OpenFold3 now available on Amazon SageMaker JumpStart
In short: Amazon has added OpenFold3-preview to SageMaker JumpStart, allowing users to deploy models for predicting 3D structures of proteins, DNA, RNA, and ligands. The implementation utilizes asynchronous inference endpoints to handle long-running predictions while supporting cost-efficient autoscaling and scale-to-zero capabilities.
This summary was generated automatically by AI from AWS Machine Learning's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.
What changed?
- 1Added OpenFold3 (0.4.1) as a deployable model in SageMaker JumpStart.
- 2Support for asynchronous inference to manage long-duration compute tasks.
- 3Integration with ml.g6 instance types for GPU-accelerated folding.
- 4Capability to process protein complexes, nucleic acids, and small-molecule ligands.
Why it matters
This release simplifies the infrastructure overhead for drug discovery teams by offloading the management of GPU stacks, request queuing, and model warm-up to AWS. It enables high-throughput batch processing of biomolecular sequences without maintaining custom infrastructure.
Sources
- AWS Machine LearningOfficialPrimary sourceOriginal article →„OpenFold3 on Amazon SageMaker JumpStart: Predict biomolecular structures“13 Nov 2026, 23:53
- Published by source
- 13 Nov 2026, 23:53
- Found by our system
- 14 Nov 2026, 00:20
- Summary generated
- 14 Nov 2026, 00:21
This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy