EvoDiff · azureml v1 ↗
- source model id
- azureml/EvoDiff@1
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- license
- MIT
- max output tokens
- 4096
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
# Key capabilities ## About this model EvoDiff can unconditionally sample diverse structurally-plausible proteins, generate intrinsically disordered regions, and scaffold structural motifs using only…
azureFoundry/azureml/EvoDiff@1
EvoDiff can unconditionally sample diverse structurally-plausible proteins, generate intrinsically disordered regions, and scaffold structural motifs using only sequence information, challenging a paradigm in structure-based protein design.
Below are several use cases for EvoDiff. Currently, Azure AI Foundry supports unconditional or conditional design with EvoDiff-Seq. To use EvoDiff-MSA, we point you to our github repository for more information.
See Responsible AI for additional considerations for responsible use.
Below are several use cases for EvoDiff. Currently, Azure AI Foundry supports unconditional or conditional design with EvoDiff-Seq. To use EvoDiff-MSA, we point you to our github repository for more information.
This model is intended for use on protein sequences. It is not meant for natural language or other biological sequences, such as DNA sequences. This model will not generate sequences that are not proteins. This includes cases such as trying to generate other biological sequences, such as DNA sequences, or natural language. In other words, the model will perform best on data within the data distribution, which includes protein sequences and multiple sequence alignments (MSAs).
Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.
We trained all EvoDiff sequence models on 42M sequences from UniRef50 using a dilated convolutional neural network architecture introduced in the CARP protein masked language model. We trained 38M-parameter and 640M-parameter versions for each forward corruption scheme and for left-to-right autoregressive (LRAR) decoding.
The provider has not supplied this information.
32GB NVIDIA V100 GPUsThe provider has not supplied this information.
The provider has not supplied this information.
The provider has not supplied this information.
The provider has not supplied this information.
We investigated two types of forward processes for diffusion over discrete data modalities to determine which would be most effective. In order-agnostic autoregressive diffusion OADM, one amino acid is converted to a special mask token at each step in the forward process. After steps, where is the length of the sequence, the entire sequence is masked. We additionally designed discrete denoising diffusion probabilistic models D3PM for protein sequences. In EvoDiff-D3PM, the forward process corrupts sequences by sampling mutations according to a transition matrix, such that after steps the sequence is indistinguishable from a uniform sample over the amino acids. In the reverse process for both, a neural network model is trained to undo the previous corruption. The trained model can then generate new sequences starting from sequences of masked tokens or of uniformly-sampled amino acids for EvoDiff-OADM or EvoDiff-D3PM, respectively.
The provider has not supplied this information.
The provider has not supplied this information.
For all other models in the EvoDiff suite, please see our github repository. We provide all generated sequences on the EvoDiff Zenodo.
We obtain sequences from the Uniref50 dataset, which contains approximately 42 million protein sequences. The Multiple Sequence Alignments (MSAs) are from the OpenFold dataset, which contains 401,381 MSAs for 140,000 unique Protein Data Bank (PDB) chains and 16,000,000 UniClust30 clusters. The intrinsically disordered regions (IDR) data was obtained from the Reverse Homology GitHub. For the scaffolding structural motif benchmark, we provide pdb and fasta files used for conditionally generating sequences in the examples/scaffolding-pdbs folder. We also provide pdb files used for conditionally generating MSAs in the examples/scaffolding-msas folder.
The provider has not supplied this information.
Start using EvoDiff on Azure AI Foundry with this Jupyter Notebook.
For full details, please refer to our preprint.
1–1 / 1
1–1 / 1
1–3 / 3
Microsoft Foundry · Model page ↗
1–1 / 1
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.