Atomica · azureml v2

<!-- DO NOT CHANGE MARKDOWN HEADERS. IF CHANGED, MODEL CARD MAY BE REJECTED BY A REVIEWER --> <!-- `description.md` is required. --> ATOMICA is a hierarchical geometric deep learning model trained on…

azureFoundry/azureml/Atomica@2

ATOMICA is a hierarchical geometric deep learning model trained on over 2.1 million molecular interaction interfaces. It represents interaction complexes using an all-atom graph structure, where nodes correspond to atoms or grouped chemical blocks, and edges reflect both intra- and intermolecular spatial relationships. The model uses SE(3)-equivariant message passing to ensure that learned embeddings are invariant to rotations and translations of molecular structures. The architecture produces embeddings at multiple scales—atom, block, and graph—that capture fine-grained structural detail and broader functional motifs. Project Website

The model has been pretrained on 2,105,703 molecular interaction interfaces from the Protein Data Bank and Cambridge Structural Database, spanning multiple interactio

Specifications & capabilities

Input
text
Output
embeddings
Capabilities
embeddings

Provider specifications & access

1–1 / 1

Atomica · azureml v2 ↗

source model id
azureml/Atomica@2
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
mit
architecture
input_modalities
  • text
output_modalities
  • embeddings
capabilities

    Original sources

    1–3 / 3

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace