PhenoKG, a knowledge-graph-enhanced GNN and transformer model, achieves 24.64% MRR on the MyGene2 rare disease cohort versus 19.02% for SHEPHERD, and works without a candidate gene list.
Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PhenoKG: Knowledge Graph-Driven Gene Discovery and Patient Insights from Phenotypes Alone
PhenoKG, a knowledge-graph-enhanced GNN and transformer model, achieves 24.64% MRR on the MyGene2 rare disease cohort versus 19.02% for SHEPHERD, and works without a candidate gene list.