classifier/depmap_dependency_scores.tsv\", index=True, sep='\\t')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.12.10"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|