Skip to main content
Challenge

Build an NCBI Gene Synonym Drift and Nomenclature Auditor

Track gene symbol synonyms and catalog changes from NCBI Datasets gene metadata reports. Harmonize historical aliases into canonical identifiers mapped to FHIR Terminology bindings.

Data ScienceHosted by Vera
Challenge brief

What you are building

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

Track gene symbol synonyms and catalog changes from NCBI Datasets gene metadata reports. Harmonize historical aliases into canonical identifiers mapped to FHIR Terminology bindings.

Bioinformatics Data Curator

Parse gene data reports extracted from NCBI Datasets JSON packages using Pydantic schemas.

Extract current official gene symbols, historical synonyms, and cross-referenced taxonomy tags.

Reconcile obsolete aliases against canonical FHIR Coding datatypes with human-readable narratives.

Output structured audit reports highlighting deprecated symbols and recommended canonical mappings.

Tabular browser interface showing obsolete aliases alongside canonical FHIR ConceptMap entries.

Ingest synthetic NCBI gene-service reports representing human genes A2M and ACRV1 from local mock files. Starter examples below are synthetic. They are not downloaded records.

NCBI Datasets gene download Utilizes NCBI Datasets symbol query pattern 'datasets download gene symbol ACRV1 A2M --taxon human' and resulting metadata reports.

pydantic-ai, biopython, streamlit. Enforces strict data model boundaries on multi-field NCBI metadata reports and nested FHIR terminology objects. General purpose hosted reasoning model or local LLM via Ollama for alias disambiguation.

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 all listed synonyms from NCBI gene data report JSON without data loss.

Maps uncurated symbols to valid FHIR Coding objects including system, code, and display fields.

Flags ambiguous historical aliases shared across multiple distinct Gene IDs.

```json [ { "input": { "gene_id": 2, "current_symbol": "A2M", "taxname": "Homo sapiens", "synonyms": [ "A2MD", "CPAMD5", "FWP007" ] }, "expected_output": { "canonical_symbol": "A2M", "gene_id": 2, "synonyms_found": 3, "fhir_coding": { "system": "https://www.ncbi.nlm.nih.gov/gene", "code": "2", "display": "A2M" }, "status": "harmonized" } }, { "input": { "gene_id": 9999, "current_symbol": "UNKNOWN", "taxname": "Homo sapiens", "synonyms": [] }, "expected_output": { "canonical_symbol": "UNKNOWN", "gene_id": 9999, "synonyms_found": 0, "fhir_coding": { "system": "https://www.ncbi.nlm.nih.gov/gene", "code": "9999", "display": "UNKNOWN" }, "status": "unresolved_synonyms" } } ] ```

Research data harmonization only; does not inform patient diagnostic reports or medication administration. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Research data harmonization only; does not inform patient diagnostic reports or medication administration. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Extracts all listed synonyms from NCBI gene data report JSON without data loss. Maps uncurated symbols to valid FHIR Coding objects including system, code, and display fields. Flags ambiguous historical aliases shared across multiple distinct Gene IDs.

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

Parse gene data reports extracted from NCBI Datasets JSON packages using Pydantic schemas. Extract current official gene symbols, historical synonyms, and cross-referenced taxonomy tags. Reconcile obsolete aliases against canonical FHIR Coding datatypes with human-readable narratives. Output structured audit reports highlighting deprecated symbols and recommended canonical mappings.

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 all listed synonyms from NCBI gene data report JSON without data loss. Maps uncurated symbols to valid FHIR Coding objects including system, code, and display fields. Flags ambiguous historical aliases shared across multiple distinct Gene IDs.

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

Tabular browser interface showing obsolete aliases alongside canonical FHIR ConceptMap entries.

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 data harmonization only; does not inform patient diagnostic reports or medication administration.

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

  • Parse gene data reports extracted from NCBI Datasets JSON packages using Pydantic schemas.

  • Extract current official gene symbols, historical synonyms, and cross-referenced taxonomy tags.

  • Reconcile obsolete aliases against canonical FHIR Coding datatypes with human-readable narratives.

  • Output structured audit reports highlighting deprecated symbols and recommended canonical mappings.

Resources and assets

Reference links and supporting material

Dataset notes

Ingest synthetic NCBI gene-service reports representing human genes A2M and ACRV1 from local mock files. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Pydantic AI

Typed Python agent framework.

Evaluated output

No output checks are configured.

Evaluation checks
  • Parse gene data reports extracted from NCBI Datasets JSON packages using Pydantic schemas. Extract current...
  • Extracts all listed synonyms from NCBI gene data report JSON without data loss. Maps uncurated symbols to v...
  • Tabular browser interface showing obsolete aliases alongside canonical FHIR ConceptMap entries.
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
  • Pydantic AI · Optional
Orchestration
  • Pydantic AI · 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 an NCBI Gene Synonym Drift and Nomenclature Auditor