Skip to main content
Back to challenges
Challenge

Gestational GWAS Phenotype Risk Evaluator using Google ADK and Gemini

Context-specific genetic effects during pregnancy require dynamic interpretation of GWAS locus variations across different gestational stages. Build a multimodal agent using Google ADK and Gemini to parse longitudinal EHR and genomic records, producing gestational risk profiles with an F1 score above 0.88.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Construct a context-specific gestational GWAS interpretation agent using Google ADK and Gemini multimodal processing.

Delivery guide

How work is evaluated

Evaluation

Evaluates gestational risk classification F1 score across longitudinal trimester data.

Datasets

Challenge datasets

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

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

score_range_check

Verifies risk_score is between 0.0 and 1.0.

Binary check

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

Dimension 2

f1_score

Harmonic mean of precision and recall for gestational risk prediction. • target: 0.88 • 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

  • Deploy agents using Google Agent Development Kit (ADK).

  • Integrate Gemini models for multimodal medical record and genomic plot parsing.

  • Evaluate context-specific genetic effects across gestational trimesters.

  • Achieve high F1 score on maternal risk phenotype stratification.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic dataset of longitudinal gestational EHR profiles matched with context-specific GWAS locus genotypes.

Challenge setup

Evaluates gestational risk classification F1 score across longitudinal trimester data.

Challenge input

JSON containing trimester, locus_id, risk_allele_dosage, and clinical history.

Google ADK

Google Agent Development Kit for building Gemini-powered agent applications.

Evaluated output

JSON with predicted_condition and risk_score.

Evaluation checks
  • Verifies risk_score is between 0.0 and 1.0.
  • Harmonic mean of precision and recall for gestational risk prediction. • target: 0.88 • range: 0-1
Configured evaluation evidence
  • Benchmark: Gestational Genomic Risk Prediction Benchmark
  • F1 Score target: 0.88
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Google · Required
  • Google Gemini · Optional
  • Google ADK · Optional

Evaluation contract

  • score_range_check · Weight 1
  • f1_score · Weight 1

Metrics

  • f1_score · Target 0.88

Benchmarks

  • Gestational Genomic Risk Prediction Benchmark
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing trimester, locus_id, risk_allele_dosage, and clinical history.

    Output: JSON with predicted_condition and risk_score.

    Execution harness: Python

Evaluation tools

  • Google ADK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Gestational GWAS Phenotype Risk Evaluator using Google ADK and Gemini