Challenge

Autonomous Oncology Triage: Multimodal Variant Interpretation with Google ADK

With oncology businesses like Guardant Health and Tempus AI reporting massive revenue growth, the bottleneck in precision medicine has shifted from sequencing to data interpretation. Germany's new Precision Medicine Pilot emphasizes robust data infrastructure to handle this surge. In this challenge, you will use the Google Agent Development Kit (ADK) and the o3-mini model to build an autonomous lab agent capable of triaging genomic variants and matching them to clinical trials. Your agent must handle multimodal inputs, including raw VCF (Variant Call Format) files, pathology PDFs, and structured EHR data. Using Google ADK’s integration with Vertex AI, you will implement a 'Reasoning-and-Acting' (ReAct) loop that queries the COSMIC database and clinicaltrials.gov. The goal is to automate the extraction of 'Actionable Alterations' and flag cases where high-fidelity WGS (like PacBio HiFi) is required for resolving ambiguous structural variants in noncoding regions, as highlighted in recent Nature Genetics research.

Frontier Science & ResearchHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

With oncology businesses like Guardant Health and Tempus AI reporting massive revenue growth, the bottleneck in precision medicine has shifted from sequencing to data interpretation. Germany's new Precision Medicine Pilot emphasizes robust data infrastructure to handle this surge. In this challenge, you will use the Google Agent Development Kit (ADK) and the o3-mini model to build an autonomous lab agent capable of triaging genomic variants and matching them to clinical trials. Your agent must handle multimodal inputs, including raw VCF (Variant Call Format) files, pathology PDFs, and structured EHR data. Using Google ADK’s integration with Vertex AI, you will implement a 'Reasoning-and-Acting' (ReAct) loop that queries the COSMIC database and clinicaltrials.gov. The goal is to automate the extraction of 'Actionable Alterations' and flag cases where high-fidelity WGS (like PacBio HiFi) is required for resolving ambiguous structural variants in noncoding regions, as highlighted in recent Nature Genetics research.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

False Positive Check

Ensure Benign variants are NOT flagged as 'Actionable'.

Binary check

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

Dimension 2

Precision at Trial Matching

Percentage of suggested trials where patient meets 100% of inclusion criteria. • 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

What you should walk away with

  • Master Google ADK agent initialization with Gemini and o3 model configurations

  • Implement multimodal tool-use to extract insights from histopathology images and genomic reports simultaneously

  • Design a recursive reasoning loop in o3 to evaluate 'Variant of Unknown Significance' (VUS) status

  • Build an autonomous tool for querying the GenomeWeb/NCBI APIs to fetch the latest research on BRCA1/2 mutations

  • Orchestrate a 'Human-in-the-loop' checkpoint using Vertex AI's evaluation framework for expert oncologist review

  • Optimize data sovereignty by implementing local-first processing for PII (Personally Identifiable Information) before cloud inference

  • Integrate PacBio HiFi WGS metadata into the triage logic to recommend high-resolution sequencing for complex inversions

  • Deploy a Streamlit-based oncology dashboard that visualizes the agent's reasoning trace and evidence links

How this agent runs

The evaluation measures the agent's ability to identify actionable variants and provide the correct clinical trial matches.

Preview configuration

Challenge input

VCF file + Clinical History PDF

Google ADK

Provides seamless integration with multimodal Gemini models.

o3-mini

High-density reasoning for complex genomic triage logic.

Biopython

Industry standard for biological data manipulation.

Evaluated output

Trial Eligibility Report (JSON)

Checks for
  • Ensure Benign variants are NOT flagged as 'Actionable'.
  • Percentage of suggested trials where patient meets 100% of inclusion criteria. • target: 0.95 • range: 0-1
Proof of success
  • Benchmark: Clinvit-QA
  • Precision At Trial Matching target: 0.95
  • Protected reference cases support private evaluation
Runtime evidence
  • Docker execution harness
  • Docker sandbox
View technical recipe

Configured tools

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

Evaluation contract

  • False Positive Check · Weight 1
  • Precision at Trial Matching · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Run this agent on your dataset and AI stack

Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.

Scope a managed run
Start from your terminal
$npx -y @versalist/cli start autonomous-oncology-triage-multimodal-variant-interpretation-with-google-adk

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Frequently Asked Questions about Autonomous Oncology Triage: Multimodal Variant Interpretation with Google ADK