合成致死率（SL）在发现癌症新靶点方面显示出巨大的前景。 CRISPR双敲除（CDKO）技术只能筛选数百个基因及其组合，但不能筛选全基因组。因此，CDKO实验中的基因和基因对选择非常需要良好的SL预测模型。然而，缺乏可扩展的 SL 属性阻碍了 SL 交互对样本外数据的泛化，从而阻碍了建模工作。在本文中，我们认识到 SL 连接性是一种可扩展且可泛化的 SL 属性。我们为单个样本特定的 SL 预测模型 (MLEC-iSL) 开发了一种新颖的两步多层编码器，它首先预测 SL 连接性，然后预测 SL 相互作用。 MLEC-iSL 具有三种编码器，即基因编码器、图编码器和 Transformer 编码器。 MLEC-iSL 在 K562（AUPR，0.73；AUC，0.72）和 Jurkat（AUPR，0.73；AUC，0.71）细胞中实现了高 SL 预测性能，而现有方法没有超过 0.62 AUPR 和 AUC。 MLEC-iSL 的预测性能在 22Rv1 细胞的 CDKO 实验中得到验证，在 987 个选定基因对中产生 46.8% 的 SL 率。该屏幕还揭示了细胞凋亡和有丝分裂细胞死亡途径之间的 SL 依赖性。© 作者 2024。由牛津大学出版社出版。

Synthetic lethality (SL) has shown great promise for the discovery of novel targets in cancer. CRISPR double-knockout (CDKO) technologies can only screen several hundred genes and their combinations, but not genome-wide. Therefore, good SL prediction models are highly needed for genes and gene pairs selection in CDKO experiments. However, lack of scalable SL properties prevents generalizability of SL interactions to out-of-sample data, thereby hindering modeling efforts. In this paper, we recognize that SL connectivity is a scalable and generalizable SL property. We develop a novel two-step multilayer encoder for individual sample-specific SL prediction model (MLEC-iSL), which predicts SL connectivity first and SL interactions subsequently. MLEC-iSL has three encoders, namely, gene, graph, and transformer encoders. MLEC-iSL achieves high SL prediction performance in K562 (AUPR, 0.73; AUC, 0.72) and Jurkat (AUPR, 0.73; AUC, 0.71) cells, while no existing methods exceed 0.62 AUPR and AUC. The prediction performance of MLEC-iSL is validated in a CDKO experiment in 22Rv1 cells, yielding a 46.8% SL rate among 987 selected gene pairs. The screen also reveals SL dependency between apoptosis and mitosis cell death pathways.© The Author(s) 2024. Published by Oxford University Press.