Skip to main content
Challenge

Build a Research Literature Functional Evidence Synthesizer for Gene Sets

Extract gene accessions from NCBI Datasets packages and query scientific literature summaries with Haystack. Construct 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 accessions from NCBI Datasets packages and query scientific literature summaries with Haystack. Construct structured evidence matrices linked to FHIR DiagnosticReport payloads.

Biocuration Literature Specialist

Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene reports.

Retrieve open-access scientific publication abstracts related to target gene accessions.

Synthesize literature findings using Haystack extractive pipelines into structured evidence statements.

Assemble findings into FHIR DiagnosticReport payloads containing linked scientific citations.

Split-view web console showing gene package metadata on the left and literature evidence matrices on the right.

Use NCBI Datasets gene report metadata from human genes combined with open-access PubMed Central abstract dumps. Starter examples below are synthetic. They are not downloaded records.

NCBI Datasets gene download Extracts gene symbols and accession lists from NCBI Datasets metadata reports generated by datasets download gene.

haystack, pydantic, fastapi. Haystack provides an end-to-end framework for literature retrieval, extraction, and synthesis pipelines. API LLM or high-capability local model with strong scientific text synthesis and citation grounding.

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.

Extracts target gene symbols from NCBI Datasets gene report metadata.

Retrieves relevant literature summaries and extracts functional evidence sentences.

Emits FHIR DiagnosticReport JSON containing coded gene references and bibliographic citations.

```json [ { "input": { "gene_symbol": "BRCA1", "gene_id": "672", "abstracts": [ { "pmid": "12345", "text": "BRCA1 is involved in DNA repair and cell cycle checkpoint control." } ] }, "expected_output": { "gene_symbol": "BRCA1", "evidence_count": 1, "summary": "BRCA1 participates in DNA double-strand break repair.", "fhir_report": { "resourceType": "DiagnosticReport", "status": "final", "conclusion": "Literature indicates role in DNA repair and cell cycle checkpoint control (PMID: 12345)." } } }, { "input": { "gene_symbol": "ACRV1", "gene_id": "879", "abstracts": [] }, "expected_output": { "gene_symbol": "ACRV1", "evidence_count": 0, "summary": "No literature abstracts provided for synthesis.", "fhir_report": { "resourceType": "DiagnosticReport", "status": "registered", "conclusion": "No literature evidence records available." } } } ] ```

Research literature curation only; produces no medical diagnosis, treatment plan, or personal health insights. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Research literature curation only; produces no medical diagnosis, treatment plan, or personal health insights. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Extracts target gene symbols from NCBI Datasets gene report metadata. Retrieves relevant literature summaries and extracts functional evidence sentences. Emits FHIR DiagnosticReport JSON containing coded gene references and bibliographic citations.

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 reports. Retrieve open-access scientific publication abstracts related to target gene accessions. Synthesize literature findings using Haystack extractive pipelines into structured evidence statements. Assemble findings into FHIR DiagnosticReport payloads containing linked scientific citations.

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

Extracts target gene symbols from NCBI Datasets gene report metadata. Retrieves relevant literature summaries and extracts functional evidence sentences. Emits FHIR DiagnosticReport JSON containing coded gene references and bibliographic citations.

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

Split-view web console showing gene package metadata on the left and literature evidence matrices on the right.

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 literature curation only; produces no medical diagnosis, treatment plan, or personal health insights.

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 reports.

  • Retrieve open-access scientific publication abstracts related to target gene accessions.

  • Synthesize literature findings using Haystack extractive pipelines into structured evidence statements.

  • Assemble findings into FHIR DiagnosticReport payloads containing linked scientific citations.

Resources and assets

Reference links and supporting material

Dataset notes

Use NCBI Datasets gene report metadata from human genes combined with open-access PubMed Central abstract dumps. 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 reports. Retrieve open-access...
  • Extracts target gene symbols from NCBI Datasets gene report metadata. Retrieves relevant literature summari...
  • Split-view web console showing gene package metadata on the left and literature evidence matrices on the ri...
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 Research Literature Functional Evidence Synthesizer for Gene Sets