PhD Research Fellow in Computational Biology

There is a vacancy for a PhD Research Fellow in computational biology at the Department of Informatics . The position is for a fixed-term period of 3 years with the possibility of a 4th year with career-promoting work (e.g. teaching duties at the Department). The position is subject to financing by NFR. About the project/work tasks: The successful candidate is involved in developing ensemble learning strategies for cell-type deconvolution to improve performance and to provide error estimates. This includes both implementing pistemic uncertainties (model uncertainties) and aleatoric uncertainty (stochastic errors from the measurement process). Further exploration of adversarial learning strategies for ensemble generation to provide an out-of-the-box solution for cell-type deconvolution which provides error estimates are planned. Second, in the overall NFR project algorithms for cell type deconvolution on spatial transcriptomics data get developed. These algorithms as well as the ones for error predictions shall get implemented in the existing Deconomix software package and GUI application. This shall make the algorithms accessible and re-usable to both expert bioinformatician and wet-lab biologists with little programming knowledge. Qualifications and personal qualities: Applicants must hold a master's degree or equivalent education in physics, mathematics, computational biology, informatics or similar. Master students can apply provided they complete their final master exam before 01.09.2025. It is a condition of employment that the master's degree has been awarded. Experience from or competence in front and back-end development in Phyton is a requirement. Experience from or competence in mathematical model development for deconvolution models is a requirement. Experience from or competence in working with biological data is a requirement. Experience in working with high dimensional biological data from single cell RNASeq and spatial transcriptomics data is an advantage. Experience in supervised and unsupervised learning techniques is an advantage. Experience with cell type specific interactions is an advantage. Experience in other programming languages than Python is an advantage. Statistical knowledge (survival analyses, linear regression, etc.) is an advantage. Working experience in interdisciplinary teams (i.e. in medicine) is an advantage. Experience in working with cancer data is an advantage. Applicants must be able to work independently and in a structured manner and demonstrate good collaborative skills. Applicants must be proficient in both written and oral English.

The University of Bergen is a renowned educational and research institution, organised into seven faculties and approximately 54 institutes and academic centres. Campus is located in the centre of Bergen with university areas at Nygårdshøyden, Haukeland, Marineholmen, Møllendalsveien and Årstad. There are seven departments and several centres at Faculty of Science and Technology.