Skip to main content
Back to challenges
Challenge

Multi-Omic Network Biology Collaboration System with CrewAI

Deciphering complex biological networks requires specialized collaborative agents for genomics, proteomics, and graph neural networks. You will construct a CrewAI multi-agent team that analyzes GPU-accelerated biological network graphs, producing validated therapeutic target leads with 88% cross-modality agreement.

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.

Orchestrate a multi-agent network with CrewAI to integrate genomic and proteomic knowledge graphs for drug target discovery.

Delivery guide

How work is evaluated

Evaluation

Evaluates multi-agent target validation consensus and gene interaction pathway analysis.

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

target_consensus_validity

Ensure identified target is a known upstream/downstream effector in pathway

Binary check

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

Dimension 2

cross_modality_agreement

Agreement percentage between genomic and proteomic agent findings • 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

  • Build role-playing multi-agent systems using CrewAI framework

  • Assign specialized tasks across Genomics Analyst, Proteomics Specialist, and Target Lead Crew members

  • Process graph-based biological interaction networks to prioritize drug candidates

Resources and assets

Reference links and supporting material

Dataset notes

Multi-omic target interaction graph dataset covering 2,000 biological nodes and 15,000 directed edges.

Challenge setup

Evaluates multi-agent target validation consensus and gene interaction pathway analysis.

Challenge input

JSON object with query_gene and background_pathway

CrewAI

Mandatory CrewAI role-playing framework.

Evaluated output

JSON object with consensus_target string and confidence_score float

Evaluation checks
  • Ensure identified target is a known upstream/downstream effector in pathway
  • Agreement percentage between genomic and proteomic agent findings • target: 0.88 • range: 0-1
Configured evaluation evidence
  • Benchmark: TargetDiscovery-Bench
  • Cross Modality Agreement 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
  • CrewAI · Required
  • crewAI · Optional
  • Zed · Optional

Evaluation contract

  • target_consensus_validity · Weight 1
  • cross_modality_agreement · Weight 1

Metrics

  • cross_modality_agreement · Target 0.88

Benchmarks

  • TargetDiscovery-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with query_gene and background_pathway

    Output: JSON object with consensus_target string and confidence_score float

    Execution harness: Python

Evaluation tools

  • CrewAI · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Multi-Omic Network Biology Collaboration System with CrewAI