Barbara De Kegel

The paper shows that gene loss in cancer is often compensated by paralog protein abundance changes, stabilizing protein-protein interaction networks and creating therapeutic vulnerabilities.

The paper predicts synthetic lethal interactions between paralog pairs in cancer cell lines using machine learning and features from CRISPR screens and molecular profiles.

KBoost infers gene regulatory networks from gene expression data using kernel PCA regression, boosting, and Bayesian model averaging, showing improved performance across datasets and applied to breast cancer data.

The paper investigates how paralog genes contribute to variable essentiality in cancer cell lines and finds that paralogs from whole genome duplications show more variable essentiality due to buffering relationships.