




As our newest student addition, you will join our Discovery Data Science team to strengthen proteomics-driven therapeutic target discovery in oncology. Mass-spectrometry (MS)–based proteomics provides valuable insights into tumor-specific protein expression, but datasets are often affected by missing values, batch effects, and inter-study variability. In this project, you will develop and evaluate statistical and machine learning approaches for mechanism-aware imputation and cohort integration, enabling more robust and interpretable protein-level analyses across studies. You will gain hands-on experience in high-dimensional omics data analysis and see how computational insights directly inform innovative antibody therapeutic strategies in oncology! The main research aim of this project is to establish a robust computational foundation for proteomics-driven therapeutic target identification, ensuring that protein-level evidence can be integrated, interpreted, and leveraged with maximal precision in oncology research.