Back to challenges
Challenge

Pangenome Phenotype Feature Pipeline with Vercel AI SDK

Pangenome analyses identify complex structural variants tied to gestational phenotypes and crop domestication. Developers will build an AI SDK web workflow in TypeScript to query pangenome graph databases, perform phenotypic association lookups, and stream real-time genetic architecture visualizations to researchers.

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.

Build a reactive TypeScript application using Vercel AI SDK to stream pangenome structural variant analyses and phenotypic lookups.

Delivery guide

How work is evaluated

Evaluation

Evaluates streaming response schema validity, structural variant parsing, and query response time.

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

sv_type_check

Verifies that structural variant type is accurately parsed.

Binary check

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

Dimension 2

json_streaming_integrity

Percentage of stream chunks forming valid JSON syntax. • target: 1 • 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

  • Implement a Next.js / TypeScript API route using Vercel AI SDK `streamText`.

  • Query graph pangenome data structures to identify structural variants (SVs).

  • Associate structural variant dosages with complex gestational and crop yield phenotypes.

  • Stream structured JSON and UI updates to real-time research dashboards.

Resources and assets

Reference links and supporting material

Dataset notes

Pangenome graph structural variant annotations and trait association summary statistics.

How this agent runs

Evaluates streaming response schema validity, structural variant parsing, and query response time.

Challenge input

JSON containing locus coordinates and phenotypic query filter.

AI SDK

Standard TypeScript SDK for streaming LLM responses to modern web apps.

Evaluated output

JSON containing structural variant ID, graph node path, and phenotype association.

Checks for
  • Verifies that structural variant type is accurately parsed.
  • Percentage of stream chunks forming valid JSON syntax. • target: 1 • range: 0-1
Proof of success
  • Benchmark: Pangenomics Query Benchmark
  • Json Streaming Integrity target: 1
  • 1 public reference case
Runtime evidence
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Vercel AI SDK · Required
  • Kira · Optional
Policy Serving
  • Pangu 3.0 · Optional
Orchestration
  • Vercel AI SDK · Required

Evaluation contract

  • sv_type_check · Weight 1
  • json_streaming_integrity · Weight 1

Recipe state

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

Frequently Asked Questions about Pangenome Phenotype Feature Pipeline with Vercel AI SDK