Harry Triantafyllidis

Modules:

• Data Science (MSc)

I obtained my PhD Degree in Computer Science (Operations Research) in Greece, co-advised by the Massachusetts Institute of Technology. Since then, I have been an MRC Early Career Research Fellow with the School of Public Health at Imperial (2021-2022), and have held postdoctoral research positions at University College London (2016-2018) and University of Oxford (2018-2021).

My research centers on the development and application of advanced analytical tools in healthcare/medicine, aimed at enhancing decision-making processes that inform policy and improve patient stratification and disease outcomes. I am currently working with NCDs such as cancer, asthma and sickle cell disease. The ultimate aim is to bridge the gap between data science and practical health applications, driving improvements in global health and providing impactful actionable insights in the clinical setting.

My current research focuses on utilizing mathematical programming optimization, machine learning techniques, and deep learning to identify phenotypic differences in disease and primarily in different types of cancer.I have built a platform called HarmonizeR to facilitate genomic and transcriptomic integration into these methodologies using R and Python. The platform enables analyses of a multitude of angles:

• Exploratory genomic, transcriptomic analysis (unsupervised learning)
• Generalised Linear Models for Classification across multiple clinical and molecular features using RENOIR
• Gene - Regulatory Network Reconstruction and Optimization using Mathematical Programming (MILP) using CARNIVAL
• Deep Learning

Currently I am interested to infer the functional implications of different somatic mutations by classifying their heterogeneity (gene activity profiling in pathways, modes of regulation) across cancer type, subtype and other clinical/molecular features.