Feature/geom qm9 dataset

[chrisiacovella]

Pull Request Summary

Add in the GEOM QM9 dataset.

Associated Issue(s)

• Add in GEOM QM9 dataset #424

Pull Request Checklist

• Issue(s) raised/addressed and linked
• Includes appropriate unit test(s)
• Appropriate docstring(s) added/updated
• Appropriate .rst doc file(s) added/updated
• PR is ready for review

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 89.69%. Comparing base (3f0e0eb) to head (09f1dff).

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Copilot]

Pull request overview

This PR adds support for the GEOM QM9 dataset (multi-conformer QM9 molecules) across the core dataset loader, curation tooling, and example notebooks, along with environment updates needed to run/curate the dataset.

Changes:

• Add GEOM QM9 dataset configuration (YAML + test TOML defaults) and register the dataset name in the core enums.
• Add GEOM QM9 curation config + curation implementation + a curation script to generate curated HDF5 artifacts.
• Update OpenMM/ASE example notebooks and adjust conda environments / ReadTheDocs OS setting.

Reviewed changes

Copilot reviewed 17 out of 17 changed files in this pull request and generated 13 comments.

Show a summary per file

File	Description
modelforge/tests/data/dataset_defaults/geom_qm9.toml	Adds test/default dataset parameters for GEOM_QM9.
modelforge/dataset/yaml_files/geom_qm9.yaml	Defines GEOM QM9 dataset versions + remote download metadata (urls/checksums).
modelforge/dataset/parameters.py	Registers GEOM_QM9 in DataSetName.
modelforge/dataset/init.py	Registers GEOM_QM9 in _ImplementedDatasets (affects tests + dataset fetching).
modelforge-openmm/modelforge/openmm/examples/simple_example_from_smiles.ipynb	New OpenMM PythonForce example notebook using a ModelForge checkpoint.
modelforge-curate/modelforge/curate/datasets/yaml_files/geom_qm9_curation.yaml	Adds raw GEOM-QM9 download metadata for curation.
modelforge-curate/modelforge/curate/datasets/scripts/curate_geom_qm9.py	Script to curate full + subset GEOM QM9 HDF5 files.
modelforge-curate/modelforge/curate/datasets/geom_qm9_curation.py	Implements GEOM QM9 curation pipeline from msgpack.
modelforge-curate/modelforge/curate/datasets/scripts/generate_tmqm_openff_selfenergy_by_charge_spin_v14.py	Adds a TMQM OpenFF self-energy correction / subset generation script.
modelforge-ase/modelforge/ase/examples/simple_example.ipynb	Updates ASE example notebook outputs/metadata.
modelforge-ase/modelforge/ase/calculator.py	Prints selected device during calculator init.
devtools/conda-envs/test_env.yaml	Adds msgpack/jax/flax/requests to test env dependencies.
devtools/conda-envs/test_env_mac.yaml	Adds msgpack/jax/flax/requests to mac test env dependencies.
devtools/conda-envs/run_env.yaml	New runtime-ish environment including msgpack/openmm/ase/jax.
devtools/conda-envs/env.yaml	Removes pip-pinned jax/flax/pytorch2jax.
devtools/conda-envs/env_modelforge_openmm.yaml	Updates OpenMM dependency spec (drops openmm-torch, pins openmm>=8.5.0).
.readthedocs.yaml	Updates RTD OS image to ubuntu-lts-latest.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.