Apply for community grant: Academic project (gpu)
MISATO is a dataset of protein-ligand dynamics that was published recently Nature computational science. With the publication of the preprint we started a community project of researchers and enthusiasts to develop sparkling advancements in AI for drug discovery.
With this space we want to combine MISATO with the recently published ESM3 model. We found a very efficient way of sampling conformational states of proteins using a adaptation of ESM3 that we would like to make available to everyone via this demo. Apart from inference we will visualize the conformational states starting from a 3D structure of a protein.
Hope you like it : with your community grant we can move to a gradio space (from docker) and actually provide inference 🚀
Hi @TillCyrill , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.