Back to prompt library
Build a Research Literature Functional Evidence Synthesizer for Gene Sets — implementation
Linked challenge: Build a Research Literature Functional Evidence Synthesizer for Gene Sets
Prompt source
implementation74 lines11 sectionsNo variables1 code block
## Build
Extract gene accessions from NCBI Datasets packages and query scientific literature summaries with Haystack. Construct structured evidence matrices linked to FHIR DiagnosticReport payloads.
## User
Biocuration Literature Specialist
## Workflow
1. Extract canonical gene symbols and RefSeq accessions from NCBI Datasets gene reports.
2. Retrieve open-access scientific publication abstracts related to target gene accessions.
3. Synthesize literature findings using Haystack extractive pipelines into structured evidence statements.
4. Assemble findings into FHIR DiagnosticReport payloads containing linked scientific citations.
## Interface
Split-view web console showing gene package metadata on the left and literature evidence matrices on the right.
## Data
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.
## Source
[NCBI Datasets gene download](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/how-tos/genes/download-gene-data-package/)
Extracts gene symbols and accession lists from NCBI Datasets metadata reports generated by `datasets download gene`.
## Tools
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.
## 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
- 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.
## Starter Examples
```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."
}
}
}
]
```
## Safety
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.