Back to Prompt Library
implementation
Build the application
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Research Gene Synonym Catalog Drift and Terminology Mapper
Format
Code-aware
Lines
80
Sections
11
Linked challenge
Build a Research Gene Synonym Catalog Drift and Terminology Mapper
Prompt source
Original prompt text with formatting preserved for inspection.
80 lines
11 sections
No variables
1 code block
## Build
Evaluate gene symbol synonym catalogs from NCBI gene reports against standard terminologies. Detect deprecated symbols and generate FHIR ConceptMap resources for translational registries.
## User
Genomic Nomenclature Curator
## Workflow
1. Ingest NCBI Datasets gene reports containing canonical symbols, aliases, and taxonomy metadata.
2. Compare historical gene aliases against standard terminology mapping tables to identify drift.
3. Formulate replacement mappings for retired or ambiguous gene symbols.
4. Construct FHIR R5 ConceptMap resources defining explicit source-to-target translation rules.
## Interface
Streamlit portal displaying alias change histories and providing one-click FHIR ConceptMap export.
## Data
Extract gene metadata reports using NCBI Datasets CLI for human genes ACRV1 and A2M via `--include none`.
Starter examples below are synthetic. They are not downloaded records.
## Source
[NCBI Datasets gene download](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/how-tos/genes/download-gene-data-package/)
Extracts gene metadata reports and synonym catalogs produced by NCBI Datasets `download gene symbol` queries.
## Tools
pydantic-ai, fastapi, pandas.
Pydantic AI structures terminology transformation rules and validates FHIR ConceptMap element schemas.
API-based or local LLM for drafting textual rationales for nomenclature migrations.
## Deliverables
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.
## Acceptance
- Identifies outdated gene synonyms that conflict with canonical NCBI Gene ID definitions.
- Generates valid FHIR ConceptMap resources adhering to FHIR R5 terminology specifications.
- Validates that all target mappings point to valid canonical symbols with active NCBI Gene IDs.
## Starter Examples
```json
[
{
"input": {
"gene_id": 2,
"current_symbol": "A2M",
"provided_query_symbol": "CPAMD5"
},
"expected_output": {
"is_synonym": true,
"canonical_symbol": "A2M",
"concept_map": {
"resourceType": "ConceptMap",
"status": "active",
"group": [
{
"source": "http://example.org/legacy-symbols",
"target": "http://hl7.org/fhir/sid/ncbi-gene",
"element": [
{
"code": "CPAMD5",
"target": [
{
"code": "A2M",
"relationship": "equivalent"
}
]
}
]
}
]
}
}
},
{
"input": {
"gene_id": null,
"current_symbol": null,
"provided_query_symbol": "UNKNOWN_XYZ"
},
"expected_output": {
"is_synonym": false,
"canonical_symbol": null,
"concept_map": null,
"error": "Symbol UNKNOWN_XYZ not resolved in NCBI gene reports"
}
}
]
```
## Safety
Addresses only public gene nomenclature drift; does not provide diagnostic or therapeutic advice.
Use mock external writes. Require human review before any real deployment.Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.