Artificial intelligence (AI) has contributed substantially to the resolution of a variety of biomedical problems, including cancer, over the past decade. Deep learning, a subfield of AI that is highly flexible and supports automatic feature extraction, is increasingly being applied in various areas of both basic and clinical cancer research. In this review, we describe numerous recent examples of the application of AI in oncology, including cases in which deep learning has efficiently solved problems that were previously thought to be unsolvable, and we address obstacles that must be overcome before such application can become more widespread. We also highlight resources and datasets that can help harness the power of AI for cancer research. The development of innovative approaches to and applications of AI will yield important insights in oncology in the coming decade.

No abstract

Polyploidy can lead to aneuploidy and tumorigenesis. Here, we report that the Hippo pathway effector Yap promotes the diploid-polyploid conversion and polyploid cell growth through the Akt-Skp2 axis. Yap strongly induces the acetyltransferase p300-mediated acetylation of the E3 ligase Skp2 via Akt signaling. Acetylated Skp2 is exclusively localized to the cytosol, which causes hyper-accumulation of the cyclin-dependent kinase inhibitor p27, leading to mitotic arrest and subsequently cell polyploidy. Additionally, the pro-apoptotic factors FoxO1/3 are overly degraded by acetylated Skp2, resulting in polyploid cell division, genomic instability and oncogenesis. Importantly, the depletion or inactivation of Akt or Skp2 abrogated Hippo signal deficiency-induced liver tumorigenesis, indicating their epistatic interaction. Thus, we conclude that Hippo-Yap signaling suppresses cell polyploidy and oncogenesis through Skp2.

SUMMARY pRb and p53 are two major tumor suppressors. Here, we found that p53 activates expression of Pirh2 and KPC1, two of the three ubiquitin ligases for p27. Loss of p53 in the absence of Skp2, the third ubiquitin ligase for p27, shrinks the cellular pool of p27 ubiquitin ligases to accumulate p27 protein. In the absence of pRb and p53, p27 was unable to inhibit DNA synthesis in spite of its abundance, but could inhibit division of cells that maintain DNA replication with re-replication. This mechanism blocked pRb and p53 doubly deficient pituitary and prostate tumorigenesis lastingly coexistent with BrdU-labeling neoplastic lesions, revealing an unconventional cancer cell vulnerability when pRb and p53 are inactivated.

The recruitment of RNA polymerase II (Pol II) to core promoters is highly regulated during rapid induction of genes. In response to heat shock, heat shock transcription factor 1 (HSF1) is activated and occupies heat shock gene promoters. Promoter‐bound HSF1 recruits general transcription factors and Mediator, which interact with Pol II, but stress‐specific mechanisms of Pol II recruitment are unclear. Here, we show in comparative analyses of HSF1 paralogs and their mutants that HSF1 interacts with the pericentromeric adaptor protein shugoshin 2 (SGO2) during heat shock in mouse cells, in a manner dependent on inducible phosphorylation of HSF1 at serine 326, and recruits SGO2 to the HSP70 promoter. SGO2‐mediated binding and recruitment of Pol II with a hypophosphorylated C‐terminal domain promote expression of HSP70, implicating SGO2 as one of the coactivators that facilitate Pol II recruitment by HSF1. Furthermore, the HSF1‐SGO2 complex supports cell survival and maintenance of proteostasis in heat shock conditions. These results exemplify a proteotoxic stress‐specific mechanism of Pol II recruitment, which is triggered by phosphorylation of HSF1 during the heat shock response.