by Meta AI
FAIR Chemistry provides open datasets and machine-learning models for molecules, materials and catalysts. Its UMA model covers several chemistry domains in one pretrained model.
Web appFree
Step 1: Install the package with pip install fairchem-core.
Step 2: Request access to the UMA checkpoints.
Step 3: Build or read your structure as an ASE Atoms object.
Step 4: Load a pretrained UMA model and attach a FAIRChemCalculator with the task that matches your system.
Step 5: Request energies and forces from ASE, or run a relaxation or simulation.
Choose by scientific domain, matching the task to your chemistry and its level of theory. For example, omol is used for molecules and omat for inorganic crystals.
With the omol task you set the molecule's total charge and spin multiplicity in atoms.info before attaching the calculator.
Yes. The documentation links an interactive UMA playground for exploring atomistic simulations in the browser.
Yes. The omat task predicts stress as well as energy and forces, so ASE can relax both the atoms and the unit cell.
CellposeGeneralist deep-learning cell and nucleus segmentation tool for microscopy images across diverse biological samples
CDVAEGenerative deep-learning model for creating stable crystal structures with targeted materials properties
napari AI ecosystemnapari is a fast, interactive viewer for multi-dimensional images in Python. It displays arrays, overlays points, polygons and segmentations, and lets you annotate and edit them.