Add 37Conf8 benchmark (#233)

Co-authored-by: Domantas Kuryla <dk584@icepc16>
Co-authored-by: joehart2001 <[email protected]>
Co-authored-by: ElliottKasoar <[email protected]>
Co-authored-by: ElliottKasoar <[email protected]>

Author: 4 people

ml_peg/analysis/conformers/37CONF8/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: DLPNO-CCSD(T)/cc-pVTZ

ml_peg/analysis/conformers/37Conf8/analyse_37Conf8.py

@@ -0,0 +1,146 @@
+"""
+Analyse 37Conf8 conformer energy benchmark.
+
+10.1002/cphc.201801063.
+"""
+
+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" / "37Conf8" / "outputs"
+OUT_PATH = APP_ROOT / "data" / "conformers" / "37Conf8"
+
+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_37conf8.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 barrier heights for all systems.
+
+    Returns
+    -------
+    dict[str, list]
+        Dictionary of all reference and predicted 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 / "37conf8_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_37conf8(metrics: dict[str, dict]) -> None:
+    """
+    Run 37Conf8 barriers test.
+
+    Parameters
+    ----------
+    metrics
+        All new benchmark metric names and dictionary of values for each model.
+    """
+    return

ml_peg/app/conformers/37Conf8/app_37Conf8.py

@@ -0,0 +1,91 @@
+"""Run 37Conf8 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 = "37Conf8"
+DOCS_URL = (
+    "https://ddmms.github.io/ml-peg/user_guide/benchmarks/conformers.html#37conf8"
+)
+DATA_PATH = APP_ROOT / "data" / "conformers" / "37Conf8"
+
+
+class ThirtySevenConf8App(BaseApp):
+    """37Conf8 benchmark app layout and callbacks."""
+
+    def register_callbacks(self) -> None:
+        """Register callbacks to app."""
+        scatter = read_plot(
+            DATA_PATH / "figure_37conf8.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/37Conf8/{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() -> ThirtySevenConf8App:
+    """
+    Get 37Conf8 benchmark app layout and callback registration.
+
+    Returns
+    -------
+    ThirtySevenCONF8App
+        Benchmark layout and callback registration.
+    """
+    return ThirtySevenConf8App(
+        name=BENCHMARK_NAME,
+        description=(
+            "Performance in predicting relative conformer energies "
+            "of 37 organic molecules representing pharmaceuticals, drugs, catalysts, "
+            "synthetic precursors, and industry-related chemicals (37 neutral "
+            "molecules, 8 conformers each). "
+            "Reference data from DLPNO-CCSD(T) calculations."
+        ),
+        docs_url=DOCS_URL,
+        table_path=DATA_PATH / "37conf8_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=8062, debug=True)

ml_peg/app/conformers/conformers.yml

@@ -0,0 +1,2 @@
+title: Conformers
+description:

ml_peg/calcs/conformers/37Conf8/calc_37Conf8.py

@@ -0,0 +1,79 @@
+"""
+Compute the 37Conf8 dataset for molecular conformer relative energies.
+
+10.1002/cphc.201801063.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from ase import units
+from ase.io import read, write
+import pandas as pd
+import pytest
+from tqdm import tqdm
+
+from ml_peg.calcs.utils.utils import download_s3_data
+from ml_peg.models.get_models import load_models
+from ml_peg.models.models import current_models
+
+MODELS = load_models(current_models)
+
+KCAL_TO_EV = units.kcal / units.mol
+
+OUT_PATH = Path(__file__).parent / "outputs"
+
+
+@pytest.mark.parametrize("mlip", MODELS.items())
+def test_37conf8_conformer_energies(mlip: tuple[str, Any]) -> None:
+    """
+    Benchmark the 37Conf8 dataset.
+
+    Parameters
+    ----------
+    mlip
+        Name of model use and model to get calculator.
+    """
+    model_name, model = mlip
+    calc = model.get_calculator()
+
+    data_path = (
+        download_s3_data(
+            filename="37CONF8.zip",
+            key="inputs/conformers/37Conf8/37Conf8.zip",
+        )
+        / "37CONF8"
+    )
+
+    df = pd.read_excel(
+        data_path / "37Conf8_data.xlsx", sheet_name="Rel_Energy_SP", header=2
+    )
+    calc = model.get_calculator()
+    # Add D3 calculator for this test
+    calc = model.add_d3_calculator(calc)
+
+    write_dir = OUT_PATH / model_name
+    write_dir.mkdir(parents=True, exist_ok=True)
+
+    for i in tqdm(range(len(df) - 3)):
+        molecule_name = df.iloc[i][0].strip()
+        conf_id = int(df.iloc[i][1])
+        label = f"{molecule_name}_{conf_id}"
+        if conf_id == 1:
+            zero_conf = read(data_path / "PBEPBE-D3" / f"{label}_PBEPBE-D3.xyz")
+            zero_conf.info["charge"] = 0
+            zero_conf.info["spin"] = 1
+            zero_conf.calc = calc
+            e_model_zero_conf = zero_conf.get_potential_energy()
+        else:
+            atoms = read(data_path / "PBEPBE-D3" / f"{label}_PBEPBE-D3.xyz")
+            atoms.info["charge"] = 0
+            atoms.info["spin"] = 1
+            atoms.calc = calc
+            atoms.info["model_rel_energy"] = (
+                atoms.get_potential_energy() - e_model_zero_conf
+            )
+            atoms.info["ref_energy"] = float(df.iloc[i][2]) * KCAL_TO_EV
+            write(write_dir / f"{label}.xyz", atoms)