File size: 5,966 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"# import json\n",
"# import os\n",
"\n",
"# # Read in the organ to conditions mapping JSON file\n",
"# with open(\"clin-oracle-tahoe-hack-2025/data/organ_to_conditions_mapping.json\", \"r\") as f:\n",
"# organ_to_conditions = json.load(f)\n",
" \n",
"# # Display basic information about the mapping\n",
"# print(f\"Loaded organ to conditions mapping with {len(organ_to_conditions)} organs\")\n",
"# print(f\"Sample organ: {list(organ_to_conditions.keys())[0]}\")\n",
"# print(f\"Sample conditions: {organ_to_conditions[list(organ_to_conditions.keys())[0]][:3]}...\")\n"
]
},
{
"cell_type": "code",
"execution_count": 55,
"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\"]))"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"/home/ubuntu/tahoe/clin-oracle-tahoe-hack-2025/indication_to_organ_mapping_confident.tsv\", sep='\\t')"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [],
"source": [
"indic = pd.read_csv(\"genetic_support/data/indic.tsv\", sep='\\t')\n",
"assoc = pd.read_csv(\"genetic_support/data/assoc.tsv.gz\", sep='\\t')"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": [
"assoc = assoc.merge(df, left_on=\"mesh_term\", right_on=\"indication_mesh_term\")"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"189"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(target_to_drug)"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [],
"source": [
"assoc[\"drug\"] = assoc[\"gene\"].map(target_to_drug)\n",
"assoc[\"drug_organ\"] = assoc[\"drug\"] + \"_\" + assoc[\"organ\"]"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [],
"source": [
"assoc = assoc.loc[assoc[\"drug_organ\"].notna()]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"assoc[[\"drug_organ\",]]"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"arow 3885\n",
"gene ABL1\n",
"mesh_id D014012\n",
"source OTG\n",
"original_trait Tinnitus / tiniitis | non-cancer illness code,...\n",
"original_link https://genetics.opentargets.org/study/NEALE2_...\n",
"extra_info NaN\n",
"l2g_rank 4.0\n",
"l2g_share 0.12\n",
"pval 0.0\n",
"year 2018.0\n",
"beta NaN\n",
"odds_ratio 4.072184\n",
"pic_qtl_pval NaN\n",
"pic_h4 NaN\n",
"af_gnomad_nfe 0.02489\n",
"mesh_term Tinnitus\n",
"indication_mesh_term Tinnitus\n",
"organ CNS/Brain\n",
"drug Flumatinib (mesylate)\n",
"drug_organ Flumatinib (mesylate)_CNS/Brain\n",
"Name: 234, dtype: object"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"assoc.iloc[0]"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
"assoc[\"is_associated_with_indication\"] = 1\n",
"assoc[[\"drug_organ\",\"is_associated_with_indication\"]].to_csv(\"/home/ubuntu/tahoe/clin-oracle-tahoe-hack-2025/data_for_classifier/assoc_drug_organ_label.tsv\", sep='\\t', index=False)"
]
},
{
"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
}
|