Homepage » Amazon Web Services Solutions » Quantum Computing Exploration for Drug Discovery on Amazon Web Services
Quantum Computing Exploration for Drug Discovery on Amazon Web Services
Advance drug discovery research with quantum or classical computing
首页 » 亚马逊云科技解决方案 » 量子计算探索之药物发现
Quantum Computing Exploration for Drug Discovery on Amazon Web Services
Advance drug discovery research with quantum or classical computing
Overview
Quantum Computing Exploration for Drug Discovery on Amazon Web Services is an open-source solution that allows researchers and quantum computing advocates to design and run computational studies in the field of drug discovery. With this solution, you can access quantum computers via the Amazon Braket service. The Amazon Braket Hybrid Job feature allows you to use classical computing and quantum computing resources to evaluate experiment values such as cost, time, and performance. The solution comes with built-in sample code for certain drug discovery problems, such as molecular docking, protein folding, RNA folding, and retrosynthetic planning, to help you get started with quantum computing in the field.
Benefits
Amazon Braket Hybrid Job provides flexibility for you to use either quantum computing or classical computing resources, or both. You can evaluate and compare experimental values by testing the same problem with these resources.
The solution includes code for certain drug discovery use cases. You can learn and customize the code step-by-step in Jupyter Notebook.
The batch-run results are stored in Amazon S3 and you can find the visualization and comparison of different experiment results in Notebook.
Technical details
The diagram below presents the architecture you can automatically deploy using the solution's implementation guide and accompanying Amazon CloudFormation template.
This solution deploys a notebook instance to allow users to conduct notebook experiments. Notebooks come with use cases for different drug discovery problems such as molecule unfolding, RNA folding, and protein folding.
When used for the first time, the system will mirror and upload the dependent packages required for the experiment to Amazon ECR.
This program uses Amazon Braket Hybrid Job for experiments.
The experiment results are stored in Amazon S3.
Run multiple Hybrid Jobs in one experiment, and initiate the events in Amazon EventBridge when the Hybrid Job is completed.
Events initiated by Amazon EventBridge are sent to Lambda for analysis and summary.
Lambda sends a analysis report to Amazon SNS, and all subscribers who have subscribed to this topic will receive this report by email. This step is optional, and you can specify emails for subscription notifications when deploying the solution.
Return to SageMaker Notebook to run the code to analyze and display the experimental results.