We work on methods that integrate symbolic knowledge with statistical learning. This includes mapping entities in formal ontologies into vector spaces while preserving their semantic relations. We develop embedding frameworks for Description Logics (e.g., EL++ and ALC) that provide mathematical guarantees for logical soundness and approximate the interpretation of formalized theories.
- Section
- Foundations
- Keywords
- ontology embeddings, description logic, geometric embeddings, EL++, ALC, neuro-symbolic AI, knowledge graph embedding, mOWL
Connections
related papers borg:linkedPaper
- Semantic similarity and machine learning with ontologies
- Predicting protein functions using positive-unlabeled ranking with ontology-based priors
- DeepGOPlus: improved protein function prediction from sequence
- DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier
- A Machine Learning Based Approach for Similarity Search on Biodiversity Knowledge Graphs
- Combining biomedical knowledge graphs and text to improve predictions for drug-target interactions and drug-indications
- Neuro-symbolic representation learning on biological knowledge graphs
- LEP-AD: language embedding of proteins and attention to drugs predicts drug-target interactions
- Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learning
- Ontology Embedding: A Survey of Methods, Applications and Resources
- Data science and symbolic AI: Synergies, challenges and opportunities
- DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier
- DeepPVP: phenotype-based prioritization of causative variants using deep learning
- DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug\textendashtarget interactions
- DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms
- DELE: Deductive EL++ Embeddings for Knowledge Base Completion
- Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
- OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction
- Semantic Disease Gene Embeddings (SmuDGE): phenotype-based disease gene prioritization without phenotypes
- mOWL: Python library for machine learning with biomedical ontologies
- SIDEKICK: A Semantically Integrated Resource for Drug Effects, Indications, and Contraindications
- From Axioms over Graphs to Vectors, and Back Again: Evaluating the Properties of Graph-based Ontology Embeddings
- Large-Scale Knowledge Integration for Enhanced Molecular Property Prediction
- EL Embeddings: Geometric construction of models for the Description Logic EL++
- Enhancing Geometric Ontology Embeddings for $\mathcalE\mathcalL^++$ with Negative Sampling and Deductive Closure Filtering
- Semi-Supervised Entity Alignment via Knowledge Graph Embedding with Awareness of Degree Difference
- Ontology-Based Concept Recognition by Using Word Embeddings
- Robust Knowledge Graph Embedding via Denoising
- Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
- Neural Multi-hop Logical Query Answering with Concept-Level Answers
- Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings
- Lattice-Preserving $\mathcal ALC$ Ontology Embeddings
- Fully Geometric Multi-hop Reasoning on Knowledge Graphs with Transitive Relations
- Neuro-Symbolic AI in Life Sciences
related projects borg:linkedProject
- Personalized cancer treatment prediction (KCSH Pathway to Impact 2025)
- KAUST Center of Excellence for Generative AI (Health and Wellness, BCB theme)
- Towards sound, complete, and explainable machine learning with biomedical ontologies (CRG11)
- Disease Models from Patient-derived Leukemic Cells in Biomimetic Peptide Scaffolds for Precision Medicine Applications
- A public Saudi pangenome as reference for genomics in the Middle East
- Enabling desert revegetation by AI-tailored soil microbiome fortification
- Enabling mangrove restoration by AI-tailored microbiome fortification
- Computational methods for functional metagenomics: from protein functions to multi-scale interactions
- IBNSINA-QI: Integrating Biomedical Networks and Semantic Information for Neural network Analysis of Quantitative Information
- Development of Algorithms for Biotechnology and Biomedical Applications
- CompleX: Variant Prioritization in Complex Disease
- Improving health of Saudi population
- Improvement of genetic variant prioritization technology
- Bio2Vec: Smart analytics infrastructure for the life sciences
- Data integration and ontologies for microbial cell factories
related people borg:linkedPerson
- Robert Hoehndorf
- Mona Alshahrani
- Sarah Alghamdi
- Sumyyah Toonsi
- Sara Althubaiti
- Maxat Kulmanov
- Imane Boudellioua
- Azza Althagafi
- Miguel Angel Rodriguez Garcia
- Zhenwei Tang
- Yang Liu
- Xi Peng
- Rund Tawfiq
- Kexin Niu
- Tengwei Song
- Paul N Schofield
- Charlotte Hauser
- Malak Althagafi
- Heribert Hirt
- Gabriel Wittum
- Arne Nägel
- Takashi Gojobori
- Georgios V Gkoutos
- Vladimir Bajic
- Xin Gao
- Michel Dumontier
- Jens Lehmann
- Fernando Zhapa-Camacho
- Sakhaa Alsaedi
- Abeer Almutairi
- Daulet Toibazar
- Amal Alhelal
- Md Nurul Muttakin
- Hatoon Al Ali
- Shahad Qatan
- Safana Bakheet
- Sawsan Al Boeisa
- Mahdi Bu Ali
- Asaad Mohammedsaleh
- Ashraf Kibraya
- Aleksei Matveev
related courses borg:linkedCourse
- Knowledge Representation and Reasoning
- Neurosymbolic AI
- Application of AI in Bioinformatics
- Knowledge Representation and Reasoning
- Neurosymbolic AI
- Data Analytics
- Knowledge Representation and Reasoning
- Data Analytics
- Knowledge Representation and Reasoning
- Knowledge Representation and Reasoning
- Introduction to Artificial Intelligence
- Machine learning
Referenced by
research topics borg:topic
- Personalized cancer treatment prediction (KCSH Pathway to Impact 2025)
- KAUST Center of Excellence for Generative AI (Health and Wellness, BCB theme)
- Towards sound, complete, and explainable machine learning with biomedical ontologies (CRG11)
- Disease Models from Patient-derived Leukemic Cells in Biomimetic Peptide Scaffolds for Precision Medicine Applications
- A public Saudi pangenome as reference for genomics in the Middle East
- Enabling desert revegetation by AI-tailored soil microbiome fortification
- Enabling mangrove restoration by AI-tailored microbiome fortification
- Computational methods for functional metagenomics: from protein functions to multi-scale interactions
- IBNSINA-QI: Integrating Biomedical Networks and Semantic Information for Neural network Analysis of Quantitative Information
- Development of Algorithms for Biotechnology and Biomedical Applications
- CompleX: Variant Prioritization in Complex Disease
- Improving health of Saudi population
- Improvement of genetic variant prioritization technology
- Bio2Vec: Smart analytics infrastructure for the life sciences
- Data integration and ontologies for microbial cell factories
- Robert Hoehndorf
- Imane Boudellioua
- Mona Alshahrani
- Maxat Kulmanov
- Sarah Alghamdi
- Azza Althagafi
- Sumyyah Toonsi
- Rund Tawfiq
- Yang Liu
- Fernando Zhapa-Camacho
- Sakhaa Alsaedi
- Abeer Almutairi
- Sara Althubaiti
- Daulet Toibazar
- Amal Alhelal
- Md Nurul Muttakin
- Hatoon Al Ali
- Shahad Qatan
- Kexin Niu
- Xi Peng
- Zhenwei Tang
- Safana Bakheet
- Sawsan Al Boeisa
- Mahdi Bu Ali
- Asaad Mohammedsaleh
- Miguel Angel Rodriguez Garcia
- Ashraf Kibraya
- Tengwei Song
- Aleksei Matveev
- Charlotte Hauser
- Malak Althagafi
- Heribert Hirt
- Gabriel Wittum
- Arne Nägel
- Takashi Gojobori
- Paul N Schofield
- Georgios V Gkoutos
- Vladimir Bajic
- Xin Gao
- Michel Dumontier
- Jens Lehmann
- DeepGOPlus: improved protein function prediction from sequence
- Neuro-Symbolic AI in Life Sciences
- Large-Scale Knowledge Integration for Enhanced Molecular Property Prediction
- Ontology Embedding: A Survey of Methods, Applications and Resources
- Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings
- Semantic similarity and machine learning with ontologies
- Predicting protein functions using positive-unlabeled ranking with ontology-based priors
- DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier
- A Machine Learning Based Approach for Similarity Search on Biodiversity Knowledge Graphs
- Combining biomedical knowledge graphs and text to improve predictions for drug-target interactions and drug-indications
- Neuro-symbolic representation learning on biological knowledge graphs
- LEP-AD: language embedding of proteins and attention to drugs predicts drug-target interactions
- Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learning
- Data science and symbolic AI: Synergies, challenges and opportunities
- DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier
- DeepPVP: phenotype-based prioritization of causative variants using deep learning
- DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug\textendashtarget interactions
- DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms
- DELE: Deductive EL++ Embeddings for Knowledge Base Completion
- Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
- OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction
- Semantic Disease Gene Embeddings (SmuDGE): phenotype-based disease gene prioritization without phenotypes
- mOWL: Python library for machine learning with biomedical ontologies
- SIDEKICK: A Semantically Integrated Resource for Drug Effects, Indications, and Contraindications
- From Axioms over Graphs to Vectors, and Back Again: Evaluating the Properties of Graph-based Ontology Embeddings
- EL Embeddings: Geometric construction of models for the Description Logic EL++
- Enhancing Geometric Ontology Embeddings for $\mathcalE\mathcalL^++$ with Negative Sampling and Deductive Closure Filtering
- Semi-Supervised Entity Alignment via Knowledge Graph Embedding with Awareness of Degree Difference
- Ontology-Based Concept Recognition by Using Word Embeddings
- Robust Knowledge Graph Embedding via Denoising
- Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
- Neural Multi-hop Logical Query Answering with Concept-Level Answers
- Lattice-Preserving $\mathcal ALC$ Ontology Embeddings
- Fully Geometric Multi-hop Reasoning on Knowledge Graphs with Transitive Relations
- Knowledge Representation and Reasoning
- Neurosymbolic AI
- Application of AI in Bioinformatics
- Knowledge Representation and Reasoning
- Neurosymbolic AI
- Data Analytics
- Knowledge Representation and Reasoning
- Data Analytics
- Knowledge Representation and Reasoning
- Knowledge Representation and Reasoning
- Introduction to Artificial Intelligence
- Machine learning
Open in the interactive graph →
JSON-LD (this resource)
{
"@context": {
"schema": "https://schema.org/",
"foaf": "http://xmlns.com/foaf/0.1/",
"prov": "http://www.w3.org/ns/prov#",
"dct": "http://purl.org/dc/terms/",
"borg": "https://borg.kaust.edu.sa/kg/ns/",
"borg-id": "https://borg.kaust.edu.sa/kg/",
"owl": "http://www.w3.org/2002/07/owl#"
},
"@id": "https://leechuck.de/kg-browser/id/topic/neuro-symbolic-ai",
"@type": "borg:Topic",
"owl:sameAs": {
"@id": "https://borg.kaust.edu.sa/kg/topic/neuro-symbolic-ai"
},
"schema:name": "Neuro-symbolic methods in Bioinformatics",
"borg:shortName": "Neuro-symbolic AI",
"borg:section": "Foundations",
"schema:abstract": "We work on methods that integrate symbolic knowledge with statistical learning. This includes mapping entities in formal ontologies into vector spaces while preserving their semantic relations. We develop embedding frameworks for Description Logics (e.g., EL++ and ALC) that provide mathematical guarantees for logical soundness and approximate the interpretation of formalized theories.",
"borg:keyword": [
"ontology embeddings",
"description logic",
"geometric embeddings",
"EL++",
"ALC",
"neuro-symbolic AI",
"knowledge graph embedding",
"mOWL"
],
"borg:linkedPaper": [
{
"@id": "https://leechuck.de/kg-browser/id/pub/10.1093/bib/bbaa199"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/10.1093/bioinformatics/btae237"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/10.1093/bioinformatics/btz595"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/10.1371/journal.pcbi.1008453"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/10.3897/biss.3.37048"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Alshahrani2022"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/alsharani17"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Alsulami2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Althagafi2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Chen2025"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/datascience"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/deepgo"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/deeppvp"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Hinnerichs2021"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Kulmanov2022"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Mashkova2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/onto2vec"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/opa2vec"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/smudge"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/ZhapaCamacho2022"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Ashhad2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/DBLP:conf/nesy/Zhapa-CamachoH23"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Ghunaim2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/kulmanov2019el"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Mashkova2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Pei2019"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Sara2018"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Song2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Tang2022"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/tang_neural_2023"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/vec2sparql"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/ZhapaCamacho2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/ZhapaCamacho2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/pub/Hoehndorf2025"
}
],
"borg:linkedProject": [
{
"@id": "https://leechuck.de/kg-browser/id/project/kcsh-pathway-to-impact"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/coe-genai-bcb"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/crg-explainable-ml-ontologies"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/smart-health-peptide-leukemia"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/smart-health-saudi-pangenome"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/ntgc-desert-microbiome"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/cli-mangrove-microbiome"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/crg-functional-metagenomics"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/crg-ibnsina-qi"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/ccf-algorithms-biotech-biomedical"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/crg-complex-variant-prioritization"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/ccf-saudi-population-health"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/cpf-variant-prioritization-improvement"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/crg-bio2vec"
},
{
"@id": "https://leechuck.de/kg-browser/id/project/ccf-microbial-cell-factories"
}
],
"borg:linkedPerson": [
{
"@id": "https://leechuck.de/kg-browser/id/person/robert-hoehndorf"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/mona-alshahrani"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/sarah-alghamdi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/sumyyah-toonsi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/sara-althubaiti"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/maxat-kulmanov"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/imane-boudellioua"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/azza-althagafi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/miguel-angel-rodriguez-garcia"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/zhenwei-tang"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/yang-liu"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/xi-peng"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/rund-tawfiq"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/kexin-niu"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/tengwei-song"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/paul-n-schofield"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/charlotte-hauser"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/malak-althagafi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/heribert-hirt"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/gabriel-wittum"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/arne-naegel"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/takashi-gojobori"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/georgios-v-gkoutos"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/vladimir-bajic"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/xin-gao"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/michel-dumontier"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/jens-lehmann"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/fernando-zhapa-camacho"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/sakhaa-alsaedi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/abeer-almutairi"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/daulet-toibazar"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/amal-alhelal"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/md-nurul-muttakin"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/hatoon-al-ali"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/shahad-qatan"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/safana-bakheet"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/sawsan-al-boeisa"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/mahdi-bu-ali"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/asaad-mohammedsaleh"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/ashraf-kibraya"
},
{
"@id": "https://leechuck.de/kg-browser/id/person/aleksei-matveev"
}
],
"borg:linkedCourse": [
{
"@id": "https://leechuck.de/kg-browser/id/course/krr-2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/neurosymbolic-2026"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/aibio-2025"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/krr-2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/neurosymbolic-2024"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/data-analytics-2023"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/krr-2022"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/data-analytics-2021"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/krr-2021"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/krr-2020"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/intro-ai-2019"
},
{
"@id": "https://leechuck.de/kg-browser/id/course/ml-aber-2013"
}
]
}
Machine-readable copy: data.jsonld. Full dataset: kg.jsonld.