Synthetic lethality describes a genetic interaction between two perturbations, leading to cell death, whereas neither event alone has a significant effect on cell viability. This concept can be exploited to specifically target tumor cells. CRISPR viability screens have been widely employed to identify cancer vulnerabilities. However, an approach to systematically infer genetic interactions from viability screens is missing. Here we describe PAn-canceR Inferred Synthetic lethalities (PARIS), a machine learning approach to identify cancer vulnerabilities. PARIS predicts synthetic lethal (SL) interactions by combining CRISPR viability screens with genomics and transcriptomics data across hundreds of cancer cell lines profiled within the Cancer Dependency Map. Using PARIS, we predicted 15 high confidence SL interactions within 549 DNA damage repair (DDR) genes. We show experimental validation of an SL interaction between the tumor suppressor CDKN2A, thymidine phosphorylase (TYMP) and the thymidylate synthase (TYMS), which may allow stratifying patients for treatment with TYMS inhibitors. Using genome-wide mapping of SL interactions for DDR genes, we unraveled a dependency between the aldehyde dehydrogenase ALDH2 and the BRCA-interacting protein BRIP1. Our results suggest BRIP1 as a potential therapeutic target in ~ 30% of all tumors, which express low levels of ALDH2. PARIS is an unbiased, scalable and easy to adapt platform to identify SL interactions that should aid in improving cancer therapy with increased availability of cancer genomics data.

中文翻译：

---

通过机器学习预测合成致死率来发现癌症的脆弱性

综合致死性描述了两种扰动之间的遗传相互作用，导致细胞死亡，而单独的事件对细胞活力没有显着影响。这一概念可用于特异性靶向肿瘤细胞。CRISPR 活力筛选已被广泛用于识别癌症脆弱性。然而，缺乏一种从活力筛选中系统地推断遗传相互作用的方法。在这里，我们描述了 PAn-canceR 推断综合致死率 (PARIS)，这是一种识别癌症脆弱性的机器学习方法。PARIS 通过将 CRISPR 活力筛选与癌症依赖性图谱中数百个癌细胞系的基因组学和转录组学数据相结合，预测合成致死 (SL) 相互作用。使用 PARIS，我们预测了 549 个 DNA 损伤修复 (DDR) 基因内的 15 个高置信度 SL 相互作用。我们对肿瘤抑制因子 CDKN2A、胸苷磷酸化酶 (TYMP) 和胸苷酸合成酶 (TYMS) 之间的 SL 相互作用进行了实验验证，这可能允许对接受 TYMS 抑制剂治疗的患者进行分层。利用 DDR 基因 SL 相互作用的全基因组图谱，我们揭示了乙醛脱氢酶 ALDH2 和 BRCA 相互作用蛋白 BRIP1 之间的依赖性。我们的结果表明 BRIP1 是约 30% 表达低水平 ALDH2 的肿瘤的潜在治疗靶点。PARIS 是一个公正、可扩展且易于调整的平台，用于识别 SL 相互作用，通过增加癌症基因组学数据的可用性来帮助改善癌症治疗。