As genome sequencing data increases with the improving NGS machines, new algorithms and methods need to be developed to analyse, process and make use of the data to better detect pathogens and their outbreaks. I started working on such projects already during my Master's and continue in pursuit of optimized algorithms and better suited machine learning methods to computationally detect a disease-causing agent and predict its spread. I have focused on different projects and topics until now, including developing and implementing an efficient indexing and aligning algorithm, which can align and analyse sequences as they are being sequenced (more details). Followed by a focus on curating a fungi-hosts database and using ResNets to detect fungal pathogenic potential from short DNA samples (see published paper and more details on the project). I am now more focused on analysing and predicting the spread of emerging diseases and their mutations (more details).
Machine Learning, Epidemiology, Genomic Surveillance, Pathogenicity Prediction, Live-DREAM Analysis