Jobs and Positions
Feature selection for supervised diagnostic classification of pancreas-related
Supervised machine learning can analyze large sets of genomic data, including gene
expression data from next-generation sequencing of RNA molecules. This thesis would
focus on utilization of machine learning for classification of different pancreas-related
cancer types based on the expression of small non-coding microRNAs. Specifically, the
selection of specific microRNAs for classificator training as well as choosing the best pre-
processing of gene expression data before classifications itself would be the main goal of
the proposed thesis. Offered to master/very enthusiastic bachelor students.
Circular RNA quantification from RNA-sequencing of glioblastoma patients
Circular RNAs (circRNAs) are a novel class of non-coding RNAs that have emerged as
potential players in the development of different cancer types, including glioblastoma. The
circular form of these non-coding RNAs makes their detection and subsequent
bioinformatic analysis from Next-generation sequencing data a challenging topic. This
thesis aims to analyse RNA-sequencing data of glioblastoma patients in order to identify
circular RNAs that could have key roles in the biology of glioblastoma. Offered to
master/very enthusiastic bachelor students.
Bioinformatic analysis of RNA-sequencing data for identification of piwi-interacting
Piwi-interacting RNAs (piRNAs) is a class of small non-coding RNAs that arose as
potential cancer biomarkers present in human urine. Liquid biopsy, such as urine, is more
easily obtainable compared to cancer tissue samples which require invasive clinical
procedure. The goal of this thesis would be to analyse small RNA-sequencing data from
human urine samples of patients with bladder cancer. Specifically targeted will be
bioinformatical quantification of piRNAs as potential biomarkers for bladder cancer.
Offered to bachelor students.