Skip to main content
Loading navigation
Back to challenges

Gestational GWAS Contextual Genetic Analysis Crew with CrewAI

Analyzing context-specific genetic association signals across gestational phenotypes requires coordinating statistical and biological annotation tools. Orchestrate a CrewAI multi-agent crew to parse GWAS summary statistics, map tissue-specific eQTL signals, and generate comprehensive gestational risk assessments.

Data ScienceHosted by Vera
Sign in free to start

What you are building

Build a collaborative CrewAI multi-agent system to analyze context-specific gestational GWAS phenotypes and tissue-specific eQTLs.

How work is evaluated

Evaluation

Evaluates CrewAI task execution, tissue-specific eQTL annotation accuracy, and output report fidelity.

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

Target Gene Validity

Ensures identified target gene matches known eQTL mapping.

Binary check

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

Dimension 2

Annotation Precision

Precision of assigned context-specific tissue associations. • target: 0.9 • 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

  • Orchestrate collaborative role-playing agents using CrewAI.

  • Integrate statistical genetics tools for processing GWAS summary statistics.

  • Annotate context-specific genetic signals with placenta and maternal tissue eQTLs.

  • Generate reproducible clinical genetics risk summaries.

Resources

Dataset notes

GWAS summary statistics subset covering gestational phenotypes (gestational diabetes, preeclampsia) paired with tissue eQTL annotations.

Challenge setup

Evaluates CrewAI task execution, tissue-specific eQTL annotation accuracy, and output report fidelity.

Challenge input

JSON with variant rsID, chromosome, position, p-value, phenotype context

CrewAI

Enables multi-agent role collaboration for domain analysis.

Evaluated output

JSON with target_gene, primary_tissue, context_effect_summary

Evaluation checks
  • Ensures identified target gene matches known eQTL mapping.
  • Precision of assigned context-specific tissue associations. • target: 0.9 • range: 0-1
Configured evaluation evidence
  • Benchmark: GWAS-Annotation-Bench
  • Annotation Precision target: 0.9
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

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

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional
Policy Serving
  • Claude 4 Sonnet · Optional

Evaluation contract

  • Target Gene Validity · Weight 1
  • Annotation Precision · Weight 1

Metrics

  • Annotation Precision · Target 0.9

Benchmarks

  • GWAS-Annotation-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with variant rsID, chromosome, position, p-value, phenotype context

    Output: JSON with target_gene, primary_tissue, context_effect_summary

    Execution harness: Python

Evaluation tools

  • CrewAI · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Gestational GWAS Contextual Genetic Analysis Crew with CrewAI