DeepMind released AlphaFold 3 inference codebase

DeepMind released AlphaFold 3 inference codebase

Wohoo! DeepMind released AlphaFold 3 inference codebase, model weights and an on-demand server! AlphaFold can generate highly accurate biomolecular structure predictions containing proteins, DNA, RNA, ligands, ions, and also model chemical modifications for proteins and nucleic acids in one platform.

DeepMind released AlphaFold 3 inference codebase

The model weights require you to fill a Google Form and wait for 3-4 business days, but hoping @GoogleDeepMind brings the model weights over to the Hub.

You can also check out the AlphaFold Server for on-demand inference here.

How does the AlphaFold Server work?

The AlphaFold Server is an online platform designed to generate highly accurate predictions of biomolecular structures, including proteins, DNA, RNA, ligands, ions, and chemical modifications for proteins and nucleic acids, all within a single system. This service is powered by the latest AlphaFold 3 model.

How does the AlphaFold Server work

Take a look at some examples

Terms of Use and Attribution

The AlphaFold Server is available for non-commercial purposes only, in accordance with its Terms of Service. Its outputs cannot be used in docking or screening applications, nor can they be utilized to train machine learning models or related technologies for biomolecular structure prediction similar to the AlphaFold Server.

Read related articles in our Blog:


Posted

in

by

Tags: