bump up to 0.0.10

rsinghlab · Dec 28, 2023 · 0cd95da · 0cd95da
1 parent 2e4f506
commit 0cd95da
Show file tree

Hide file tree

Showing 22 changed files with 1,178 additions and 503 deletions.
diff --git a/clocks/notebooks/hrsinchphenoage.ipynb b/clocks/notebooks/hrsinchphenoage.ipynb
@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ae756043-21a3-46e9-9fd8-1e5449eba9cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import pandas as pd\n",
+    "import pyaging as pya\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "46c6fc26-9a6b-4027-bd01-601b70eb401a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.system(\"git clone https://github.com/MorganLevineLab/methylCIPHER.git\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ef41c1be-5a8b-463f-914c-3f74fcc04465",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('methylCIPHER/data-raw/HRSInChPhenoAge_CpG.csv')\n",
+    "\n",
+    "df['feature'] = df['CpG']\n",
+    "df['coefficient'] = df['Weight']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "aeadf8d3-e31b-4e44-9928-39cb3986deb0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features = df['feature'].tolist()\n",
+    "\n",
+    "weights = torch.tensor(df['coefficient'].tolist()).unsqueeze(0)\n",
+    "intercept = torch.tensor([52.8334080])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "1b43e476-72ef-43fd-9871-f41d95c8b269",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LinearModel(\n",
+       "  (linear): Linear(in_features=959, out_features=1, bias=True)\n",
+       ")"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = pya.models.LinearModel(len(features))\n",
+    "\n",
+    "model.linear.weight.data = weights\n",
+    "model.linear.bias.data = intercept\n",
+    "\n",
+    "model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "4f437c4e-313a-401a-8e30-6e68ad397fc4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "weights_dict = {\n",
+    "    'preprocessing': None, \n",
+    "    'preprocessing_helper': None,\n",
+    "    'postprocessing': None,\n",
+    "    'postprocessing_helper': None,\n",
+    "    'features': features,\n",
+    "    'weight_dict': model.state_dict(),\n",
+    "}\n",
+    "\n",
+    "metadata_dict = {\n",
+    "    'species': 'Homo sapiens',\n",
+    "    'data_type': 'methylation',\n",
+    "    'year': 2022,\n",
+    "    'implementation_approved_by_author(s)': '⌛',\n",
+    "    'preprocessing': weights_dict['preprocessing'], \n",
+    "    'postprocessing': weights_dict['postprocessing'], \n",
+    "    'citation': \"Higgins-Chen, Albert T., et al. \\\"A computational solution for bolstering reliability of epigenetic clocks: Implications for clinical trials and longitudinal tracking.\\\" Nature aging 2.7 (2022): 644-661.\",\n",
+    "    'doi': \"https://doi.org/10.1038/s43587-022-00248-2\",\n",
+    "    \"notes\": None,\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "34136f3c-92b8-4641-a103-381d3a7dd857",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.save(weights_dict, '../weights/hrsinchphenoage.pt')\n",
+    "torch.save(metadata_dict, '../metadata/hrsinchphenoage.pt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "d7a8c672-d9f7-487e-af1d-addc55155534",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.system(\"rm -r methylCIPHER\")"
+   ]
+  }
+ ],
+ "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": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/clocks/notebooks/join_metadata.ipynb b/clocks/notebooks/join_metadata.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "59eb29df-0597-4d45-b2e6-8825670effe2",
    "metadata": {},
    "outputs": [],

diff --git a/clocks/notebooks/knight.ipynb b/clocks/notebooks/knight.ipynb
@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fb157849-5454-4a60-8548-fff633fff764",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import pandas as pd\n",
+    "import pyaging as pya\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "46c6fc26-9a6b-4027-bd01-601b70eb401a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.system(\"curl -o coefficients.csv https://static-content.springer.com/esm/art%3A10.1186%2Fs13059-016-1068-z/MediaObjects/13059_2016_1068_MOESM3_ESM.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b9f484b1-f501-41b7-9565-82e03bfe97dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('coefficients.csv')\n",
+    "\n",
+    "df['feature'] = df['CpGmarker']\n",
+    "df['coefficient'] = df['CoefficientTraining']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a284fe99-dc47-4f0c-b2ff-274e136e7020",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features = df['feature'][1:].tolist()\n",
+    "\n",
+    "weights = torch.tensor(df['coefficient'][1:].tolist()).unsqueeze(0)\n",
+    "intercept = torch.tensor([df['coefficient'][0]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7b4c3f6b-72af-4e99-84c4-65b8ef58c91d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LinearModel(\n",
+       "  (linear): Linear(in_features=148, out_features=1, bias=True)\n",
+       ")"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = pya.models.LinearModel(len(features))\n",
+    "\n",
+    "model.linear.weight.data = weights\n",
+    "model.linear.bias.data = intercept\n",
+    "\n",
+    "model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "e32706f0-ce07-455e-bb17-1993c1c0e152",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "weights_dict = {\n",
+    "    'preprocessing': None, \n",
+    "    'preprocessing_helper': None,\n",
+    "    'postprocessing': None,\n",
+    "    'postprocessing_helper': None,\n",
+    "    'features': features,\n",
+    "    'weight_dict': model.state_dict(),\n",
+    "}\n",
+    "\n",
+    "metadata_dict = {\n",
+    "    'species': 'Homo sapiens',\n",
+    "    'data_type': 'methylation',\n",
+    "    'year': 2016,\n",
+    "    'implementation_approved_by_author(s)': '⌛',\n",
+    "    'preprocessing': weights_dict['preprocessing'], \n",
+    "    'postprocessing': weights_dict['postprocessing'], \n",
+    "    'citation': \"Knight, Anna K., et al. \\\"An epigenetic clock for gestational age at birth based on blood methylation data.\\\" Genome biology 17.1 (2016): 1-11.\",\n",
+    "    'doi': \"https://doi.org/10.1186/s13059-016-1068-z\",\n",
+    "    \"notes\": None,\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "34136f3c-92b8-4641-a103-381d3a7dd857",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.save(weights_dict, '../weights/knight.pt')\n",
+    "torch.save(metadata_dict, '../metadata/knight.pt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "303e9b76-993f-4691-af9d-1151b3c7638f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.system(\"rm coefficients.csv\")"
+   ]
+  }
+ ],
+ "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": "3.9.17"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/clocks/notebooks/leecpc.ipynb → clocks/notebooks/leecontrol.ipynb b/clocks/notebooks/leecpc.ipynb → clocks/notebooks/leecontrol.ipynb
@@ -126,8 +126,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "torch.save(weights_dict, '../weights/leecpc.pt')\n",
-    "torch.save(metadata_dict, '../metadata/leecpc.pt')"
+    "torch.save(weights_dict, '../weights/leecontrol.pt')\n",
+    "torch.save(metadata_dict, '../metadata/leecontrol.pt')"
    ]
   },
   {

diff --git a/clocks/notebooks/leerefinedrpc.ipynb → clocks/notebooks/leerefinedrobust.ipynb b/clocks/notebooks/leerefinedrpc.ipynb → clocks/notebooks/leerefinedrobust.ipynb
@@ -126,8 +126,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "torch.save(weights_dict, '../weights/leerefinedrpc.pt')\n",
-    "torch.save(metadata_dict, '../metadata/leerefinedrpc.pt')"
+    "torch.save(weights_dict, '../weights/leerefinedrobust.pt')\n",
+    "torch.save(metadata_dict, '../metadata/leerefinedrobust.pt')"
    ]
   },
   {

diff --git a/clocks/notebooks/leerpc.ipynb → clocks/notebooks/leerobust.ipynb b/clocks/notebooks/leerpc.ipynb → clocks/notebooks/leerobust.ipynb
@@ -126,8 +126,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "torch.save(weights_dict, '../weights/leerpc.pt')\n",
-    "torch.save(metadata_dict, '../metadata/leerpc.pt')"
+    "torch.save(weights_dict, '../weights/leerobust.pt')\n",
+    "torch.save(metadata_dict, '../metadata/leerobust.pt')"
    ]
   },
   {