Richard Redon | Searcharxiv

arXiv2026

Federated SPARQL querying for genomic variant functional annotation

Sensitive health data should preferentially be analysed on site. In typical bioinformatics workows, public databases are duplicated and used by specialised tools to enrich the local datasets. In the case of genomic variation data, this process is called variant annotation. In this session we demonstrate variant annotation using federated SPARQL queries. We rst overview how clinico-genomic data can be modelled as a knowledge graph (KG), leveraging state-of-the-art biomedical ontologies. We then perform variant annotation by querying UniprotKB, a massive curated KG for gene and proteins. Our approach avoids public data duplication while maintaining genomic data on site and aligning it with FAIR principles. Our use-case is based on the ICAN project, a research program aimed at studying the physiopathology of cerebral berry aneurysms.

q-bio.QM↗

arXiv2025

Predicting clinical outcomes from patient care pathways represented with temporal knowledge graphs

Background: With the increasing availability of healthcare data, predictive modeling finds many applications in the biomedical domain, such as the evaluation of the level of risk for various conditions, which in turn can guide clinical decision making. However, it is unclear how knowledge graph data representations and their embedding, which are competitive in some settings, could be of interest in biomedical predictive modeling. Method: We simulated synthetic but realistic data of patients with intracranial aneurysm and experimented on the task of predicting their clinical outcome. We compared the performance of various classification approaches on tabular data versus a graph-based representation of the same data. Next, we investigated how the adopted schema for representing first individual data and second temporal data impacts predictive performances. Results: Our study illustrates that in our case, a graph representation and Graph Convolutional Network (GCN) embeddings reach the best performance for a predictive task from observational data. We emphasize the importance of the adopted schema and of the consideration of literal values in the representation of individual data. Our study also moderates the relative impact of various time encoding on GCN performance.

cs.LG↗