Pages

Other

Neuro-symbolic AI

Neuro-symbolic methods in bioinformatics aim to combine the deductive guarantees of symbolic knowledge with the inductive power of statistical learning. Our group develops methods that map entities described in formal ontologies into vector spaces while preserving the semantic relations expressed by their axioms, so that downstream models can use background knowledge directly in similarity search, link prediction, and classification. The distinctive angle at KAUST is a focus on description logics as the source of structure: we design embedding constructions for languages such as EL++ and ALC

Neuro-Symbolic AI in Life Sciences

Year: 2025 Venue: Handbook on Neurosymbolic AI and Knowledge Graphs Authors: Robert Hoehndorf, Catia Pesquita, Fernando Zhapa-Camacho DOI: 10.3233/faia250239 Abstract Life sciences have a long history of driving advancements in various disciplines, including mathematics, philosophy, and logic. In recent years, life sciences have also become a significant application area for Artificial Intelligence (AI) technologies, including for neuro-symbolic AI methods. The life sciences knowledge infrastructure, characterized by its widespread use of ontologies, complex annotation models, large size, and

Neuro-symbolic representation learning on biological knowledge graphs

Year: 2017 Venue: Bioinformatics Authors: Mona Alshahrani, Mohammad Asif Khan, Omar Maddouri, Akira R. Kinjo, Nuria Queralt-Rosinach, Robert Hoehndorf Abstract Motivation: Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on

New approaches to the representation and analysis of phenotype knowledge in human diseases and their animal models

Venue: Briefings in Functional Genomics Authors: Paul N. Schofield, John P. Sundberg, Robert Hoehndorf, Georgios V. Gkoutos Abstract The systematic investigation of the phenotypes associated with genotypes in model organisms holds the promise of revealing genotype–phenotype relations directly and without additional, intermediate inferences. Large-scale projects are now underway to catalog the complete phenome of a species, notably the mouse. With the increasing amount of phenotype information becoming available, a major challenge that biology faces today is the systematic analysis of this

Notions of similarity for systems biology models

Year: 2018 Venue: Briefings in Bioinformatics Authors: Ron Henkel, Robert Hoehndorf, Tim Kacprowski, Christian Knupfer, Wolfgang Liebermeister, Dagmar Waltemath Abstract Systems biology models are rapidly increasing in complexity, size and numbers. When building large models, researchers rely on software tools for the retrieval, comparison, combination and merging of models, as well as for version control. These tools need to be able to quantify the differences and similarities between computational models. However, depending on the specific application, the notion of 'similarity' may greatly

OBML - Ontologies in Biomedicine and Life Sciences

Venue: Journal of Biomedical Semantics Authors: Heinrich Herre, Robert Hoehndorf, Janet Kelso, Frank Loebe, Stefan Schulz DOI: 10.1186/2041-1480-2-S4-I1 Abstract The OBML 2010 workshop, held at the University of Mannheim on September 9-10, 2010, is the 2nd in a series of meetings organized by the Working Group "Ontologies in Biomedicine and Life Sciences" of the German Society of Computer Science (GI) and the German Society of Medical Informatics, Biometry and Epidemiology (GMDS). Integrating, processing and applying the rapidly expanding information generated in the life sciences -- from

OligoPVP: Phenotype-driven analysis of individual genomic information to prioritize oligogenic disease variants

Year: 2018 Venue: Scientific Reports Authors: Imane Boudellioua, Maxat Kulmanov, Paul N Schofield, Georgios V Gkoutos, Robert Hoehndorf Abstract Purpose: An increasing number of Mendelian disorders have been identified for which two or more variants in one or more genes are required to cause the disease, or significantly modify its severity or phenotype. It is difficult to discover such interactions using existing approaches. The purpose of our work is to develop and evaluate a system that can identify combinations of variants underlying oligogenic diseases in individual whole exome or whole

Onto2Graph

Generates entailment-aware graph projections of OWL ontologies suitable for downstream graph machine learning while preserving the axioms' deductive structure. Get it GitHub: https://github.com/bio-ontology-research-group/Onto2Graph ★ 12 Developed in projects IBNSINA-QI: Integrating Biomedical Networks and Semantic Information for Neural network Analysis of Quantitative Information Bio2Vec: Smart analytics infrastructure for the life sciences Category: Ontology Reasoning & Tooling

Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations

Year: 2018 Venue: Bioinformatics Authors: Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf Abstract Motivation: Biological knowledge is widely represented in the form of ontology-based annotations: ontologies describe the phenomena assumed to exist within a domain, and the annotations associate a (kind of) biological entity with a set of phenomena within the domain. The structure and information contained in ontologies and their annotations make them valuable for developing machine learning, data analysis and knowledge extraction algorithms; notably, semantic similarity is widely used to

Ontology based text mining of gene-phenotype associations: application to candidate gene prediction

Year: 2019 Venue: Database Authors: Senay Kafkas, Robert Hoehndorf Abstract Gene–phenotype associations play an important role in understanding the disease mechanisms which is a requirement for treatment development. A portion of gene–phenotype associations are observed mainly experimentally and made publicly available through several standard resources such as MGI. However, there is still a vast amount of gene–phenotype associations buried in the biomedical literature. Given the large amount of literature data, we need automated text mining tools to alleviate the burden in manual curation of

Ontology design patterns to disambiguate relations between genes and gene products in GENIA

Venue: Journal of Biomedical Semantics Authors: Robert Hoehndorf, Axel-Cyrille Ngonga Ngomo, Sampo Pyysalo, Tomoko Ohta, Anika Oellrich, Dietrich Rebholz-Schuhmann DOI: 10.1186/2041-1480-2-S5-S1 Abstract MOTIVATION:Annotated reference corpora play an important role in biomedical information extraction. A semantic annotation of the natural language texts in these reference corpora using formal ontologies is challenging due to the inherent ambiguity of natural language. The provision of formal definitions and axioms for semantic annotations offers the means for ensuring consistency as well as

Ontology Embedding: A Survey of Methods, Applications and Resources

Year: 2025 Venue: IEEE Transactions on Knowledge and Data Engineering Authors: Jiaoyan Chen, Olga Mashkova, Fernando Zhapa-Camacho, Robert Hoehndorf, Yuan He, Ian Horrocks DOI: 10.1109/tkde.2025.3559023 Abstract Ontologies are widely used for representing domain knowledge and meta data, playing an increasingly important role in Information Systems, the Semantic Web, Bioinformatics and many other domains. However, logical reasoning that ontologies can directly support are quite limited in learning, approximation and prediction. One straightforward solution is to integrate statistical analysis

Ontology engineering

Ontology engineering and semantic interoperability address the practical problem of turning hundreds of independently developed biomedical ontologies into an infrastructure that can be queried, reasoned over, and combined at scale. Our group designs architectures for processing large, heterogeneous datasets using Semantic Web standards, with a particular emphasis on bringing automated reasoning into routine data-access workflows. The angle taken at KAUST is engineering-led: we treat ontology-based data access as a service that must be fast enough for interactive use, expressive enough to

Ontology-based cross-species integration and analysis of Saccharomyces cerevisiae phenotypes

Year: 2011 Venue: Proceedings of the 3rd Workshop for Ontologies in Biomedicine and Life sciences (OBML) Authors: Georgios V. Gkoutos, Robert Hoehndorf Abstract Ontologies are widely used in the biomedical community for annotation and integration of databases. Formal definitions can relate classes from different ontologies and thereby integrate data across different levels of granularity, domains and species. We have applied this methodology to the Ascomycete Phenotype Ontology (APO), enabling the reuse of various orthogonal ontologies and we have converted the phenotype associated data found

Ontology-based prediction of cancer driver genes

Year: 2019 Venue: Scientific Reports Authors: Sara Althubaiti, Andreas Karwath, Ashraf Dallol, Adeeb Noor, Shadi Salem Alkhayyat, Rolina Alwassia, Katsuhiko Mineta, Takashi Gojobori, Andrew D Beggs, Paul N Schofield, Georgios V Gkoutos, Robert Hoehndorf Abstract Identifying and distinguishing cancer driver genes among thousands of candidate mutations remains a major challenge. Accurate identification of driver genes and driver mutations is critical for advancing cancer research and personalizing treatment based on accurate stratification of patients. Due to inter-tumor genetic heterogeneity

Ontology-based validation and identification of regulatory phenotypes

Year: 2018 Venue: Bioinformatics Authors: Maxat Kulmanov, Paul N Schofield, Georgios V Gkoutos, Robert Hoehndorf Abstract Motivation: Function annotations of gene products, and phenotype annotations of genotypes, provide valuable information about molecular mechanisms that can be utilized by computational methods to identify functional and phenotypic relatedness, improve our understanding of disease and pathobiology, and lead to discovery of drug targets. Identifying functions and phenotypes commonly requires experiments which are time-consuming and expensive to carry out; creating the

OPA2Vec

Combines ontology axioms with associated annotation properties (labels, synonyms, definitions) into a single corpus, then trains Word2Vec to produce semantically rich vectors for ontology classes. Get it GitHub: https://github.com/bio-ontology-research-group/opa2vec ★ 37 Developed in projects Bio2Vec: Smart analytics infrastructure for the life sciences CompleX: Variant Prioritization in Complex Disease Category: Ontology Embedding & Machine Learning

OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction

Year: 2018 Venue: Bioinformatics Authors: Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf DOI: 10.1093/bioinformatics/bty933 Abstract Motivation: Ontologies are widely used in biology for data annotation, integration and analysis. In addition to formally structured axioms, ontologies contain meta-data in the form of annotation axioms which provide valuable pieces of information that characterize ontology classes. Annotation axioms commonly used in ontologies include class labels, descriptions or synonyms. Despite being a rich source of semantic information, the ontology meta-data are generally

PathoPhenoDB: linking human pathogens to their disease phenotypes in support of infectious disease research

Year: 2019 Venue: Scientific Data Authors: Senay Kafkas, Marwa Abdelhakim, Yasmeen Hashish, Maxat Kulmanov, Marwa Abdellatif, Paul N Schofield, Robert Hoehndorf DOI: 10.1101/489971 Abstract Understanding the relationship between the pathophysiology of infectious disease, the biology of the causative agent and the development of therapeutic and diagnostic approaches is dependent on the synthesis of a wide range of types of information. Provision of a comprehensive and integrated disease phenotype knowledgebase has the potential to provide novel and orthogonal sources of information for the

Phased genome assemblies and pangenome graphs of human populations of Japan and Saudi Arabia

Year: 2025 Venue: Scientific Data Authors: Maxat Kulmanov, Saeideh Ashouri, Yang Liu, Marwa Abdelhakim, Ebtehal Alsolme, Masao Nagasaki, Yasuyuki Ohkawa, Yutaka Suzuki, Rund Tawfiq, Katsushi Tokunaga, Toshiaki Katayama, Malak S. Abedalthagafi, Robert Hoehndorf, Yosuke Kawai DOI: 10.1038/s41597-025-05652-y Abstract The selection of a reference sequence in genome analysis is critical, as it serves as the foundation for all downstream analyses. Recently, the pangenome graph has been proposed as a data model that incorporates haplotypes from multiple individuals. Here we present JaSaPaGe, a

PhenomeNET: a whole-phenome approach to disease gene discovery

Venue: Nucleic Acids Research Authors: Robert Hoehndorf, Paul N. Schofield, Georgios V. Gkoutos Abstract Phenotypes are investigated in model organisms to understand and reveal the molecular mechanisms underlying disease. Phenotype ontologies were developed to capture and compare phenotypes within the context of a single species. Recently, these ontologies were augmented with formal class definitions that may be utilized to integrate phenotypic data and enable the direct comparison of phenotypes between different species. We have developed a method to transform phenotype ontologies into a

Phenotype informatics

Phenotypes are the observable consequences of genotype, environment, and their interaction, and they remain the principal currency by which disease is recognised, model organisms are characterised, and plant traits are catalogued. Our work develops the informatics infrastructure that makes phenotype data computable across species and clinical settings: the phenotype ontologies themselves, the cross-species crosswalks that link them, the tools that capture and standardise phenotype descriptions from text and images, and the computational pipelines that connect phenotype evidence back to genes

Phenotype-driven discovery of digenic variants in personal genome sequences

Year: 2017 Venue: Proceedings of VarI-SIG Authors: Imane Boudellioua, Maxat Kulmanov, Paul N Schofield, Georgios V Gkoutos, Robert Hoehndorf Abstract Identification of variants associated with inherited diseases is a major challenge, in particular in the analysis of clinical sequence data from individual patients. An increasing number of Mendelian diseases have been identified in which two or more variants in multiple genes are required to cause the disease, or significantly modify its severity or phenotype. It is difficult to discover such interactions using existing approaches. Information

PIDO: The Primary Immunodeficiency Disease Ontology

Venue: Bioinformatics Authors: Nico Adams, Robert Hoehndorf, Georgios V. Gkoutos, Gesine Hansen, Christian Hennig Abstract Motivation: Primary Immunodeficiency Diseases (PIDs) are Mendelian conditions of high phenotypic complexity and low incidence. They usually manifest in toddlers and infants, although they can also occur much later in life. Information about PIDs is often widely scattered throughout the clinical as well as the research literature and hard to find for both generalists as well as experienced clinicians. Semantic Web technologies coupled to clinical information systems can go

Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion

Year: 2022 Venue: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Authors: Zhenwei Tang, Shichao Pei, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Robert Hoehndorf, Xiangliang Zhang DOI: 10.24963/ijcai.2022/312 Abstract Most real-world knowledge graphs (KG) are far from complete and comprehensive. This problem has motivated efforts in predicting the most plausible missing facts to complete a given KG, i.e., knowledge graph completion (KGC). However, existing KGC methods suffer from two main issues, 1) the false negative issue, i.e., the sampled negative

Predicting protein functions using positive-unlabeled ranking with ontology-based priors

Year: 2024 Venue: Bioinformatics Authors: Fernando Zhapa-Camacho, Zhenwei Tang, Maxat Kulmanov, Robert Hoehndorf DOI: 10.1093/bioinformatics/btae237 Abstract Automated protein function prediction is a crucial and widely studied problem in bioinformatics. Computationally, protein function is a multilabel classification problem where only positive samples are defined and there is a large number of unlabeled annotations. Most existing methods rely on the assumption that the unlabeled set of protein function annotations are negatives, inducing the false negative issue, where potential positive

Prediction of Metabolic Pathway Involvement in Prokaryotic UniProtKB Data by Association Rule Mining

Year: 2016 Venue: PLoS ONE Authors: Imane Boudellioua, Rabie Saidi, Robert Hoehndorf, Maria J. Martin, Victor Solovyev DOI: 10.1371/journal.pone.0158896 Abstract The widening gap between known proteins and their functions has encouraged the development of methods to automatically infer annotations. Automatic functional annotation of proteins is expected to meet the conflicting requirements of maximizing annotation coverage, while minimizing erroneous functional assignments. This trade-off imposes a great challenge in designing intelligent systems to tackle the problem of automatic protein

Projects

Funded research projects led by or involving the Bio-Ontology Research Group. Period Project Role 2025–ongoing KAUST Smart Health Initiative 2024 round (SHI2024) PI 2025–2026 Personalized cancer treatment prediction (KCSH Pathway to Impact 2025) PI 2024–ongoing KAUST Center of Excellence for Generative AI (Health and Wellness, BCB theme) PI 2024–2026 A public Saudi pangenome as reference for genomics in the Middle East PI 2023–2026 Towards sound, complete, and explainable machine learning with biomedical ontologies (CRG11) PI 2023–2026 Disease Models from Patient-derived Leukemic Cells in

Protein function

Determining what a protein does, from its sequence alone, is one of the foundational problems of computational molecular biology. Experimental characterisation cannot keep pace with sequencing throughput, and large-scale ontologies such as the Gene Ontology (GO) provide the structured background knowledge needed to make automated assignment of function tractable. Our work centres on the DeepGO family of systems, which couple deep neural networks with the formal axioms of the Gene Ontology so that predicted annotations are not only accurate but also logically consistent with what is already

Protein function prediction as approximate semantic entailment

Year: 2024 Venue: Nature Machine Intelligence Authors: Maxat Kulmanov, Francisco J. Guzman-Vega, Paula Duek Roggli, Lydie Lane, Stefan T. Arold, Robert Hoehndorf DOI: 10.1038/s42256-024-00795-w Abstract Abstract The Gene Ontology (GO) is a formal, axiomatic theory with over 100,000 axioms that describe the molecular functions, biological processes and cellular locations of proteins in three subontologies. Predicting the functions of proteins using the GO requires both learning and reasoning capabilities in order to maintain consistency and exploit the background knowledge in the GO. Many

Publications

A complete list of publications by members of the Bio-Ontology Research Group, drawn from our local research knowledge graph (223 entries). Quick filters: Neuro-symbolic AI Ontology engineering Applied Ontology Protein function Rare disease Drug mechanisms Genomics Biomedical informatics Semantic similarity Microbial communities Phenotype informatics Bioengineering Publications by topic Neuro-symbolic AI (29) (2025) Ontology Embedding: A Survey of Methods, Applications and Resources (2025) Neuro-Symbolic AI in Life Sciences (2024) Predicting protein functions using positive-unlabeled ranking

Quantitative comparison of mapping methods between Human and Mammalian Phenotype Ontology

Year: 2011 Venue: Proceedings of the 3rd Workshop for Ontologies in Biomedicine and Life sciences (OBML) Authors: Anika Oellrich, Robert Hoehndorf, Georgios V. Gkoutos, Dietrich Rebholz-Schuhmann Abstract Researchers use animal studies to better understand human diseases. In recent years, large-scale phenotype studies such as Phenoscape and EuroPhenome have been initiated to identify genetic causes of a species phenome. Species-specific phenotype ontologies are required to capture and report about all findings and to automatically infer results relevant to human diseases. The integration of

Quantitative evaluation of ontology design patterns for combining pathology and anatomy ontologies

Year: 2019 Venue: Scientific Reports Authors: Sarah M. Alghamdi, Beth A. Sundberg, John P. Sundberg, Paul N. Schofield, Robert Hoehndorf Abstract Data are increasingly annotated with multiple ontologies to capture rich information about the features of the subject under investigation. Analysis may be performed over each ontology separately, but recently there has been a move to combine multiple ontologies to provide more powerful analytical possibilities. However, it is often not clear how to combine ontologies or how to assess or evaluate the potential design patterns available. Here we use a

Ranking Adverse Drug Reactions With Crowdsourcing

Year: 2015 Venue: J Med Internet Res Authors: Assaf Gottlieb, Robert Hoehndorf, Michel Dumontier, B. Russ Altman DOI: 10.2196/jmir.3962 Abstract Background: There is no publicly available resource that provides the relative severity of adverse drug reactions (ADRs). Such a resource would be useful for several applications, including assessment of the risks and benefits of drugs and improvement of patient-centered care. It could also be used to triage predictions of drug adverse events. Objective: The intent of the study was to rank ADRs according to severity. Methods: We used Internet-based

Rare disease

The diagnosis of rare and Mendelian disease has been transformed by exome and genome sequencing, but interpretation remains the bottleneck: a typical patient genome contains tens of thousands of rare variants, only one or a few of which are causative. Effective diagnostic support requires the integration of patient-specific molecular data with structured background knowledge about genes, phenotypes, and disease mechanisms. We develop methods, anchored on the PhenomeNET phenotype network and the PVP family of variant prioritisation tools, that combine automated reasoning over phenotype

Representing physiological processes and their participants with PhysioMaps

Year: 2013 Venue: Journal of Biomedical Semantics Authors: Daniel Cook, Maxwell Neal, Robert Hoehndorf, Georgios Gkoutos, John Gennari DOI: 10.1186/2041-1480-4-S1-S2 Abstract BACKGROUND:As the number and size of biological knowledge resources for physiology grows, researchers need improved tools for searching and integrating knowledge and physiological models. Unfortunately, current resources--databases, simulation models, and knowledge bases, for example--are only occasionally and idiosyncratically explicit about the semantics of the biological entities and processes that they describe