LIVE
OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston

Amazon Adds OpenFold3 Biomolecular Model to SageMaker JumpStart

🏢 Big Tech 2 min read 👁 6

Amazon Web Services has integrated the OpenFold3 biomolecular structure prediction model into Amazon SageMaker JumpStart, allowing researchers to deploy the tool using asynchronous inference.

Amazon Adds OpenFold3 Biomolecular Model to SageMaker JumpStart🏢Big Tech

Photo: AWS Machine Learning Blog

Key points

  • OpenFold3-preview is now available on Amazon SageMaker JumpStart.
  • The model predicts 3D structures for proteins, DNA, RNA, and ligands.
  • Deployments use SageMaker Asynchronous Inference to handle lengthy folding times and scale to zero.

Amazon Web Services has announced the availability of the OpenFold3-preview model on Amazon SageMaker JumpStart. Developed by the OpenFold Consortium and the AlQuraishi Lab at Columbia University, OpenFold3 is an open-source model designed to predict the three-dimensional structures of proteins, DNA, RNA, small-molecule ligands, and their complexes. Users can deploy the model into their AWS accounts with a few lines of code, utilizing network isolation to keep sequences secure within their private environments.

Computational drug discovery teams frequently rely on structure prediction for target identification, protein engineering, and virtual screening. However, running these models presents technical challenges due to the need for GPU infrastructure, specific CUDA and PyTorch stacks, and serving layers capable of handling prolonged computing tasks. SageMaker JumpStart addresses these hurdles by providing an AWS-maintained container on a managed endpoint that handles GPU warmup and request queuing.

Because structural folding can take several minutes depending on the size and complexity of molecular chains, OpenFold3 on JumpStart operates using SageMaker Asynchronous Inference rather than traditional real-time endpoints. This configuration queues incoming batches automatically and features a scale-to-zero capability to prevent idle billing costs. The model and its code are released under the Apache 2.0 license, permitting research organizations and pharmaceutical firms to inspect, fine-tune, and build upon the software.

Source AWS Machine Learning Blog — aws.amazon.com/blogs/machine-learning/openfold3-on-amazon-sagemaker-jum… ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.