Contact person: Eivind Valen
Keywords: Gene regulation, data science, machine learning
Research group: Biochemistry and Molecular Biology (BMB)
Department of Biosciences
With the exponentially increasing amounts of data, life science is rapidly turning into an information science. Much of this data is very rich, but produced to answer a specific hypothesis and only interpreted in this narrow context. We are interested in how we can uncover and use all the ignored information in large collections of publicly available data sets on genes and their regulation. By making use of data science and machine learning techniques we aim to develop methodology to explore this data, uncover rules of gene regulation and make novel discoveries about how life works at the fundamental level and what goes wrong during disease.
Topics from methodological research:
- This type of data exploration can take many forms and can be shaped by the candidate's preferences. Commonly used are techniques for clustering, supervised learning and various machine learning methods
Topics in life science:
- Data sets typically take the form of RNA or protein abundance measurements and various data on the process producing the RNA/protein (e.g. translation).
Mentoring and internship will be offered by a relevant external partner.
