A machine learning and directed network optimization approach to uncover regulatory patterns.

TP53, the , is the most frequently mutated gene in human cancers and the functional characterization of its regulation is fundamental. To address this we employ two strategies: machine learning to predict the mutation status of , and directed regulatory networks to reconstruct the effect of mutations on the transcipt levels of targets. Using data from established databases (Cancer Cell Line Encyclopedia, The Cancer Genome Atlas), machine learning could predict the mutation status, but not resolve different mutations.

The Challenge of Combining Chemo- and Radiotherapy with Checkpoint Kinase Inhibitors.

Preclinical models of cancer have demonstrated enhanced efficacy of cell-cycle checkpoint kinase inhibitors when used in combination with genotoxic agents. This combination therapy is predicted to be exquisitely toxic to cells with a deficient G-S checkpoint or cells with a genetic predisposition leading to intrinsic DNA replication stress, as these cancer cells become fully dependent on the intra-S and G-M checkpoints for DNA repair and cellular survival. Therefore, abolishing remaining cell-cycle checkpoints after damage leads to increased cell death in a tumor cell-specific fashion.