Leveraging generative AI to accelerate public health genomics data standardization

The article discusses AI Genomics Schema Harmonizer, a generative AI solution developed by the Digital Transformation Hub at Cal Poly to streamline genomic data standardization for public health laboratories.

• Addresses challenges in genomic data interoperability and standardization
• Reduces manual data preparation time from 2-4 hours per submission to minutes
• Uses Amazon Bedrock and Claude Sonnet 3.5 v2 foundation model for processing
• Automatically aligns laboratory-specific terms with NCBI BioSample definitions
• Improves data submission accuracy by eliminating manual errors
• Developed by Cal Poly students in collaboration with public health laboratories

The solution demonstrates how generative AI can solve complex data standardization challenges in public health genomics, potentially saving hundreds of hours of manual work annually.