mims-harvard/SHEPHERD
SHEPHERD: Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
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.
Stars
79
Forks
29
Language
HTML
License
MIT
Category
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.
Higher-rated alternatives
mims-harvard/ClinVec
ClinVec: Unified Embeddings of Clinical Codes Enable Knowledge-Grounded AI in Medicine
NYUMedML/DeepEHR
Chronic Disease Prediction Using Medical Notes
biocentral/biocentral_server
Compute functionality for biocentral.
nomic-ai/contrastors
Train Models Contrastively in Pytorch
hybrid-kg/clep
🤖 A Python Package for generating new patient representations driven by data and prior knowledge