Midlife Microglial Trajectory Analyzer with Pydantic AI
NIH research demonstrates that brain immunity undergoes a major midlife overhaul, driven by distinct transcriptomic shifts in microglial populations. In this challenge, developers will construct a type-safe single-cell RNA velocity and trajectory interpretation agent using Pydantic AI. The system will ingest microglial cluster profile data, classify midlife neuroinflammatory transition markers, and output structured inflammatory state indices.
What you are building
The core problem, expected build, and operating context for this challenge.
Construct a type-safe microglial trajectory analysis pipeline using Pydantic AI to characterize midlife brain immune shifts.
How work is evaluated
Evaluates state classification accuracy for microglial single-cell expression profiles.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
pydantic_validation
Model outputs parse into Pydantic target schema without errors
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
state_classification_accuracy
Accuracy of classified microglial activation state against expert labeled dataset • target: 0.88 • 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
Define strict Pydantic schemas for microglial gene expression profiling
Execute Python bioinformatic tools for trajectory scoring within Pydantic AI dependencies
Classify midlife neuroinflammatory state transitions (homeostatic vs DAM/midlife-reactive)
Provide validated diagnostic reports on microglial age-dependent activation
Reference links and supporting material
Single-cell RNA-seq microglial count matrices across rodent and human lifespan datasets (months 2 to 24).
Challenge setup
Evaluates state classification accuracy for microglial single-cell expression profiles.
Challenge input
JSON containing key gene marker levels (CD11b, CLEC7A, APOE, CX3CR1)
Pydantic AI
Mandatory Pydantic AI framework
Evaluated output
JSON containing microglial_state (string) and activation_index (float 0-1)
- Model outputs parse into Pydantic target schema without errors
- Accuracy of classified microglial activation state against expert labeled dataset • target: 0.88 • range: 0-1
- Benchmark: ImmunoCell-Bench
- State Classification Accuracy target: 0.88
- 1 public reference case
- 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
- Pydantic AI · Required
- Google Cloud · Optional
- DeepSeek · Optional
- Pydantic AI · Required
Evaluation contract
- pydantic_validation · Weight 1
- state_classification_accuracy · Weight 1
Metrics
- state_classification_accuracy · Target 0.88
Benchmarks
- ImmunoCell-Bench
- biotech
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing key gene marker levels (CD11b, CLEC7A, APOE, CX3CR1)
Output: JSON containing microglial_state (string) and activation_index (float 0-1)
Execution harness: Python
Evaluation tools
- Pydantic AI · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.