Skip to main content
Challenge

Build a Research Study Specimen Provenance Reconciler

Correlate specimen accession identifiers from NCBI gene data packages with FHIR Specimen resources. Verify collection context and track specimen chain-of-custody in research registries.

Data ScienceHosted by Vera
Challenge brief

What you are building

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

Correlate specimen accession identifiers from NCBI gene data packages with FHIR Specimen resources. Verify collection context and track specimen chain-of-custody in research registries.

Biobank Repository Coordinator

Read specimen source tables and RefSeq accession metadata from NCBI gene packages.

Validate specimen attributes against FHIR Specimen and ResearchStudy resource definitions.

Flag records missing mandatory specimen processing timestamps or tissue source ontology codes.

Construct validated FHIR Specimen resource bundles with resolved provenance references.

Browser-based audit table showing missing accession links, tissue type codes, and batch export buttons.

Generate synthetic biobank records matching NCBI Datasets gene accession formats stored as local JSON files. Starter examples below are synthetic. They are not downloaded records.

HL7 FHIR overview Applies FHIR R5 foundation definitions for Specimen, ResearchStudy, and Provenance metadata structures.

vercel-ai-sdk, pydantic, nextjs. vercel-ai-sdk streams UI-driven JSON schema validation errors and provenance corrections directly to web curators. Hosted or local model accessed via streaming HTTP API; low latency token generation for rapid UI feedback.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Verify 100% of specimen entries against FHIR Specimen structural constraints.

Identify and flag specimens missing SNOMED or NCIT anatomical origin codes.

Generate valid FHIR Provenance records establishing input data package provenance.

```json [ { "input": { "sample_accession": "SAMN12345678", "gene_accession": "NM_020107.5", "tissue_code": "410602000", "tissue_display": "Liver" }, "expected_output": { "resourceType": "Specimen", "id": "SAMN12345678", "type": { "coding": [ { "system": "http://snomed.info/sct", "code": "410602000", "display": "Liver" } ] }, "status": "available", "provenance_valid": true } }, { "input": { "sample_accession": "SAMN87654321", "gene_accession": "NM_020107.5", "tissue_code": "", "tissue_display": "Unknown Tissue" }, "expected_output": { "resourceType": "Specimen", "id": "SAMN87654321", "status": "unavailable", "provenance_valid": false, "validation_errors": [ "Missing required anatomical coding" ] } } ] ```

Research specimen provenance tracking utilizing de-identified accession keys without clinical diagnostic advice. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Research specimen provenance tracking utilizing de-identified accession keys without clinical diagnostic advice. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Verify 100% of specimen entries against FHIR Specimen structural constraints. Identify and flag specimens missing SNOMED or NCIT anatomical origin codes. Generate valid FHIR Provenance records establishing input data package provenance.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

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
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Read specimen source tables and RefSeq accession metadata from NCBI gene packages. Validate specimen attributes against FHIR Specimen and ResearchStudy resource definitions. Flag records missing mandatory specimen processing timestamps or tissue source ontology codes. Construct validated FHIR Specimen resource bundles with resolved provenance references.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Verify 100% of specimen entries against FHIR Specimen structural constraints. Identify and flag specimens missing SNOMED or NCIT anatomical origin codes. Generate valid FHIR Provenance records establishing input data package provenance.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

Browser-based audit table showing missing accession links, tissue type codes, and batch export buttons.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Research specimen provenance tracking utilizing de-identified accession keys without clinical diagnostic advice.

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

  • Read specimen source tables and RefSeq accession metadata from NCBI gene packages.

  • Validate specimen attributes against FHIR Specimen and ResearchStudy resource definitions.

  • Flag records missing mandatory specimen processing timestamps or tissue source ontology codes.

  • Construct validated FHIR Specimen resource bundles with resolved provenance references.

Resources and assets

Reference links and supporting material

Dataset notes

Generate synthetic biobank records matching NCBI Datasets gene accession formats stored as local JSON files. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Vercel AI SDK

TypeScript toolkit for AI apps.

Evaluated output

No output checks are configured.

Evaluation checks
  • Read specimen source tables and RefSeq accession metadata from NCBI gene packages. Validate specimen attrib...
  • Verify 100% of specimen entries against FHIR Specimen structural constraints. Identify and flag specimens m...
  • Browser-based audit table showing missing accession links, tissue type codes, and batch export buttons.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 2 configured tools

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

Action Space
  • Vercel AI SDK · Optional
Orchestration
  • Vercel AI SDK · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Research Study Specimen Provenance Reconciler