mims-harvard/SHEPHERD

SHEPHERD: Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases

47
/ 100
Emerging

This project helps clinicians and geneticists diagnose rare genetic diseases faster and more accurately. By inputting a patient's observed symptoms (phenotypes) and candidate genes, it outputs likely causal genes, similar patient cases, or characterizations of novel diseases. This tool is designed for medical professionals involved in the diagnosis of rare diseases, particularly those working with genetic sequencing and detailed patient phenotyping.

No commits in the last 6 months.

Use this if you are a clinician or geneticist trying to identify the causal genes for a patient with suspected rare genetic disease, find similar patient cases, or characterize a novel disease, especially when dealing with limited prior data.

Not ideal if you need to diagnose common diseases or if you don't have detailed patient phenotype data and a list of candidate genes.

rare-disease-diagnosis clinical-genetics phenotype-analysis undiagnosed-diseases genomic-medicine
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

79

Forks

29

Language

HTML

License

MIT

Last pushed

Jul 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/SHEPHERD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.