A systems toxicology approach for the prediction of kidney toxicity and its mechanisms in vitro

The failure to predict kidney toxicity of new chemical entities early in the development process before they reach humans remains a critical issue. Here, we used primary human kidney cells and applied a systems biology approach that combines multidimensional datasets and machine learning to identify biomarkers that not only predict nephrotoxic compounds but also provide hints towards their mechanism of toxicity. Gene expression and high content imaging phenotypical data from 46 diverse kidney toxicants were analyzed using Random Forest machine learning. Imaging features capturing changes in cell morphology and nucleus texture along with mRNA levels of HMOX1 and SQSTM1 were identified as the most powerful predictors of toxicity. These biomarkers were validated by their ability to accurately predict kidney toxicity of 4 out of 6 candidate therapeutics that exhibited toxicity only in in late stage preclinical/clinical studies. Network analysis of similarities in toxic phenotypes was perfor...新化学实体（new chemical entities）在进入人体临床试验前，无法在研发早期阶段预测其肾毒性，仍是一项亟待解决的关键问题。本研究采用原代人肾细胞（primary human kidney cells），结合多维数据集（multidimensional datasets）与机器学习（machine learning）的系统生物学方法（systems biology approach），筛选得到既能精准预测肾毒性化合物（nephrotoxic compounds）、又能揭示其毒性作用机制（mechanism of toxicity）的生物标志物（biomarkers）。本研究针对46种不同肾毒性化合物的基因表达（gene expression）与高内涵成像（high content imaging）表型数据（phenotypical data），采用随机森林（Random Forest）机器学习算法开展分析。结果显示，能够反映细胞形态（cell morphology）与细胞核纹理（nucleus texture）变化的成像特征，以及HMOX1、SQSTM1的mRNA表达水平（mRNA levels），是预测毒性最有效的标志物。上述生物标志物的预测性能得到验证：6种仅在临床前/临床研究（preclinical/clinical studies）阶段表现出肾毒性的候选治疗药物（candidate therapeutics）中，该标志物可准确预测其中4种的肾毒性。本研究针对毒性表型的相似性开展了网络分析，原文后续内容未完整呈现