Campana Pedro A, Prasse Paul, Lienhard Matthias, Thedinga Kristina, Herwig Ralf, Scheffer Tobias
University of Potsdam, Department of Computer Science, Potsdam, Germany.
Max Planck Institute for Molecular Genetics, Department Computational Molecular Biology, Berlin, Germany.
NAR Genom Bioinform. 2024 Apr 27;6(2):lqae043. doi: 10.1093/nargab/lqae043. eCollection 2024 Jun.
Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drugs components that are tailored to the transcriptomic profile of a given primary tumor. The SMILES representation of molecules that is used by state-of-the-art drug-sensitivity models is not conducive for neural networks to generalize to new drugs, in part because the distance between atoms does not generally correspond to the distance between their representation in the SMILES strings. Graph-attention networks, on the other hand, are high-capacity models that require large training-data volumes which are not available for drug-sensitivity estimation. We develop a modular drug-sensitivity graph-attentional neural network. The modular architecture allows us to separately pre-train the graph encoder and graph-attentional pooling layer on related tasks for which more data are available. We observe that this model outperforms reference models for the use cases of precision oncology and drug discovery; in particular, it is better able to predict the specific interaction between drug and cell line that is not explained by the general cytotoxicity of the drug and the overall survivability of the cell line. The complete source code is available at https://zenodo.org/doi/10.5281/zenodo.8020945. All experiments are based on the publicly available GDSC data.
计算药物敏感性模型有潜力通过识别针对特定原发性肿瘤转录组特征量身定制的靶向药物成分来改善治疗效果。最先进的药物敏感性模型所使用的分子SMILES表示不利于神经网络推广到新药，部分原因是原子之间的距离通常与它们在SMILES字符串中的表示之间的距离不对应。另一方面，图注意力网络是高容量模型，需要大量训练数据，而这些数据在药物敏感性估计中是不可用的。我们开发了一种模块化药物敏感性图注意力神经网络。模块化架构使我们能够在有更多可用数据的相关任务上分别预训练图编码器和图注意力池化层。我们观察到，在精准肿瘤学和药物发现的用例中，该模型优于参考模型；特别是，它能够更好地预测药物与细胞系之间的特定相互作用，而这种相互作用无法用药物的一般细胞毒性和细胞系的整体生存能力来解释。完整的源代码可在https://zenodo.org/doi/10.5281/zenodo.8020945获取。所有实验均基于公开可用的GDSC数据。
