PulseAugur
EN
LIVE 18:05:38

GNNs create hierarchy-aware knowledge graph embeddings for yeast phenotype prediction

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a novel method using graph neural networks (GNNs) to create hierarchy-aware embeddings for knowledge graphs. This approach incorporates semantic loss derived from ontologies to better represent domain knowledge. The method was applied to predict yeast phenotype, achieving a mean R^2 score of 0.360 for double gene knockouts, outperforming baseline models. Incorporating semantic loss further improved predictive performance to R^2=0.377, demonstrating the value of ontology structure for quantitative predictions and potentially guiding biological discovery. AI

IMPACT Enhances biological discovery by improving quantitative prediction from knowledge graphs and ontologies.

RANK_REASON Academic paper detailing a new method for knowledge graph embeddings and its application.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

GNNs create hierarchy-aware knowledge graph embeddings for yeast phenotype prediction

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Filip Kronstr\"om, Alexander H. Gower, Daniel Brunns{\aa}ker, Ievgeniia A. Tiukova, Ross D. King ·

    Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction

    arXiv:2605.03690v1 Announce Type: new Abstract: We present a method for finding hierarchy-aware embeddings of knowledge graphs (KGs) using graph neural networks (GNNs) enriched with a semantic loss derived from underlying ontologies. This method yields embeddings that better refl…

  2. arXiv cs.AI TIER_1 English(EN) · Ross D. King ·

    Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction

    We present a method for finding hierarchy-aware embeddings of knowledge graphs (KGs) using graph neural networks (GNNs) enriched with a semantic loss derived from underlying ontologies. This method yields embeddings that better reflect domain knowledge. To demonstrate their utili…

RELATED ENTITIES

RELATED TOPICS