Georgios V. Gkoutos

PhysioMap connects physiological traits to causal relationships and predicts responses in metabolic diseases, showing agreement with references after excluding discordant cases.

The paper models how education interacts with neurobiological features to influence cognitive outcomes in the UK Biobank cohort, showing that right fronto-parietal connectivity mediates this effect.

The paper shows that male sex hormones and reduced plakoglobin impair atrial conduction and sodium currents in mice, contributing to atrial remodelling.

This study uses Mendelian randomization to identify genetic links between chronotype and brain volume differences outside the suprachiasmatic nucleus in the UK Biobank.

Klarigi identifies compositional and discriminatory ontology classes for groups of biomedical entities, providing semantic explanations that extend existing knowledge.

The paper expands ontology labels to improve clinical text characterization by linking synonyms across ontologies, enhancing semantic similarity for patient annotation.

This paper develops a method to use uncurated clinical text phenotypes for differential diagnosis of common diseases using semantic similarity.

DeepMOCCA integrates multi-omics data with biological networks to predict cancer survival and identify patient-specific prognostic markers.

The paper introduces a heuristic-based negation detection algorithm for clinical text, showing it is fast, accurate, and generalisable compared to existing rule-based methods.

The paper identifies and repairs hidden contradictions in biomedical ontologies by combining them and using automated reasoning to find and fix unsatisfiable classes.

The paper develops a framework to extend ontologies using clinical text, improving their ability to characterize and classify medical data.

Komenti automates clinical audit by extracting medication data from text, revealing high precision and identifying at-risk patient subgroups.

This paper introduces a method to predict cancer driver genes using ontology-based features and validates it in nasopharyngeal and colorectal cancers.

DeepPVP prioritizes causative variants using deep learning and phenotype similarity, outperforming existing methods in speed and accuracy.

Vec2SPARQL integrates vector space representations with SPARQL queries to enable semantic similarity and classification within a single query for biomedical applications.

OligoPVP identifies oligogenic disease variants by integrating patient phenotypes and gene interactions in whole exome or genome sequences, showing improved performance over existing methods.

The paper develops an ontology-based method to validate consistency between function and phenotype annotations and predicts phenotypes from functions, improving annotation quality and enabling new biological insights.