Blavatnik School of Computer Sciences, Tel Aviv University, Tel Aviv 69978, Israel.
Blavatnik School of Computer Sciences, Tel Aviv University, Tel Aviv 69978, Israel; Department of Molecular Microbiology and Biotechnology, Faculty of Life Sciences, Tel Aviv University, Tel Aviv 69978, Israel; Sackler School of Medicine, Tel Aviv University, Tel Aviv 69978, Israel; Department of Computer Science and Center for Bioinformatics and Computational Biology, University of Maryland, College Park, MD 20742, USA.
Cell Syst. 2016 Mar 23;2(3):209-13. doi: 10.1016/j.cels.2016.03.001.
Drug side effects levy a massive cost on society through drug failures, morbidity, and mortality cases every year, and their early detection is critically important. Here, we describe the array of model-based phenotype predictors (AMPP), an approach that leverages medical informatics resources and a human genome-scale metabolic model (GSMM) to predict drug side effects. AMPP is substantially predictive (AUC > 0.7) for >70 drug side effects, including very serious ones such as interstitial nephritis and extrapyramidal disorders. We evaluate AMPP's predictive signal through cross-validation, comparison across multiple versions of a side effects database, and co-occurrence analysis of drug side effect associations in scientific abstracts (hypergeometric p value = 2.2e-40). AMPP outperforms a previous biochemical structure-based method in predicting metabolically based side effects (aggregate AUC = 0.65 versus 0.59). Importantly, AMPP enables the identification of key metabolic reactions and biomarkers that are predictive of specific side effects. Taken together, this work lays a foundation for future detection of metabolically grounded side effects during early stages of drug development.
药物副作用每年通过药物失败、发病率和死亡率给社会带来巨大成本，早期发现这些副作用至关重要。在这里，我们描述了基于模型的表型预测器 (AMPP)，这是一种利用医学信息学资源和人类基因组规模代谢模型 (GSMM) 来预测药物副作用的方法。AMPP 对超过 70 种药物副作用具有很强的预测能力（AUC>0.7），包括间质性肾炎和锥体外系疾病等非常严重的副作用。我们通过交叉验证、比较副作用数据库的多个版本以及药物副作用关联在科学摘要中的共现分析（超几何 p 值=2.2e-40）来评估 AMPP 的预测信号。AMPP 在预测基于代谢的副作用方面优于以前的基于生化结构的方法（综合 AUC=0.65 与 0.59）。重要的是，AMPP 能够识别出对特定副作用具有预测性的关键代谢反应和生物标志物。总之，这项工作为在药物开发的早期阶段检测基于代谢的副作用奠定了基础。
