Towards sound, complete, and explainable machine learning with biomedical ontologies (CRG11)
Faithful, complete, and explainable machine-learning methods on biomedical ontologies. Grant URF/1/5041-01-01 activated Apr 2023.
Overview
Faithful, complete, and explainable machine-learning methods on biomedical ontologies. Grant URF/1/5041-01-01 activated Apr 2023.
Funding
- Funder: KAUST Competitive Research Grant (CRG11)
- Grant ID:
URF/1/5041-01-01 - Role: PI
- Period: 2023–2026
Team
- Robert Hoehndorf — PI (KAUST (Professor of Computer Science))
Software
- AbermOWL — Cloud-based federated reasoning system combining AberOWL with mOWL for symbolic + approximate neuro-symbolic reasoning over SROIQ(D). code
- mOWL — Unified Python library for OWL ontology embedding methods; implements logically faithful and representation-complete optimization. code
Recent publications acknowledging this grant
- (2025) Lattice-based $ALC}$ ontology embeddings with saturation
- (2024) Predicting protein functions using positive-unlabeled ranking with ontology-based priors Supplementary Material
- (2024) Neuro-symbolic AI in Life Sciences
- (2023) DeepGOMeta: Functional Insights into Microbial Communities with Deep Learning-Based Protein Function Prediction
- (2022) Large-Scale Knowledge Integration for Enhanced Molecular Property Prediction
- (2022) INDIGENA: inductive prediction of disease--gene associations using phenotype ontologies Supplementary Material
- (2022) Exploring the Use of Ontology Components for Distantly-Supervised Disease and Phenotype Named Entity Recognition
- (2022) Context-based protein function prediction in bacterial genomes
- (2022) Causal Knowledge Graphs: Leveraging Background Knowledge for Causal Inference at Scale
- (2020) PAVS: A database of phenotype-associated variants in Saudi Arabia
Tags: neuro-symbolic AI, ontologies, knowledge graphs, knowledge representation and reasoning, ontology embeddings, semantic similarity