Background and job description
The brain is a highly complex organ that susceptible to a wide range of psychiatric and neurodegenerative diseases. In collaboration with the Netherlands Brain Bank, we recently initiated the Netherlands Neurogenetics Database, which aims to integrate genetics (common genetic variants & polygenic risk scores), with extensive clinical and neuropathological data, and (single cell) multi-omics data types in order to study the effects of genetic variation on brain disease. Using Machine learning text mining approaches (Google Bert), we aim to convert clinical neuropathological summary files into standardized clinical and neuropathological trait assessments. The clinical data will be converted into disease trajectories using graph-based approaches, while machine learning models will be used study the relationship between clinical disease trajectories, neuropathology and genetic susceptibility to CNS disorders. The proposed 4-year PhD project is a bioinformatics/computational research project that aims to analyze and integrate datasets and computational approaches and coordinate processing tissues and generating new datasets and data types. Machine learning, and genomics computational tools are at the heart of this project. We’re looking for an ambitious candidate with computational/bioinformatics expertise in Python, R, Linux-shell scripting, GitHub, analysis of genomics data types, cloud-based computing and affiliation with graph-based and machine learning approaches, and a broad interest in neurogenomics and transcriptional regulation.