Skip to main content
Loading navigation
Back to challenges

Pediatric Rapid WGS Clinical Decision Multi-Agent Network via AutoGen

Pediatric whole-genome sequencing requires rapid variant interpretation under stringent operational latencies. Deploy an AutoGen multi-agent clinical consensus workflow on decentralized Akash Network infrastructure to evaluate pediatric genomic variants and generate standardized diagnostic FHIR reports within targeted turnaround limits.

Data ScienceHosted by Vera
Sign in free to start

What you are building

Build a multi-agent system using AutoGen hosted on Akash Network compute to process pediatric rapid whole-genome sequencing datasets.

How work is evaluated

Evaluation

Evaluates multi-agent AutoGen consensus speed, HPO phenotype matching, and FHIR report output validity.

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

FHIR Schema Compliance

Validates that DiagnosticReport meets FHIR R4 schema requirements.

Binary check

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

Dimension 2

Phenotype Match Rate

Accuracy of correlating phenotypic HPO terms with causative genes. • 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

  • Design multi-agent role delegation using Microsoft AutoGen for clinical genetics.

  • Deploy scalable containerized compute workloads onto Akash Network decentralized cloud.

  • Automate phenotype (HPO terms) to genotype cross-referencing.

  • Export structured diagnostic recommendations into HL7 FHIR DiagnosticReport resources.

Resources

Dataset notes

Pediatric clinical cases dataset linking HPO terms, candidate genetic variants, and expert-validated primary diagnoses.

Challenge setup

Evaluates multi-agent AutoGen consensus speed, HPO phenotype matching, and FHIR report output validity.

Challenge input

JSON containing patient HPO terms and candidate genomic variants

AutoGen

Enables multi-agent role playing for consensus diagnostics.

Akash Network

Provides decentralized cloud infrastructure for fast execution.

Evaluated output

JSON FHIR DiagnosticReport containing primary diagnosis and candidate variant

Evaluation checks
  • Validates that DiagnosticReport meets FHIR R4 schema requirements.
  • Accuracy of correlating phenotypic HPO terms with causative genes. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: PediatricGenomics-Bench
  • Phenotype Match Rate target: 95%
  • 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
  • AutoGen · Required
  • Akash Network · Optional
  • Zed · Optional

Evaluation contract

  • FHIR Schema Compliance · Weight 1
  • Phenotype Match Rate · Weight 1

Metrics

  • Phenotype Match Rate · Target 0.95

Benchmarks

  • PediatricGenomics-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing patient HPO terms and candidate genomic variants

    Output: JSON FHIR DiagnosticReport containing primary diagnosis and candidate variant

    Execution harness: Python

Evaluation tools

  • AutoGen · Multi-Agent Framework
  • Akash Network · Inference Runtime Host

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Pediatric Rapid WGS Clinical Decision Multi-Agent Network via AutoGen