Machine-learning analysis reveals an important role for negative selection in shaping cancer aneuploidy landscapes.

BACKGROUND: Aneuploidy, an abnormal number of chromosomes within a cell, is a hallmark of cancer. Patterns of aneuploidy differ across cancers, yet are similar in cancers affecting closely related tissues. The selection pressures underlying aneuploidy patterns are not fully understood, hindering our understanding of cancer development and progression. RESULTS: Here, we apply interpretable machine learning methods to study tissue-selective aneuploidy patterns. We define 20 types of features corresponding to genomic attributes of chromosome-arms, normal tissues, primary tumors, and cancer cell lines (CCLs), and use them to model gains and losses of chromosome arms in 24 cancer types. To reveal the factors that shape the tissue-specific cancer aneuploidy landscapes, we interpret the machine learning models by estimating the relative contribution of each feature to the models. While confirming known drivers of positive selection, our quantitative analysis highlights the importance of negative selection for shaping aneuploidy landscapes. This is exemplified by tumor suppressor gene density being a better predictor of gain patterns than oncogene density, and vice versa for loss patterns. We also identify the importance of tissue-selective features and demonstrate them experimentally, revealing KLF5 as an important driver for chr13q gain in colon cancer. Further supporting an important role for negative selection in shaping the aneuploidy landscapes, we find compensation by paralogs to be among the top predictors of chromosome arm loss prevalence and demonstrate this relationship for one paralog interaction. Similar factors shape aneuploidy patterns in human CCLs, demonstrating their relevance for aneuploidy research. CONCLUSIONS: Our quantitative, interpretable machine learning models improve the understanding of the genomic properties that shape cancer aneuploidy landscapes.

Increased RNA and protein degradation is required for counteracting transcriptional burden and proteotoxic stress in human aneuploid cells.

Aneuploidy results in a stoichiometric imbalance of protein complexes that jeopardizes cellular fitness. Aneuploid cells thus need to compensate for the imbalanced DNA levels by regulating their RNA and protein levels, but the underlying molecular mechanisms remain unknown. Here, we dissected multiple diploid vs. aneuploid cell models. We found that aneuploid cells cope with transcriptional burden by increasing several RNA degradation pathways, and are consequently more sensitive to the perturbation of RNA degradation. At the protein level, aneuploid cells mitigate proteotoxic stress by reducing protein translation and increasing protein degradation, rendering them more sensitive to proteasome inhibition. These findings were recapitulated across hundreds of human cancer cell lines and primary tumors, and aneuploidy levels were significantly associated with the response of multiple myeloma patients to proteasome inhibitors. Aneuploid cells are therefore preferentially dependent on several key nodes along the gene expression process, creating clinically-actionable vulnerabilities in aneuploid cells.