Skip to main content
Challenge

Build a Gene Functional Evidence Publication Matcher

Extract gene symbols and RefSeq accessions from NCBI Datasets packages to retrieve literature abstracts. Synthesize structured evidence matrices linked to FHIR DiagnosticReport payloads.

Data ScienceHosted by Vera
Challenge brief

What you are building

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

Extract gene symbols and RefSeq accessions from NCBI Datasets packages to retrieve literature abstracts. Synthesize structured evidence matrices linked to FHIR DiagnosticReport payloads.

Functional Biocurator

Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene data packages.

Retrieve indexed open scientific abstracts matching gene accession queries using Haystack.

Synthesize functional evidence statements summarizing protein molecular functions and pathways.

Link extracted evidence statements to FHIR DiagnosticReport resources with narrative sections.

Curator desktop web app displaying paper citations alongside proposed FHIR narrative snippets.

Download open access scientific summary corpora and synthetic NCBI gene packages for human BRCA1 (gene-id: 672). Starter examples below are synthetic. They are not downloaded records.

NCBI Datasets gene download Uses NCBI Datasets gene-id syntax 'datasets download gene gene-id 672 --include gene,protein' to seed literature queries.

haystack, biopython, qdrant. Orchestrates retriever-reader pipelines over biomedical abstracts to match gene accessions with published evidence. High-capability reasoning model with 32k context for comprehensive document synthesis.

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.

Indexes and searches biomedical literature text using canonical NCBI gene identifiers.

Produces synthesized evidence summaries containing verified document accession citations.

Outputs FHIR DiagnosticReport JSON containing a compliant human-readable narrative div.

```json [ { "input": { "gene_id": 672, "symbol": "BRCA1", "abstract_text": "BRCA1 plays a critical role in DNA repair through homologous recombination, interacting directly with BARD1." }, "expected_output": { "gene_symbol": "BRCA1", "functional_summary": "Involved in DNA repair via homologous recombination and forms complexes with BARD1.", "citations_found": 1, "fhir_narrative_generated": true } }, { "input": { "gene_id": 99999, "symbol": "C9orf000", "abstract_text": "Uncharacterized open reading frame with unknown biological function and no documented protein interactions." }, "expected_output": { "gene_symbol": "C9orf000", "functional_summary": "Uncharacterized locus with no documented molecular function.", "citations_found": 0, "fhir_narrative_generated": true } } ] ```

Research evidence synthesis only; non-diagnostic and not for patient therapy selection. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Research evidence synthesis only; non-diagnostic and not for patient therapy selection. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Indexes and searches biomedical literature text using canonical NCBI gene identifiers. Produces synthesized evidence summaries containing verified document accession citations. Outputs FHIR DiagnosticReport JSON containing a compliant human-readable narrative div.

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

Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene data packages. Retrieve indexed open scientific abstracts matching gene accession queries using Haystack. Synthesize functional evidence statements summarizing protein molecular functions and pathways. Link extracted evidence statements to FHIR DiagnosticReport resources with narrative sections.

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

Indexes and searches biomedical literature text using canonical NCBI gene identifiers. Produces synthesized evidence summaries containing verified document accession citations. Outputs FHIR DiagnosticReport JSON containing a compliant human-readable narrative div.

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

Curator desktop web app displaying paper citations alongside proposed FHIR narrative snippets.

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 evidence synthesis only; non-diagnostic and not for patient therapy selection.

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

  • Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene data packages.

  • Retrieve indexed open scientific abstracts matching gene accession queries using Haystack.

  • Synthesize functional evidence statements summarizing protein molecular functions and pathways.

  • Link extracted evidence statements to FHIR DiagnosticReport resources with narrative sections.

Resources and assets

Reference links and supporting material

Dataset notes

Download open access scientific summary corpora and synthetic NCBI gene packages for human BRCA1 (gene-id: 672). Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Haystack

Framework

Evaluated output

No output checks are configured.

Evaluation checks
  • Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene data packages. Retrieve indexe...
  • Indexes and searches biomedical literature text using canonical NCBI gene identifiers. Produces synthesized...
  • Curator desktop web app displaying paper citations alongside proposed FHIR narrative snippets.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 1 configured tool

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
  • Haystack · 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 Gene Functional Evidence Publication Matcher