Using generative AI and Amazon Bedrock to generate SPARQL queries to discover protein functional information with UniProtKB and Amazon Neptune
Database Blog
This article discusses using generative AI and Amazon Bedrock to transform natural language questions into SPARQL queries for exploring protein functional information in the UniProtKB database using Amazon Neptune.
- Developed an approach to generate SPARQL queries from natural language questions about proteins
- Used Amazon Bedrock with Anthropic's Claude 3.5 Sonnet model to generate queries
- Implemented an agentic workflow with three steps: query generation, critique, and refinement
- Achieved 61% accuracy in generating correct SPARQL queries for protein-related questions
- Utilized few-shot examples, natural language instructions, and an iterative query improvement process
The solution demonstrates how generative AI can help scientists without technical query language expertise to explore complex biological databases more easily.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2025
2025
2025
2024
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.