GPUMA is a minimalist Python toolkit for facile and rapid high-throughput molecular geometry optimization based on the UMA/OMol25 machine-learning interatomic potential.
GPUMA is especially designed for batch optimizations of many structures (conformer ensembles, datasets) on GPU, ensuring efficient parallelization and maximum GPU utilization by leveraging the torch-sim library. It wraps Fairchem UMA models and torch-sim functionality to provide both a simple command-line interface (CLI) and a small but expressive Python API for single- and multi-structure optimizations.
If conformer sampling is desired, GPUMA can generate conformer ensembles on the fly from SMILES strings using the morfeus library. Alternative input formats are described in the CLI section below.
Feedback and improvements are always welcome!
pip install gpumaThis installs gpuma together with its core dependencies. Make sure you are using
Python 3.12 or newer.
⚠️ Required for UMA models:
To access the UMA models on Hugging Face, you must provide a token either via theHUGGINGFACE_TOKENenvironment variable or via the config (direct token string or path to a file containing the token).
# clone the repository
git clone https://github.com/niklashoelter/gpuma.git
cd gpuma
# install using (uv) pip
uv pip install .
# or, without uv:
pip install .Full documentation is available at https://niklashoelter.github.io/gpuma/.
For local browsing of the Markdown sources, see in particular:
- docs/index.md – overview and getting started
- docs/install.md – installation details
- docs/cli.md – CLI options and input formats
- docs/config.md – configuration file schema and examples
- docs/reference.md – API and configuration reference
Using a configuration file is highly recommended for reproducibility and ease of use.
Also check the examples/ folder in the repository for sample config files and usage examples:
- examples/config.json – minimal example configuration
- examples/example_single_optimization.py – single-structure optimization from Python
- examples/example_ensemble_optimization.py – ensemble/multi-structure optimization from Python
The CLI is provided via the command gpuma. For best results, create a
config file (JSON or YAML) and reference it in all CLI calls (see examples/config.json for a minimal example).
Optimize all XYZ files in a directory (each file containing a single structure):
gpuma optimize --config examples/config.json --xyz-dir examples/example_input_xyzs/multi_xyz_dir/Optimize multiple structures contained in a single multi-XYZ file:
gpuma optimize --config examples/config.json --xyz examples/example_input_xyzs/multi_xyz_file.xyzRefer to the CLI documentation for details on configuration options, supported input formats (SMILES, XYZ, directories, multi-XYZ files), and additional CLI examples.
A minimalistic and high-level Python API is provided for easy integration into custom scripts and workflows.
For example usage, see:
Please refer to the documentation and examples for detailed usage examples and API reference.
When a run is started from SMILES, an RDKit force field (via the morfeus library) is used to generate an initial structure. Spin is not taken into account during this step, so the initial estimated geometries can be incorrect. When the UMA/Omol25 models are applied subsequently, the structure can sometimes be optimized to a maximum rather than a minimum because the model is not provided with Hessian matrices. This behavior only affects runs originating from SMILES; it does not occur with better starting geometries (e.g., when starting from XYZ files).
- Missing libraries: install optional dependencies like
pyyamlif you use YAML configs. - Fairchem/UMA: ensure network access for model downloads and optionally set or provide
huggingface_token(e.g., via a token file) to access the UMA model family.
MIT License (see LICENSE)