The primary focus of the Biomedical Discovery Informatics unit at Data Science Institute of NUI Galway are cutting-edge AI and machine learning solutions motivated by and validated within a wide range of practically-relevant life science use cases. This research falls under the general umbrella of discovery informatics that has recently emerged as a field that explores the potential of applying various computer science technologies like Semantic Web, big data analytics, AI or machine learning to interdisciplinary challenges in turning data and information into actual knowledge. Life sciences are one of the most relevant application areas of discovery informatics, both in terms of interesting research problems and societal impact opportunities. This is reflected by the strategic vision of the unit that is to deliver novel scientific results with substantial impact potential in life sciences and healthcare.
The core research topics of the unit are as follows: Representation learning for biomedical data (including networked data, protein/gene sequences, etc.); Network analytics for biomedical data; Supervised, semi-supervised, unsupervised and reinforcement learning models for sparsely annotated and/or noisy data (primarily focusing on open biomedical data); Knowledge graph generation (transformation of legacy data into knowledge graphs, integration, cleansing); Knowledge graph embeddings (statistical relational learning models, focused primarily on link prediction and knowledge base completion, but also on more advanced issues like discovery of causal relationships); Mixed embedding models for knowledge graph and unstructured (primarily text) data; Explainable AI (with special focus on hybrid approaches combining latent and graph feature models); Informing explainable / predictive models with background domain knowledge; Augmenting standard deep learning models by knowledge graphs.
Selected application areas include: Drug repurposing and discovery; Prediction of adverse drug effects (including polypharmacy scenarios); Cellular signalling prediction (with specific focus on pathways prevalent in cancer and neurodegenerative diseases); General-purpose predictive “shells” and/or software libraries for processing biomedical data; Survival analysis (with specific focus on models based on integrated multi-omics data); Clinical decision support systems (with specific focus on precision medicine).
Areas of work:
Knowledge graphs, Network analytics for biomedical data, Explainable ai, Reinforcement learning, Representation learning,
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2017, PT I