Build a protein research copilot with Amazon Bedrock AgentCore

Source Domain: aws.amazon.com

Protein researchers face a time-consuming challenge: manually searching through thousands of peptide sequences to find structurally similar candidates is slow, error-prone, and requires deep domain expertise to interpret results. Building a protein research copilot can transform how researchers search for structurally similar peptides across large datasets — enabling natural language queries, automated embedding generation, and AI-powered result summarization in a single conversational interface.

This post shows you how to build a conversational protein research assistant that combines three capabilities:

Natural language query parsing to extract structured search parameters.
Vector similarity search over protein embeddings using a specialized language model.
AI-generated scientific summaries of search results.

The system uses the Strands Agents SDK to orchestrate three specialized tools within one agent, deploys to Amazon Bedrock AgentCore for production serving, and stores peptide embeddings in Amazon Aurora PostgreSQL-Compatible Edition with pgvector.

By the end of this post, you will have built an end-to-end agent application that demonstrates how to:

Parse natural language user input like “Find 10 similar peptides to the dengue virus peptide LPAIVREAI”, into structured tool parameters using the Strands Agents SDK’s tool-use pattern.
Deploy a custom ML model (ESM-C 300M) as Amazon SageMaker AI serverless endpoint with bundled weights for fast cold starts.
Combine vector similarity search (pgvector on Amazon Aurora PostgreSQL) with metadata filtering in a single query.
Orchestrate multiple specialized tools — including nested LLM agents — within a single Bedrock AgentCore runtime and generate scientific summaries of search results.