Python
pip install esm@git+https://github.com/Biohub/esm.git@mainESM3
ESM3 is a multimodal generative protein language model that jointly models sequence, structure, and function. It enables controllable generation of novel proteins by conditioning on any combination of these modalities.
Protein Language Model•Version 2024-06
Get Started
Quickstart Guide
1
Install the esm Python package
2
Create an API key
3
Connect to the Biohub Platform API
Python
from esm.sdk.forge import ESM3ForgeInferenceClient
client = ESM3ForgeInferenceClient(model="esm3-medium-2024-08", url="https://biohub.ai", token="<your API token>")4
Run your inference
Model Tutorials
Explore All TutorialsUnderstanding the ESMProtein class
Get familiar with how ESM3 represents proteins.
Generating proteins with ESM3
Learn how to scaffold a functional motif, edit secondary structure, and guide design using solvent exposure.
Designing a novel GFP with ESM3
Walk through the exact prompting strategy used to design a novel fluorescent protein with no close natural relatives.
Guided generation with ESM3
Add scoring functions into the generation process, such as structural quality, sequence constraints, or other properties.
Model Details
Model Card
Version
2024-03
Architecture
Transformer
Supported Modalities
Sequence, structure, function
Training Data
3,000+ sequences and 700,000+ unique training tokens
Intended Use
ESM3 is designed for prompt-driven generation of sequences and structures based on inputs of motifs, partial coordinates, secondary structure (SS) constraints, or function keywords.
Limitations & Risks
Novel sequence generation can lead to designs with hazardous properties. Model proposals may not be physically realizable; pLDDT/pTM are helpful but imperfect. Not intended for clinical or therapeutic applications without further validation.
This model is released under the MIT License.