Challenge

Autism PPI Network Perturbation Analysis Agent with Google ADK

Understanding how autism mutations disrupt protein-protein interaction networks requires multi-omic graph analysis. Build a Google ADK agent hosted on Baseten to analyze PPI perturbation scores and report network centrality changes across thousands of neurodevelopmental gene variants.

Data ScienceHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Develop a protein interaction network analysis agent using Google ADK deployed via Baseten to compute topological graph disruptions.

Delivery guide

How work is evaluated

Evaluation

Evaluates graph perturbation scoring accuracy and output formatting.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

Centrality Delta Range Check

Ensures calculated deltas fall within [-1.0, 1.0].

Binary check

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

Dimension 2

Graph Metric Mean Absolute Error

MAE between computed centrality changes and expected network values. • target: 0.01 • range: 0-0.5

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

  • Construct multimodal graph agents using Google Agent Development Kit (ADK).

  • Deploy custom low-latency inference functions on Baseten platform.

  • Analyze network topology changes (betweenness centrality, degree centrality) induced by missense mutations.

  • Generate interactome perturbation summary matrices.

Resources and assets

Reference links and supporting material

Dataset notes

Protein-protein interaction graph dataset containing wildtype interactomes and mutant edge loss annotations for neurodevelopmental genes.

How this agent runs

Evaluates graph perturbation scoring accuracy and output formatting.

Challenge input

JSON with mutated gene, wildtype PPI edge list, and altered binding edges

Google ADK

Provides structure for building multimodal analytical agents.

Baseten

Delivers fast microservice deployment for graph computation.

Evaluated output

JSON with delta_degree_centrality, delta_betweenness, and hub_status

Checks for
  • Ensures calculated deltas fall within [-1.0, 1.0].
  • MAE between computed centrality changes and expected network values. • target: 0.01 • range: 0-0.5
Proof of success
  • Benchmark: ProteomicNetwork-Bench
  • Graph Metric Mean Absolute Error target: 0.01
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Google · Required
  • Google ADK · Optional
  • Baseten · Optional

Evaluation contract

  • Centrality Delta Range Check · Weight 1
  • Graph Metric Mean Absolute Error · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Autism PPI Network Perturbation Analysis Agent with Google ADK