{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2e9d5661-b193-4eb1-905c-9b54387933c1",
   "metadata": {},
   "source": [
    "# Model selection with non-SBML models and unsupported calibration tools\n",
    "\n",
    "PEtab Select is currently designed for use with models encoded in SBML. However, this requirement is inherited from PEtab, and the SBML model is irrelevant to PEtab Select, which only reads the parameter table of a model's PEtab problem to determine the estimated parameters (e.g. to accurately compute criteria values).\n",
    "\n",
    "Furthermore, PEtab Select is designed for use with one of the supported calibration tools. However, PEtab Select also implements a command-line interface (CLI) and Python interface such that other calibration tools can easily interface with PEtab Select in order to perform the model selection.\n",
    "\n",
    "In this notebook, we demonstrate model selection with a modeling framework that currently does not support PEtab problems (specifically, [statsmodels](https://www.statsmodels.org/stable/index.html)). Since statsmodels is a Python package, we use the Python interface of PEtab Select. Synthetic data was generated from the model\n",
    "$$y(t) = 20t + 10t^2 + 5t^3 + \\epsilon$$\n",
    "where $\\epsilon$ is drawn from the standard normal distribution and represents measurement noise. The hypothetical scenario is that you are provided $(t,y)$ data pairs and asked to identify the powers of $t$ that are evidenced by the data (i.e., that were used to generate the data). Here, we only consider polynomial models involving terms up to $t^5$, i.e., the superset model is\n",
    "$$y(t) = \\sum_{i=0}^5 k_i t^i,$$\n",
    "where $k_i$ is the $i$th coefficient in the linear regression model."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b2a20814-e11d-4d65-9987-b84a50abf59d",
   "metadata": {},
   "source": [
    "## \"True\" model\n",
    "\n",
    "We start by loading the data and demonstrating model calibration of the true model using statsmodels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6889e520-e13f-4b1c-8dc4-43226e37d165",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:29.325238Z",
     "iopub.status.busy": "2026-06-30T15:50:29.325021Z",
     "iopub.status.idle": "2026-06-30T15:50:30.864833Z",
     "shell.execute_reply": "2026-06-30T15:50:30.864371Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                 OLS Regression Results                                \n",
      "=======================================================================================\n",
      "Dep. Variable:                      y   R-squared (uncentered):                   1.000\n",
      "Model:                            OLS   Adj. R-squared (uncentered):              1.000\n",
      "Method:                 Least Squares   F-statistic:                          2.226e+08\n",
      "Date:                Tue, 30 Jun 2026   Prob (F-statistic):                        0.00\n",
      "Time:                        15:50:30   Log-Likelihood:                         -137.59\n",
      "No. Observations:                 101   AIC:                                      281.2\n",
      "Df Residuals:                      98   BIC:                                      289.0\n",
      "Df Model:                           3                                                  \n",
      "Covariance Type:            nonrobust                                                  \n",
      "==============================================================================\n",
      "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
      "------------------------------------------------------------------------------\n",
      "x1            19.8935      0.165    120.611      0.000      19.566      20.221\n",
      "x2            10.0536      0.051    197.694      0.000       9.953      10.155\n",
      "x3             4.9954      0.004   1334.839      0.000       4.988       5.003\n",
      "==============================================================================\n",
      "Omnibus:                        1.563   Durbin-Watson:                   1.861\n",
      "Prob(Omnibus):                  0.458   Jarque-Bera (JB):                1.284\n",
      "Skew:                          -0.078   Prob(JB):                        0.526\n",
      "Kurtosis:                       2.470   Cond. No.                         695.\n",
      "==============================================================================\n",
      "\n",
      "Notes:\n",
      "[1] R² is computed without centering (uncentered) since the model does not contain a constant.\n",
      "[2] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
     ]
    }
   ],
   "source": [
    "# Based on the statsmodels \"Ordinary Least Squares\" example\n",
    "# https://www.statsmodels.org/stable/examples/notebooks/generated/ols.html\n",
    "\n",
    "import numpy as np\n",
    "import petab\n",
    "import statsmodels.api as sm\n",
    "from petab import MEASUREMENT, TIME\n",
    "\n",
    "import petab_select\n",
    "from petab_select.constants import (\n",
    "    CANDIDATE_SPACE,\n",
    "    ESTIMATE,\n",
    "    TERMINATE,\n",
    "    UNCALIBRATED_MODELS,\n",
    "    Criterion,\n",
    ")\n",
    "\n",
    "# Data was generated with the formula (see next cell to regenerate data)\n",
    "# y(t) = 20*t + 10*t^2 + 5*t^3\n",
    "df = petab.get_measurement_df(\n",
    "    \"other_model_types_problem/petab/measurements.tsv\"\n",
    ")\n",
    "t = df[TIME].to_numpy()\n",
    "y = df[MEASUREMENT].to_numpy()\n",
    "\n",
    "# Show statsmodels fit for the \"true\" model\n",
    "true_T = np.column_stack([t**1, t**2, t**3])\n",
    "print(sm.OLS(y, true_T).fit().summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d14b4c55-2494-4fdc-a45e-e2983e6bf838",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:30.866005Z",
     "iopub.status.busy": "2026-06-30T15:50:30.865905Z",
     "iopub.status.idle": "2026-06-30T15:50:30.868151Z",
     "shell.execute_reply": "2026-06-30T15:50:30.867385Z"
    }
   },
   "outputs": [],
   "source": [
    "# Uncomment to regenerate data\n",
    "\n",
    "# import numpy as np\n",
    "# rng = np.random.default_rng(seed=0)\n",
    "\n",
    "# # Measurement time points\n",
    "# t = np.linspace(0, 10, 101)\n",
    "# # The first three powers of x are used to generate the data\n",
    "# T = np.column_stack([t**1, t**2, t**3])\n",
    "# K = np.array([20, 10, 5])\n",
    "# noise = rng.normal(size=t.size)\n",
    "# y = np.dot(T, K) + noise\n",
    "\n",
    "# # Write PEtab measurement table\n",
    "# lines = [\"observableId\\tsimulationConditionId\\ttime\\tmeasurement\"]\n",
    "# for t_, y_ in zip(t, y, strict=True):\n",
    "#     lines.append(f\"y\\tdefault\\t{round(t_,1)}\\t{round(y_,5)}\")\n",
    "# content = \"\\n\".join(lines)\n",
    "# with open(\"other_model_types_problem/petab/measurements.tsv\", \"w\") as f:\n",
    "#     f.write(content)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c566b1b7-d01b-4964-b7f6-31cb9f4e4acc",
   "metadata": {},
   "source": [
    "## Model selection\n",
    "\n",
    "To perform model selection, we define three methods to:\n",
    "\n",
    "1. calibrate a single model\n",
    "\n",
    "    This is where we convert a PEtab Select model into a statsmodels model, fit the model with statsmodels, then save the log-likelihood value in the PEtab Select model.\n",
    "\n",
    "2. perform a single iteration of a model selection method involving calibration of multiple models\n",
    "\n",
    "    This is generic code that executes the required PEtab Select commands.\n",
    "\n",
    "3. perform a full model selection run, involving all iterations of a model selection method\n",
    "\n",
    "    This loads the PEtab Select problem from disk and performs all iterations of a model selection method.\n",
    "\n",
    "In this case, the PEtab Select problem is setup to perform backward selection ([see the specification files for this example](https://github.com/PEtab-dev/petab_select/tree/main/doc/examples/other_model_types_problem/petab_select))."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "89fb34cb-3b78-4b89-b58f-78e3f90414c1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:30.869909Z",
     "iopub.status.busy": "2026-06-30T15:50:30.869634Z",
     "iopub.status.idle": "2026-06-30T15:50:30.874667Z",
     "shell.execute_reply": "2026-06-30T15:50:30.874269Z"
    }
   },
   "outputs": [],
   "source": [
    "def calibrate_model(model: petab_select.Model, t=t, y=y):\n",
    "    # Convert the PEtab Select model into a statsmodel model\n",
    "    powers = [\n",
    "        int(parameter_id[1:])\n",
    "        for parameter_id, parameter_value in model.parameters.items()\n",
    "        if parameter_value == ESTIMATE\n",
    "    ]\n",
    "    if not powers:\n",
    "        return\n",
    "    T = np.column_stack([t**i for i in powers])\n",
    "    sm_model = sm.OLS(y, T)\n",
    "\n",
    "    # Calibrate\n",
    "    results = sm_model.fit()\n",
    "\n",
    "    # Save the log-likelihood\n",
    "    model.set_criterion(criterion=Criterion.LLH, value=results.llf)\n",
    "\n",
    "\n",
    "def perform_iteration(\n",
    "    problem: petab_select.Problem, candidate_space: petab_select.CandidateSpace\n",
    "):\n",
    "    # Start the iteration, request models according to the model selection method.\n",
    "    iteration = petab_select.ui.start_iteration(\n",
    "        problem=problem, candidate_space=candidate_space\n",
    "    )\n",
    "\n",
    "    # Calibrate each model.\n",
    "    models = iteration[UNCALIBRATED_MODELS]\n",
    "    for model in models:\n",
    "        if all(\n",
    "            parameter_value != ESTIMATE\n",
    "            for parameter_value in model.parameters.values()\n",
    "        ):\n",
    "            del models[model.hash]\n",
    "            continue\n",
    "        calibrate_model(model=model)\n",
    "        # Compute the criterion based on the log-likelihood computed by statsmodels.\n",
    "        model.compute_criterion(criterion=problem.criterion)\n",
    "\n",
    "    # End the iteration and return the results.\n",
    "    return petab_select.ui.end_iteration(\n",
    "        problem=problem,\n",
    "        candidate_space=iteration[CANDIDATE_SPACE],\n",
    "        calibrated_models=models,\n",
    "    )\n",
    "\n",
    "\n",
    "def run_model_selection():\n",
    "    # Load the PEtab Select problem.\n",
    "    problem = petab_select.Problem.from_yaml(\n",
    "        \"other_model_types_problem/petab_select/problem.yaml\"\n",
    "    )\n",
    "    candidate_space = None\n",
    "\n",
    "    # Perform all iterations of the model selection method until the termination signal is emitted.\n",
    "    while True:\n",
    "        iteration_results = perform_iteration(\n",
    "            problem=problem, candidate_space=candidate_space\n",
    "        )\n",
    "        if iteration_results[TERMINATE]:\n",
    "            break\n",
    "        candidate_space = iteration_results[CANDIDATE_SPACE]\n",
    "\n",
    "    # Return the problem, which contains the calibrated models.\n",
    "    return problem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "93ffcec5-3143-4906-87a8-acf60c541ce4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:30.875845Z",
     "iopub.status.busy": "2026-06-30T15:50:30.875730Z",
     "iopub.status.idle": "2026-06-30T15:50:31.119032Z",
     "shell.execute_reply": "2026-06-30T15:50:31.118402Z"
    }
   },
   "outputs": [],
   "source": [
    "# Run the model selection method.\n",
    "problem = run_model_selection()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a93ab68f-7831-40bd-82b0-d365cca8008c",
   "metadata": {},
   "source": [
    "## Analysis\n",
    "\n",
    "As when using a PEtab-compatible calibration tool, the results from calibration with statsmodels can also be analyzed with PEtab Select.\n",
    "\n",
    "Firstly, we get the best model identified during model selection. It matches the \"true\" model, with the same AIC as computed by statsmodels at the top of this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ba3a58af-8b13-4525-812a-9c7708292bc7",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.120473Z",
     "iopub.status.busy": "2026-06-30T15:50:31.120379Z",
     "iopub.status.idle": "2026-06-30T15:50:31.123114Z",
     "shell.execute_reply": "2026-06-30T15:50:31.122687Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Best model information\n",
      "----------------------\n",
      "PEtab Select model hash: M-011100\n",
      "Selected powers of t: [1, 2, 3]\n",
      "Log-Likelihood: -137.59037189701047\n",
      "AIC: 281.18074379402094\n",
      "\n"
     ]
    }
   ],
   "source": [
    "best_model = petab_select.analyze.get_best(\n",
    "    models=problem.state.models, criterion=problem.criterion\n",
    ")\n",
    "print(f\"\"\"\n",
    "Best model information\n",
    "----------------------\n",
    "PEtab Select model hash: {best_model.hash}\n",
    "Selected powers of t: {[int(parameter_id[1:]) for parameter_id, parameter_value in best_model.parameters.items() if parameter_value == ESTIMATE]}\n",
    "Log-Likelihood: {best_model.get_criterion(criterion=Criterion.LLH)}\n",
    "AIC: {best_model.get_criterion(criterion=Criterion.AIC)}\n",
    "\"\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "92857455-d8be-4bde-adc6-e6ab8de27748",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.124233Z",
     "iopub.status.busy": "2026-06-30T15:50:31.124027Z",
     "iopub.status.idle": "2026-06-30T15:50:31.224768Z",
     "shell.execute_reply": "2026-06-30T15:50:31.224002Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot AIC of all models that were calibrated.\n",
    "\n",
    "import petab_select.plot\n",
    "\n",
    "plot_data = petab_select.plot.PlotData(\n",
    "    models=problem.state.models, criterion=problem.criterion\n",
    ")\n",
    "\n",
    "petab_select.plot.scatter_criterion_vs_n_estimated(plot_data=plot_data);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4c0a4f6f-9099-4e22-a589-80cebaf466cc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.226400Z",
     "iopub.status.busy": "2026-06-30T15:50:31.226298Z",
     "iopub.status.idle": "2026-06-30T15:50:31.508221Z",
     "shell.execute_reply": "2026-06-30T15:50:31.507385Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2000x2000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the history of model selection iterations.\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "draw_networkx_kwargs = {\n",
    "    \"arrowstyle\": \"-|>\",\n",
    "    \"node_shape\": \"s\",\n",
    "    \"edgecolors\": \"k\",\n",
    "}\n",
    "fig, ax = plt.subplots(figsize=(20, 20))\n",
    "petab_select.plot.graph_iteration_layers(\n",
    "    plot_data=plot_data,\n",
    "    draw_networkx_kwargs=draw_networkx_kwargs,\n",
    "    ax=ax,\n",
    ");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "supp-petab-prose",
   "metadata": {},
   "source": [
    "## Supplementary: the PEtab files\n",
    "\n",
    "The PEtab Select problem used above is stored alongside this notebook, in `other_model_types_problem/`. This section explains what those files contain. The directory has two parts: a standard **PEtab problem** (`petab/`) that describes the model and data, and a **PEtab Select problem** (`petab_select/`) that describes the model space and the selection settings.\n",
    "\n",
    "```\n",
    "other_model_types_problem/\n",
    "├── petab/                 # the PEtab problem\n",
    "│   ├── problem.yaml\n",
    "│   ├── parameters.tsv\n",
    "│   ├── observables.tsv\n",
    "│   ├── conditions.tsv\n",
    "│   ├── measurements.tsv\n",
    "│   └── dummy.xml\n",
    "└── petab_select/          # the PEtab Select problem\n",
    "    ├── problem.yaml\n",
    "    └── model_space.tsv\n",
    "```\n",
    "\n",
    "### The PEtab problem (`petab/`)\n",
    "\n",
    "A PEtab problem normally pairs an SBML model with tables for parameters, observables, conditions, and measurements.\n",
    "In this example however, we focus on only the information relevant to PEtab Select. The required non-dummy files are:\n",
    "\n",
    "- `problem.yaml` — the PEtab problem file. It points to the parameter table and, for its single problem, to the condition, measurement, (dummy) observable, and (dummy) SBML files.\n",
    "- `parameters.tsv` — the six regression coefficients `k0`–`k5`, one per power of `t`. Each is on a linear scale with bounds `[0, 100]`. The `estimate` column is only a default; for each candidate model, PEtab Select overrides it (via the model space) to decide which coefficients are estimated. This is the only table PEtab Select reads, in order to count the estimated parameters when computing criteria such as the AIC.\n",
    "\n",
    "The other files can be dummy files. In this example, we used them to encode as much information as possible, even though they are not used, just to demonstrate the PEtab format:\n",
    "\n",
    "- `observables.tsv` — defines a single observable `y` whose formula is the regression model $y(t) = \\sum_{i=0}^{5} k_i\\, t^i$, written as `k0*time^0 + k1*time^1 + ... + k5*time^5`. The `noiseFormula` is `1` (unit, constant noise), matching the standard-normal noise used to generate the data.\n",
    "- `conditions.tsv` — a single dummy experimental condition, `default` (the data involves no experimental perturbations/conditions).\n",
    "- `measurements.tsv` — the synthetic data: 101 measurements of observable `y` at condition `default`, one per time point $t = 0.0, 0.1, \\ldots, 10.0$. The values were generated from $y(t) = 20t + 10t^2 + 5t^3 + \\epsilon$ (i.e. only the powers $t^1, t^2, t^3$ are truly present) with standard-normal noise $\\epsilon$. This is used in the notebook to load data, but the data could have been loaded from e.g. an Excel spreadsheet too.\n",
    "- `dummy.xml` — an essentially empty SBML model.\n",
    "\n",
    "We display each PEtab table below, and print the PEtab problem YAML file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "supp-petab-tables",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "petab/parameters.tsv\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>parameterId</th>\n",
       "      <th>parameterScale</th>\n",
       "      <th>lowerBound</th>\n",
       "      <th>upperBound</th>\n",
       "      <th>estimate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>k0</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>k1</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>k2</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>k3</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>k4</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>k5</td>\n",
       "      <td>lin</td>\n",
       "      <td>0</td>\n",
       "      <td>100</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  parameterId parameterScale  lowerBound  upperBound  estimate\n",
       "0          k0            lin           0         100         1\n",
       "1          k1            lin           0         100         1\n",
       "2          k2            lin           0         100         1\n",
       "3          k3            lin           0         100         1\n",
       "4          k4            lin           0         100         1\n",
       "5          k5            lin           0         100         1"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "petab/observables.tsv\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>observableId</th>\n",
       "      <th>observableFormula</th>\n",
       "      <th>noiseFormula</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>y</td>\n",
       "      <td>k0*time^0 + k1*time^1 + k2*time^2 + k3*time^3 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  observableId                                  observableFormula  \\\n",
       "0            y  k0*time^0 + k1*time^1 + k2*time^2 + k3*time^3 ...   \n",
       "\n",
       "   noiseFormula  \n",
       "0             1  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "petab/conditions.tsv\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>conditionId</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>default</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  conditionId\n",
       "0     default"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "petab/measurements.tsv\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>observableId</th>\n",
       "      <th>simulationConditionId</th>\n",
       "      <th>time</th>\n",
       "      <th>measurement</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.12573</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>0.1</td>\n",
       "      <td>1.97290</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>0.2</td>\n",
       "      <td>5.08042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>0.3</td>\n",
       "      <td>7.13990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>0.4</td>\n",
       "      <td>9.38433</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>9.6</td>\n",
       "      <td>5537.44101</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>9.7</td>\n",
       "      <td>5697.67947</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>9.8</td>\n",
       "      <td>5861.01878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6028.19348</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>y</td>\n",
       "      <td>default</td>\n",
       "      <td>10.0</td>\n",
       "      <td>6200.50268</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>101 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    observableId simulationConditionId  time  measurement\n",
       "0              y               default   0.0      0.12573\n",
       "1              y               default   0.1      1.97290\n",
       "2              y               default   0.2      5.08042\n",
       "3              y               default   0.3      7.13990\n",
       "4              y               default   0.4      9.38433\n",
       "..           ...                   ...   ...          ...\n",
       "96             y               default   9.6   5537.44101\n",
       "97             y               default   9.7   5697.67947\n",
       "98             y               default   9.8   5861.01878\n",
       "99             y               default   9.9   6028.19348\n",
       "100            y               default  10.0   6200.50268\n",
       "\n",
       "[101 rows x 4 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from IPython.display import display\n",
    "\n",
    "for petab_file in [\n",
    "    \"petab/parameters.tsv\",\n",
    "    \"petab/observables.tsv\",\n",
    "    \"petab/conditions.tsv\",\n",
    "    \"petab/measurements.tsv\",\n",
    "]:\n",
    "    print(petab_file)\n",
    "    display(pd.read_csv(f\"other_model_types_problem/{petab_file}\", sep=\"\\t\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "supp-petab-yaml",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.531862Z",
     "iopub.status.busy": "2026-06-30T15:50:31.531769Z",
     "iopub.status.idle": "2026-06-30T15:50:31.533582Z",
     "shell.execute_reply": "2026-06-30T15:50:31.533134Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "format_version: 1\n",
      "parameter_file: parameters.tsv\n",
      "problems:\n",
      "- condition_files:\n",
      "  - conditions.tsv\n",
      "  measurement_files:\n",
      "  - measurements.tsv\n",
      "  sbml_files:\n",
      "  - dummy.xml\n",
      "  observable_files:\n",
      "  - observables.tsv\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# The PEtab problem YAML file\n",
    "print(open(\"other_model_types_problem/petab/problem.yaml\").read())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "supp-select-prose",
   "metadata": {},
   "source": [
    "### The PEtab Select problem (`petab_select/`)\n",
    "\n",
    "- `model_space.tsv` — the model space. It defines a single model subspace `M` (pointing to `../petab/problem.yaml`) with one column per coefficient, `k0`–`k5`. Each entry is `0;estimate`, meaning the coefficient can either be fixed to `0` (that power of `t` is then effectively removed from the model) or estimated (that power is present). With six independently toggled coefficients, this single row compactly encodes all $2^6 = 64$ candidate models. The goal of the selection is to recover the powers that generated the data ($t^1, t^2, t^3$)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "supp-select-table",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.534663Z",
     "iopub.status.busy": "2026-06-30T15:50:31.534577Z",
     "iopub.status.idle": "2026-06-30T15:50:31.539467Z",
     "shell.execute_reply": "2026-06-30T15:50:31.539067Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "petab_select/model_space.tsv\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>model_subspace_id</th>\n",
       "      <th>petab_yaml</th>\n",
       "      <th>k0</th>\n",
       "      <th>k1</th>\n",
       "      <th>k2</th>\n",
       "      <th>k3</th>\n",
       "      <th>k4</th>\n",
       "      <th>k5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>M</td>\n",
       "      <td>../petab/problem.yaml</td>\n",
       "      <td>0;estimate</td>\n",
       "      <td>0;estimate</td>\n",
       "      <td>0;estimate</td>\n",
       "      <td>0;estimate</td>\n",
       "      <td>0;estimate</td>\n",
       "      <td>0;estimate</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  model_subspace_id             petab_yaml          k0          k1  \\\n",
       "0                 M  ../petab/problem.yaml  0;estimate  0;estimate   \n",
       "\n",
       "           k2          k3          k4          k5  \n",
       "0  0;estimate  0;estimate  0;estimate  0;estimate  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(\"petab_select/model_space.tsv\")\n",
    "display(\n",
    "    pd.read_csv(\n",
    "        \"other_model_types_problem/petab_select/model_space.tsv\", sep=\"\\t\"\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "502e7828-1cc3-4a87-b105-5ee1cdae8e53",
   "metadata": {},
   "source": [
    "- `problem.yaml` — the model selection settings: compare models by the `AIC` `criterion`, search the model space with the `backward` `method` (start from the full model and remove terms), and read the model space from `model_space.tsv`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "supp-select-yaml",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-06-30T15:50:31.540562Z",
     "iopub.status.busy": "2026-06-30T15:50:31.540472Z",
     "iopub.status.idle": "2026-06-30T15:50:31.542497Z",
     "shell.execute_reply": "2026-06-30T15:50:31.542107Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "format_version: 1\n",
      "criterion: AIC\n",
      "method: backward\n",
      "model_space_files:\n",
      "- model_space.tsv\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# The PEtab Select problem YAML file\n",
    "print(open(\"other_model_types_problem/petab_select/problem.yaml\").read())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}