Skip to main content
Loading navigation
Back to challenges

Protein Functional Annotation Pipeline

Build a high-performance protein annotation agent using the Google ADK (Agent Development Kit). The agent's core responsibility is to reconcile unreviewed protein sequences with reviewed UniProtKB entries. You will deploy a sequence alignment service on Modal to handle heavy BLAST-like computations or HMMER searches. The Google ADK agent will orchestrate the flow: receiving an unreviewed sequence, triggering a Modal inference job for alignment, and then fetching metadata from UniProt (taxonomy, active sites, PTMs) to explain the functional confidence. The agent must handle the multimodal aspect of protein data (sequences and structural metadata) and return a detailed 'Evidence Reconciliation' report that identifies conserved domains and functional residues.

Frontier Science & ResearchHosted by Vera
Sign in free to start

What you are building

Orchestrate protein sequence alignment on Modal and functional metadata retrieval from UniProt using a Google ADK-powered agent.

How work is evaluated

Evaluation

Evaluation will check the agent's ability to correctly transfer annotations from a reviewed template to an unreviewed query sequence.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Modal Execution

Verifies that the alignment was actually performed on Modal serverless.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Annotation Accuracy

Percentage of correctly identified functional residues. • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Develop a multimodal protein analysis agent using Google ADK and Gemini

  • Deploy and scale bioinformatics sequence alignment workloads on Modal's serverless infrastructure

  • Reconcile reviewed (Swiss-Prot) and unreviewed (TrEMBL) UniProt records programmatically

  • Implement a structured annotation pipeline that maps PTMs and active sites from templates to query sequences

Resources

Dataset notes

Sample data for 1 tasks

Challenge setup

Evaluation will check the agent's ability to correctly transfer annotations from a reviewed template to an unreviewed query sequence.

Challenge input

Unreviewed FASTA sequence

Modal

Serverless cloud for AI workloads.

Google

Google AI model provider

Google ADK

Agent Development Kit for

Evaluated output

JSON mapping of residue positions to functions

Evaluation checks
  • Verifies that the alignment was actually performed on Modal serverless.
  • Percentage of correctly identified functional residues. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Annotation Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Environment
  • Modal · Optional
Action Space
  • Google · Required
  • Google ADK · Optional
Policy Serving
  • Modal · Optional
Training Infra
  • Modal · Optional

Evaluation contract

  • Modal Execution · Weight 1
  • Annotation Accuracy · Weight 1

Metrics

  • Annotation Accuracy · Target 0.95

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Unreviewed FASTA sequence

    Output: JSON mapping of residue positions to functions

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Protein Functional Annotation Pipeline