Pattern Recognition & Bioinformatics, Department of Intelligent Systems, Faculty EEMCS, Delft University of Technology, Delft 2628 XE, The Netherlands.
Holland Proton Therapy Center (HollandPTC), Delft 2600 AC, The Netherlands.
Bioinformatics. 2022 Sep 15;38(18):4360-4368. doi: 10.1093/bioinformatics/btac523.
Synthetic lethality (SL) between two genes occurs when simultaneous loss of function leads to cell death. This holds great promise for developing anti-cancer therapeutics that target synthetic lethal pairs of endogenously disrupted genes. Identifying novel SL relationships through exhaustive experimental screens is challenging, due to the vast number of candidate pairs. Computational SL prediction is therefore sought to identify promising SL gene pairs for further experimentation. However, current SL prediction methods lack consideration for generalizability in the presence of selection bias in SL data.
We show that SL data exhibit considerable gene selection bias. Our experiments designed to assess the robustness of SL prediction reveal that models driven by the topology of known SL interactions (e.g. graph, matrix factorization) are especially sensitive to selection bias. We introduce selection bias-resilient synthetic lethality (SBSL) prediction using regularized logistic regression or random forests. Each gene pair is described by 27 molecular features derived from cancer cell line, cancer patient tissue and healthy donor tissue samples. SBSL models are built and tested using approximately 8000 experimentally derived SL pairs across breast, colon, lung and ovarian cancers. Compared to other SL prediction methods, SBSL showed higher predictive performance, better generalizability and robustness to selection bias. Gene dependency, quantifying the essentiality of a gene for cell survival, contributed most to SBSL predictions. Random forests were superior to linear models in the absence of dependency features, highlighting the relevance of mutual exclusivity of somatic mutations, co-expression in healthy tissue and differential expression in tumour samples.
https://github.com/joanagoncalveslab/sbsl.
Supplementary data are available at Bioinformatics online.
当两个基因的功能同时丧失导致细胞死亡时，就会出现合成致死性（SL）。这为开发针对内源性破坏基因的合成致死对的抗癌治疗方法提供了巨大的希望。由于候选基因对的数量众多，通过详尽的实验筛选来识别新的 SL 关系具有挑战性。因此，需要进行计算 SL 预测，以识别具有进一步实验潜力的有前途的 SL 基因对。然而，当前的 SL 预测方法缺乏在 SL 数据中存在选择偏差的情况下的通用性考虑。
我们表明，SL 数据表现出相当大的基因选择偏差。我们设计的实验旨在评估 SL 预测的稳健性，结果表明，由已知 SL 相互作用的拓扑结构驱动的模型（例如，图，矩阵分解）对选择偏差特别敏感。我们使用正则化逻辑回归或随机森林引入了具有选择偏差抗性的合成致死性（SBSL）预测。每个基因对由来自癌细胞系、癌症患者组织和健康供体组织样本的 27 个分子特征描述。使用大约 8000 个在乳腺癌、结肠癌、肺癌和卵巢癌中实验衍生的 SL 对来构建和测试 SBSL 模型。与其他 SL 预测方法相比，SBSL 显示出更高的预测性能、更好的通用性和对选择偏差的稳健性。基因依赖性，量化基因对细胞存活的必要性，对 SBSL 预测贡献最大。随机森林在没有依赖性特征的情况下优于线性模型，这突出了体细胞突变的互斥性、健康组织中的共表达和肿瘤样本中的差异表达的相关性。
https://github.com/joanagoncalveslab/sbsl。
补充数据可在 Bioinformatics 在线获取。
