This allows users to predict 3D structures of proteins, DNA, RNA, and small-molecule ligands with just a few lines of code. It is aimed at computational drug discovery teams and researchers requiring accurate structure predictions.
What happened
This model, developed by the OpenFold Consortium and the AlQuraishi Lab at Columbia University, enables users to predict the 3D structures of proteins, DNA, RNA, small-molecule ligands, and the complexes they form. With SageMaker JumpStart, users can deploy OpenFold3 into their own AWS account with minimal effort. The model runs in an AWS-maintained container on a managed Amazon SageMaker AI endpoint, handling request queuing and GPU warmup, and supporting autoscaling. Users can run several predictions in parallel on multi-GPU instances and supply their own multiple sequence alignments (MSAs) to improve prediction accuracy while keeping sequences private.
What to weigh
- OpenFold3 runs in an AWS-maintained container on a managed Amazon SageMaker AI endpoint.
- The endpoint runs with network isolation to keep sequences within the AWS account.
Source: Amazon Web Services