Having a Bachelor’s and Master’s degree in Biotechnology from the University of Natural Resources And Life Sciences (Vienna, Austria), I do not consider myself a traditionally trained Bioinformatician. However, once my interest in computational biology was sparked through a course on molecular dynamics simulations, I was certain which career path to pursue. Internships, additional courses and plenty of free time spent on the computer, helped expand my knowledge and build my computational portfolio. Simultaneously, I carried out my master thesis at the Medical University of Vienna, during which I acquired extensive wet-lab skills. My project aimed at exploring the potency of micro-RNA to modulate chemo-resistance in colon carcinoma cell lines. Despite my unconventional career path, I consider my dual background as one of my greatest advantages today.
Secondment 1: Extend framework to facilitate deep learning using omics focusing on explainable AI
Secondment 2: Case study: apply data mining approaches to aid in clinical decision making for NAFLD patients
ESR 15 Project
Developing and demonstrating data mining and A.I. tools to better understand patient heterogeneity and assist patient stratification
Recent fundamental advancements in artificial intelligence and machine learning accelerate the field via data-driven approaches which allow for the extraction of clinically relevant insight. However, the heterogeneous and complex nature of biological data poses a considerable challenge in the creation of reliable tools. The project “Developing and demonstrating data mining and A.I. tools to better understand patient heterogeneity and assist patient stratification” aims at addressing this issue by integrating systems biology and data mining principles, which would benefit the whole field of precision medicine. Using necrotising soft tissue infections (NSTI) and non-alcoholic fatty liver disease (NAFLD) as case studies, we will build a clinical decision-support system encompassing a data management platform, prognostic tools based on machine learning algorithms and a user-oriented front-end. The goal is to provide caregivers with a holistic platform integratable into clinical practices, aiding them in the stratification of patients according to treatment response or disease progression. Successful completion of this project will additionally demonstrate the benefits of multidisciplinary approaches for personalised medicine.
- Machine learning applied to biological data
- Development of end-user oriented tools / software / applications
- Sports (Volleyball, CrossFit)