Build a Pydantic AI Type-Safe Pan-Cancer Allele Dosage Analysis Agent
Somatic copy number alterations and mutant gene dosage dictate prognosis and metastatic tropism across thousands of cancer samples. Build a type-safe agent using Pydantic AI that parses pan-cancer genomic profiling datasets, validates mutant dosage ratios, and outputs organ-specific tropism risk scores.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a Pydantic AI agent with strict type validation to calculate gene mutant dosage and predict metastatic tropism.
How work is evaluated
Evaluates Pydantic AI agent calculations of allele dosage and metastatic organ predictions.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
mutant_dosage_math_check
Verifies that mutant dosage formula calculation (copy_number * vaf) is mathematically accurate.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
tropism_prediction_accuracy
Accuracy of organ-specific metastatic predictions matching gold standard clinical trial records. • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Construct type-safe AI agents with Pydantic AI and Pydantic validation models
Calculate mutant allele dosage ratios from somatic copy number and VAF data
Predict organ-specific metastatic tropism (e.g., liver, brain, bone) based on mutation dosage
Ensure end-to-end type safety and validated structured outputs for clinical reporting
Reference links and supporting material
Dataset of 50 patient genomic profiles detailing copy number amplification, VAF, primary tumor origin, and validated metastatic sites.
How this agent runs
Evaluates Pydantic AI agent calculations of allele dosage and metastatic organ predictions.
Challenge input
JSON containing gene (string), copy_number (int), vaf (float), and primary_site (string).
Pydantic AI
Type-safe Python framework for structured output validation.
Evaluated output
JSON containing mutant_dosage (float), predicted_tropism (list of strings), and risk_category (string).
- Verifies that mutant dosage formula calculation (copy_number * vaf) is mathematically accurate.
- Accuracy of organ-specific metastatic predictions matching gold standard clinical trial records. • target:...
- Benchmark: Pan-Cancer Tropism Prediction Benchmark
- Tropism Prediction Accuracy target: 0.9
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Pydantic AI · Required
- Meta · Optional
- Guardrails AI · Optional
- Guardrails AI · Optional
- Pydantic AI · Required
Evaluation contract
- mutant_dosage_math_check · Weight 1
- tropism_prediction_accuracy · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.