diff --git a/README.md b/README.md
index d422ad8..4bea96c 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,27 @@
 # Analysis template repository
 
-This contains the raw structure I usually use when doing single-cell/spatial data analysis.
+This contains the raw structure I usually use when doing single-cell/spatial data analysis. This template is based on ideas from Philipp Weiler, I took heavy inspiration and copied parts from [his template repository](https://github.com/WeilerP/sc_analysis_template).
+
+## Set up
+
+1. Rename `src/fancypackage/`.
+2. Update `pyproject.toml` to include the correct information
+    - Project name
+    - Project description
+    - Project-specific Python requirements
+    - Project author
+    - Project maintainers
+    - Project URLs
+3. Update `src/fancypackage/core/_constants.py` to include any paths relevant to your analysis and that should be accessible from any script or Jupyter notebook
+4. Update this README to include the relevant information about your project.
+
+## Installation
+
+```bash
+pip install -e ".[dev]"
+pre-commit install
+```
+
+## Things to keep in mind
+
+Whenever you use a new single-cell tool, add it to `known_bio` in `pyproject.toml` s.t. `isort` can work correctly.
diff --git a/analysis/ML-2024-04-24_sample_notebook.ipynb b/analysis/ML-2024-04-24_sample_notebook.ipynb
index 34fe54d..fee0051 100644
--- a/analysis/ML-2024-04-24_sample_notebook.ipynb
+++ b/analysis/ML-2024-04-24_sample_notebook.ipynb
@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2021-05-31T09:25:05.984402Z",
@@ -82,20 +82,9 @@
    },
    "outputs": [],
    "source": [
-    "# import standard packages\n",
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "\n",
-    "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "\n",
-    "import sys\n",
-    "\n",
     "# import single-cell packages\n",
     "import scanpy as sc\n",
-    "\n",
-    "sys.path.extend([\"../\"])\n",
-    "from paths import DATA_DIR, FIG_DIR, CODE_DIR"
+    "from fancypackage import DATA_DIR, FIG_DIR"
    ]
   },
   {
@@ -107,14 +96,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running Scanpy 1.9.3, on 2023-08-09 11:52.\n"
+      "Running Scanpy 1.9.3, on 2024-04-24 17:16.\n"
      ]
     }
    ],
@@ -131,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -160,6 +149,30 @@
     "### Data loading"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Any data should be stored in the `data` directory, or somewhere centrally on the cluster. The `data` directly is acessible from anywhere in this repo via `DATA_DIR`: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/Users/mlange/Projects/analysis_template/data\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(DATA_DIR)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},