… Thus, in some ways, supervised deep learning approaches can be seen as an extension of
… —the patterns unknown to the researcher—and suggest ways to act on them? In this review, …

… Upon mapping these significant pairs to the affected pathways, we found numerous … identified
several significant interdependencies between distinct pathways (Figure S4). For example, …

DNA damage repair (DDR) pathways modulate cancer risk, progression, and therapeutic
response. We systematically analyzed somatic alterations to provide a comprehensive view of …

… a rare cancer (incidence 11.9 per 100,000) [20] but also because the recent major paradigm
shifts in the understanding of EOC point to the need to approach EOC research in new ways…

The Cancer Genome Atlas (TCGA) has profiled over 10,000 tumors across 33 different
cancer-types for many genomic features, including gene expression levels. Gene expression …

… Evaluating machine learning classifiers We evaluated the pan-cancer classifiers in various
ways. For every evaluation, we reported the AUROC and area under the precisionrecall (…

Accelerating cures for children with cancer remains an immediate challenge as a result of
extensive oncogenic heterogeneity between and within histologies, distinct molecular …

… To determine the significance of the results, we fit three one-way analysis of variance (ANOVA)
models comparing ssGSEA scores of CD4, CD8, and macrophage cell type markers, …

… Both assays attempt to reduce redundancy in some way. For L1000, scientists deliberately
chose the genes’ mRNAs (the 978 distinct molecular entities measured) to minimize …

… We generated consensus signatures because there is no way to match replicate-level
information across the assays. We applied UMAP (McInnes et al., 2018) to the consensus profiles …