{ "cells": [ { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "# Parameter estimation using ordinal data" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "This Notebook explains the use of ordinal data for parameter estimation, as described in [Schmiester et al. (2020)](https://doi.org/10.1007/s00285-020-01522-w) and [Schmiester et al. (2021)](https://doi.org/10.1093/bioinformatics/btab512). \n", "An example model is provided in `pypesto/doc/example/example_ordinal`.\n", "\n", "Ordinal data is defined as the data for which the mutual ordering of the measurements is known. The implementation allows for indistinguishable measurements, i.e. multiple measurements which cannot be ordinally distinguished from each other and are part of the same ordinal level.\n", "\n", "For the integration of ordinal data, we employ the optimal scaling approach. In this approach, each ordinal datapoint is defined as being part of a category, where the mutual ordering of categories of the same observable is known. The category interval bounds are numerically optimized and quantitative surrogate measurements are calculated to represent the ordinal measurements. This constitutes the inner subproblem of the hierarchical optimization problem.\n", "\n", "Details on the optimal scaling approach can be found in Shepard, 1962 (https://doi.org/10.1007/BF02289621).\n", "Details on the application of the gradient-based optimal scaling approach to mechanistic modeling\n", "with ordinal data can be found in Schmiester et al. 2020 (https://doi.org/10.1007/s00285-020-01522-w)\n", "and Schmiester et al. 2021 (https://doi.org/10.1093/bioinformatics/btab512)." ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## Import model from the petab_problem" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import petab\n", "\n", "import pypesto\n", "import pypesto.logging\n", "import pypesto.optimize as optimize\n", "from pypesto.hierarchical.ordinal import OrdinalInnerSolver\n", "from pypesto.petab import PetabImporter\n", "from pypesto.visualize import plot_categories_from_pypesto_result" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "To use ordinal data for parameter estimation, in pyPESTO we use the optimal scaling approach as in the referenced papers. Since the optimal scaling approach is implemented in the hierarchical manner, it requires us to specify `hierarchical=True` when importing the `petab_problem`:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Visualization table not available. Skipping.\n" ] } ], "source": [ "petab_folder = \"./example_ordinal/\"\n", "yaml_file = \"example_ordinal.yaml\"\n", "\n", "petab_problem = petab.Problem.from_yaml(petab_folder + yaml_file)\n", "\n", "importer = PetabImporter(petab_problem, hierarchical=True)" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "The `petab_problem` has to be specified in the usual PEtab formulation. The ordinal measurements have to be specified in the `measurement.tsv` file by adding `ordinal` in the `measurementType` column, and the ordering of measurements has to be specified in the `measurementCategory` column by assigning each measurement to a category:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
observableIdpreequilibrationConditionIdsimulationConditionIdmeasurementtimeobservableParametersnoiseParametersobservableTransformationnoiseDistributionmeasurementTypemeasurementCategory
0ActivityNaNInhibitor_005NaN1linnormalordinal2
1ActivityNaNInhibitor_305NaN1linnormalordinal2
2ActivityNaNInhibitor_1005NaN1linnormalordinal3
3ActivityNaNInhibitor_2505NaN1linnormalordinal3
4ActivityNaNInhibitor_3505NaN1linnormalordinal2
5ActivityNaNInhibitor_5005NaN1linnormalordinal1
6ActivityNaNInhibitor_7505NaN1linnormalordinal1
7ActivityNaNInhibitor_10005NaN1linnormalordinal1
8ActivityNaNInhibitor_30005NaN1linnormalordinal1
9YbarNaNInhibitor_005NaN1linnormalordinal1
10YbarNaNInhibitor_305NaN1linnormalordinal1
11YbarNaNInhibitor_1005NaN1linnormalordinal1
12YbarNaNInhibitor_2505NaN1linnormalordinal2
13YbarNaNInhibitor_3505NaN1linnormalordinal2
14YbarNaNInhibitor_5005NaN1linnormalordinal3
15YbarNaNInhibitor_7505NaN1linnormalordinal3
16YbarNaNInhibitor_10005NaN1linnormalordinal3
17YbarNaNInhibitor_30005NaN1linnormalordinal3
\n", "
" ], "text/plain": [ " observableId preequilibrationConditionId simulationConditionId \\\n", "0 Activity NaN Inhibitor_0 \n", "1 Activity NaN Inhibitor_3 \n", "2 Activity NaN Inhibitor_10 \n", "3 Activity NaN Inhibitor_25 \n", "4 Activity NaN Inhibitor_35 \n", "5 Activity NaN Inhibitor_50 \n", "6 Activity NaN Inhibitor_75 \n", "7 Activity NaN Inhibitor_100 \n", "8 Activity NaN Inhibitor_300 \n", "9 Ybar NaN Inhibitor_0 \n", "10 Ybar NaN Inhibitor_3 \n", "11 Ybar NaN Inhibitor_10 \n", "12 Ybar NaN Inhibitor_25 \n", "13 Ybar NaN Inhibitor_35 \n", "14 Ybar NaN Inhibitor_50 \n", "15 Ybar NaN Inhibitor_75 \n", "16 Ybar NaN Inhibitor_100 \n", "17 Ybar NaN Inhibitor_300 \n", "\n", " measurement time observableParameters noiseParameters \\\n", "0 0 5 NaN 1 \n", "1 0 5 NaN 1 \n", "2 0 5 NaN 1 \n", "3 0 5 NaN 1 \n", "4 0 5 NaN 1 \n", "5 0 5 NaN 1 \n", "6 0 5 NaN 1 \n", "7 0 5 NaN 1 \n", "8 0 5 NaN 1 \n", "9 0 5 NaN 1 \n", "10 0 5 NaN 1 \n", "11 0 5 NaN 1 \n", "12 0 5 NaN 1 \n", "13 0 5 NaN 1 \n", "14 0 5 NaN 1 \n", "15 0 5 NaN 1 \n", "16 0 5 NaN 1 \n", "17 0 5 NaN 1 \n", "\n", " observableTransformation noiseDistribution measurementType \\\n", "0 lin normal ordinal \n", "1 lin normal ordinal \n", "2 lin normal ordinal \n", "3 lin normal ordinal \n", "4 lin normal ordinal \n", "5 lin normal ordinal \n", "6 lin normal ordinal \n", "7 lin normal ordinal \n", "8 lin normal ordinal \n", "9 lin normal ordinal \n", "10 lin normal ordinal \n", "11 lin normal ordinal \n", "12 lin normal ordinal \n", "13 lin normal ordinal \n", "14 lin normal ordinal \n", "15 lin normal ordinal \n", "16 lin normal ordinal \n", "17 lin normal ordinal \n", "\n", " measurementCategory \n", "0 2 \n", "1 2 \n", "2 3 \n", "3 3 \n", "4 2 \n", "5 1 \n", "6 1 \n", "7 1 \n", "8 1 \n", "9 1 \n", "10 1 \n", "11 1 \n", "12 2 \n", "13 2 \n", "14 3 \n", "15 3 \n", "16 3 \n", "17 3 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from pandas import option_context\n", "\n", "with option_context(\"display.max_colwidth\", 400):\n", " display(petab_problem.measurement_df)" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "For ordinal measurements, the `measurement` column will be ignored.\n", "\n", "Measurements with a larger category number will be constrained to be higher in the ordering. Multiple measurements can be assigned to the same category. If this is done, these measurements will be treated as indistinguishable. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Note on inclusion of additional data types:\n", "It is possible to include observables with different types of data to the same `petab_problem`. Refer to the notebooks on using [semiquantitative data](semiquantitative_data.ipynb), [relative data](relative_data.ipynb) and [censored data](censored_data.ipynb) for details on integration of other data types. If the `measurementType` column is left empty for all measurements of an observable, the observable will be treated as quantitative." ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## Construct the objective and pypesto problem" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "Different options can be used for the optimal scaling approach:\n", "\n", "- method: `standard` / `reduced`\n", "- reparameterized: `True` / `False`\n", "- interval_constraints: `max` / `max-min`\n", "- min_gap: Any float value\n", "\n", "It is recommended to use the reduced method with reparameterization as it is the most efficient and robust choice.\n", "\n", "When no options are provided, the default is the reduced and reparameterized formulation with max as interval constraint and `min_gap=1e-16`." ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "Now when we construct the `objective`, it will construct all objects of the optimal scaling inner optimization:\n", "\n", "- `OrdinalInnerSolver`\n", "- `OrdinalCalculator`\n", "- `OrdinalProblem`\n", "\n", "Specifically, the `OrdinalInnerSolver` will be constructed with default settings. " ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "factory = importer.create_objective_creator()\n", "objective = factory.create_objective(verbose=False)" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "To give non-default options to the `OrdinalInnerSolver` and `OrdinalProblem`, one can pass them as arguments when constructing the `objective`:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "objective = factory.create_objective(\n", " inner_options={\n", " \"method\": \"reduced\",\n", " \"reparameterized\": True,\n", " \"interval_constraints\": \"max\",\n", " \"min_gap\": 0.1,\n", " },\n", " verbose=False,\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "Alternatively, we could've even given them to the `importer constructor`, they would be passed all the way to the inner solver." ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "Now let's construct the pyPESTO problem and optimizer. We're going to use a gradint-based optimizer for a faster optimization, but gradient-free optimizers can be used in the same way:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "problem = importer.create_problem(objective)\n", "\n", "engine = pypesto.engine.MultiProcessEngine(n_procs=3)\n", "\n", "optimizer = optimize.ScipyOptimizer(\n", " method=\"L-BFGS-B\",\n", " options={\"disp\": None, \"ftol\": 2.220446049250313e-09, \"gtol\": 1e-5},\n", ")\n", "n_starts = 3\n", "np.random.seed(n_starts)" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## Run optimization using optimal scaling approach" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "If we want to change options of the `OrdinalInnerSolver` a new instance of it with new options can be passed to the correct inner calculator. Since in our problem there is only one data type and so one inner problem, we pass it to the first inner calculator `problem.objective.calculator.inner_calculators[0]`.\n", "\n", "In case of multiple inner problems, one would have to check the instance of the inner calculator, find the `OrdinalCalculator` and pass the new inner solver to it." ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "#### Run optimization using the reduced and reparameterized approach" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "scrolled": true }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 10/10 [00:14<00:00, 1.41s/it]\n" ] } ], "source": [ "np.random.seed(n_starts)\n", "problem.objective.calculator.inner_calculators[\n", " 0\n", "].inner_solver = OrdinalInnerSolver(\n", " options={\n", " \"method\": \"reduced\",\n", " \"reparameterized\": True,\n", " \"interval_constraints\": \"max\",\n", " \"min_gap\": 1e-10,\n", " }\n", ")\n", "\n", "res_reduced_reparameterized = optimize.minimize(\n", " problem, n_starts=n_starts, optimizer=optimizer, engine=engine\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "#### Run optimization using the reduced non-reparameterized approach" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 10/10 [00:12<00:00, 1.30s/it]\n" ] } ], "source": [ "np.random.seed(n_starts)\n", "problem.objective.calculator.inner_calculators[\n", " 0\n", "].inner_solver = OrdinalInnerSolver(\n", " options={\n", " \"method\": \"reduced\",\n", " \"reparameterized\": False,\n", " \"interval_constraints\": \"max\",\n", " \"min_gap\": 1e-10,\n", " }\n", ")\n", "\n", "res_reduced = optimize.minimize(\n", " problem, n_starts=n_starts, optimizer=optimizer, engine=engine\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "#### Run optimization using the standard approach" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 10/10 [00:13<00:00, 1.32s/it]\n" ] } ], "source": [ "np.random.seed(n_starts)\n", "problem.objective.calculator.inner_calculators[\n", " 0\n", "].inner_solver = OrdinalInnerSolver(\n", " options={\n", " \"method\": \"standard\",\n", " \"reparameterized\": False,\n", " \"interval_constraints\": \"max\",\n", " \"min_gap\": 1e-10,\n", " }\n", ")\n", "\n", "res_standard = optimize.minimize(\n", " problem, n_starts=n_starts, optimizer=optimizer, engine=engine\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## Compare results" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Reduced formulation leads to improved computation times" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mean computation time for standard approach: 1.314679503440857\n", "Mean computation time for reduced approach: 1.2964157342910767\n", "Mean computation time for reduced reparameterized approach: 1.4066837549209594\n" ] } ], "source": [ "time_standard = res_standard.optimize_result.get_for_key(\"time\")\n", "print(f\"Mean computation time for standard approach: {np.mean(time_standard)}\")\n", "\n", "time_reduced = res_reduced.optimize_result.get_for_key(\"time\")\n", "print(f\"Mean computation time for reduced approach: {np.mean(time_reduced)}\")\n", "\n", "time_reduced_reparameterized = (\n", " res_reduced_reparameterized.optimize_result.get_for_key(\"time\")\n", ")\n", "print(\n", " f\"Mean computation time for reduced reparameterized approach: {np.mean(time_reduced_reparameterized)}\"\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "All approaches yield the same objective function values" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from pypesto.visualize import waterfall\n", "\n", "waterfall(\n", " [res_standard, res_reduced, res_reduced_reparameterized], order_by_id=True\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "To be sure the function values are the same we can look at them directly as well:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[0.0005740044728722403], [0.0005735524499463118], [0.0005735488036411325]]\n", "[[0.0019888878065788323], [0.0019888878053397384], [0.0019888878047586195]]\n", "[[0.0019888867637264276], [0.001988886720482654], [0.0019888867163511447]]\n", "[[0.0005750245895037861], [0.0005735564442667997], [0.0005749981726043572]]\n", "[[0.0005735481168856594], [0.0005744914709652644], [0.0005745014894324961]]\n", "[[0.0005740931002846301], [0.0005740925258111577], [0.0005740925408729459]]\n", "[[0.000574326933214732], [0.0005747942808938552], [0.0005735495628630107]]\n", "[[0.0005735468324744648], [0.000574185830988405], [0.0005741962154156796]]\n", "[[0.0005735697299636087], [0.0005735726866398947], [0.0005735613988301798]]\n", "[[0.0005735456832869585], [0.0005735497839313598], [0.0005735585959751523]]\n" ] } ], "source": [ "for start_id in range(10):\n", " print(\n", " [\n", " [\n", " res.fval\n", " for res in result.optimize_result.as_list()\n", " if res.id == str(start_id)\n", " ]\n", " for result in [\n", " res_standard,\n", " res_reduced,\n", " res_reduced_reparameterized,\n", " ]\n", " ]\n", " )" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "For any results, we can plot the optimized categories using the `plot_categories_from_pypesto_result` method." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot_categories_from_pypesto_result(res_standard, figsize=(10, 10))\n", "plt.show()" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "In this plot we can see that all surrogate data is inside their respective categories. So the ordering given in the measurements is fully satisfied. This constitutes a perfect fit of the data in the ordinal sense. " ] } ], "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": "3.12.3" }, "vscode": { "interpreter": { "hash": "b4f64b1cfeae9987d9a74471fe6faf49d769577c41c664ee1b5af662a144b184" } } }, "nbformat": 4, "nbformat_minor": 4 }