Add Glucose205 benchmark

ml_peg/analysis/conformers/Glucose205/analyse_Glucose205.py

@@ -0,0 +1,148 @@
+"""
+Analyse the glucose conformer energy dataset.
+
+Journal of Chemical Theory and Computation,
+2016 12 (12), 6157-6168.
+DOI: 10.1021/acs.jctc.6b00876
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ase import units
+from ase.io import read, write
+import pytest
+
+from ml_peg.analysis.utils.decorators import build_table, plot_parity
+from ml_peg.analysis.utils.utils import build_d3_name_map, load_metrics_config, mae
+from ml_peg.app import APP_ROOT
+from ml_peg.calcs import CALCS_ROOT
+from ml_peg.models.get_models import load_models
+from ml_peg.models.models import current_models
+
+MODELS = load_models(current_models)
+D3_MODEL_NAMES = build_d3_name_map(MODELS)
+
+EV_TO_KCAL = units.mol / units.kcal
+CALC_PATH = CALCS_ROOT / "conformers" / "Glucose205" / "outputs"
+OUT_PATH = APP_ROOT / "data" / "conformers" / "Glucose205"
+
+METRICS_CONFIG_PATH = Path(__file__).with_name("metrics.yml")
+DEFAULT_THRESHOLDS, DEFAULT_TOOLTIPS, DEFAULT_WEIGHTS = load_metrics_config(
+    METRICS_CONFIG_PATH
+)
+
+
+def labels() -> list:
+    """
+    Get list of system names.
+
+    Returns
+    -------
+    list
+        List of all system names.
+    """
+    for model_name in MODELS:
+        labels_list = [path.stem for path in sorted((CALC_PATH / model_name).glob("*"))]
+        break
+    return labels_list
+
+
+@pytest.fixture
+@plot_parity(
+    filename=OUT_PATH / "figure_glucose205.json",
+    title="Energies",
+    x_label="Predicted energy / kcal/mol",
+    y_label="Reference energy / kcal/mol",
+    hoverdata={
+        "Labels": labels(),
+    },
+)
+def conformer_energies() -> dict[str, list]:
+    """
+    Get conformer energies for all systems.
+
+    Returns
+    -------
+    dict[str, list]
+        Dictionary of all reference and predicted conformer energies.
+    """
+    results = {"ref": []} | {mlip: [] for mlip in MODELS}
+    ref_stored = False
+
+    for model_name in MODELS:
+        for label in labels():
+            atoms = read(CALC_PATH / model_name / f"{label}.xyz")
+
+            results[model_name].append(atoms.info["model_rel_energy"] * EV_TO_KCAL)
+            if not ref_stored:
+                results["ref"].append(atoms.info["ref_energy"] * EV_TO_KCAL)
+
+            # Write structures for app
+            structs_dir = OUT_PATH / model_name
+            structs_dir.mkdir(parents=True, exist_ok=True)
+            write(structs_dir / f"{label}.xyz", atoms)
+        ref_stored = True
+    return results
+
+
+@pytest.fixture
+def get_mae(conformer_energies) -> dict[str, float]:
+    """
+    Get mean absolute error for conformer energies.
+
+    Parameters
+    ----------
+    conformer_energies
+        Dictionary of reference and predicted conformer energies.
+
+    Returns
+    -------
+    dict[str, float]
+        Dictionary of predicted conformer energies errors for all models.
+    """
+    results = {}
+    for model_name in MODELS:
+        results[model_name] = mae(
+            conformer_energies["ref"], conformer_energies[model_name]
+        )
+    return results
+
+
+@pytest.fixture
+@build_table(
+    filename=OUT_PATH / "glucose205_metrics_table.json",
+    metric_tooltips=DEFAULT_TOOLTIPS,
+    thresholds=DEFAULT_THRESHOLDS,
+    mlip_name_map=D3_MODEL_NAMES,
+)
+def metrics(get_mae: dict[str, float]) -> dict[str, dict]:
+    """
+    Get all metrics.
+
+    Parameters
+    ----------
+    get_mae
+        Mean absolute errors for all models.
+
+    Returns
+    -------
+    dict[str, dict]
+        Metric names and values for all models.
+    """
+    return {
+        "MAE": get_mae,
+    }
+
+
+def test_glucose205(metrics: dict[str, dict]) -> None:
+    """
+    Run Glucose205 test.
+
+    Parameters
+    ----------
+    metrics
+        All new benchmark metric names and dictionary of values for each model.
+    """
+    return

ml_peg/analysis/conformers/Glucose205/metrics.yml

@@ -0,0 +1,7 @@
+metrics:
+  MAE:
+    good: 0.0
+    bad: 20.0
+    unit: kcal/mol
+    tooltip: Mean Absolute Error for all systems
+    level_of_theory: CCSD(T)

ml_peg/app/conformers/Glucose205/app_Glucose205.py

@@ -0,0 +1,90 @@
+"""Run Glucose205 app."""
+
+from __future__ import annotations
+
+from dash import Dash
+from dash.html import Div
+
+from ml_peg.app import APP_ROOT
+from ml_peg.app.base_app import BaseApp
+from ml_peg.app.utils.build_callbacks import (
+    plot_from_table_column,
+    struct_from_scatter,
+)
+from ml_peg.app.utils.load import read_plot
+from ml_peg.models.get_models import get_model_names
+from ml_peg.models.models import current_models
+
+MODELS = get_model_names(current_models)
+BENCHMARK_NAME = "Glucose205"
+DOCS_URL = (
+    "https://ddmms.github.io/ml-peg/user_guide/benchmarks/conformers.html#glucose205"
+)
+DATA_PATH = APP_ROOT / "data" / "conformers" / "Glucose205"
+
+
+class Glucose205App(BaseApp):
+    """Glucose205 benchmark app layout and callbacks."""
+
+    def register_callbacks(self) -> None:
+        """Register callbacks to app."""
+        scatter = read_plot(
+            DATA_PATH / "figure_glucose205.json",
+            id=f"{BENCHMARK_NAME}-figure",
+        )
+
+        model_dir = DATA_PATH / MODELS[0]
+        if model_dir.exists():
+            labels = sorted([f.stem for f in model_dir.glob("*.xyz")])
+            structs = [
+                f"assets/conformers/Glucose205/{MODELS[0]}/{label}.xyz"
+                for label in labels
+            ]
+        else:
+            structs = []
+
+        plot_from_table_column(
+            table_id=self.table_id,
+            plot_id=f"{BENCHMARK_NAME}-figure-placeholder",
+            column_to_plot={"MAE": scatter},
+        )
+
+        struct_from_scatter(
+            scatter_id=f"{BENCHMARK_NAME}-figure",
+            struct_id=f"{BENCHMARK_NAME}-struct-placeholder",
+            structs=structs,
+            mode="struct",
+        )
+
+
+def get_app() -> Glucose205App:
+    """
+    Get Glucose205 benchmark app layout and callback registration.
+
+    Returns
+    -------
+    Glucose205App
+        Benchmark layout and callback registration.
+    """
+    return Glucose205App(
+        name=BENCHMARK_NAME,
+        description=(
+            "Performance in predicting relative conformer energies for "
+            "205 glucose structures. "
+            "Reference data from DLPNO-CCSD(T) calculations."
+        ),
+        docs_url=DOCS_URL,
+        table_path=DATA_PATH / "glucose205_metrics_table.json",
+        extra_components=[
+            Div(id=f"{BENCHMARK_NAME}-figure-placeholder"),
+            Div(id=f"{BENCHMARK_NAME}-struct-placeholder"),
+        ],
+    )
+
+
+if __name__ == "__main__":
+    full_app = Dash(__name__, assets_folder=DATA_PATH.parent.parent)
+    benchmark_app = get_app()
+    full_app.layout = benchmark_app.layout
+    benchmark_app.register_callbacks()
+    full_app.run(port=8064, debug=True)