Ng Alvin Y J, Rajapakse Jagath C, Welsch Roy E, Matsudaira Paul T, Horodincu Victor, Evans James G
Singapore MIT Alliance, Singapore.
J Biomol Screen. 2010 Aug;15(7):858-68. doi: 10.1177/1087057110372256. Epub 2010 Jun 4.
The authors present an unsupervised, scalable, and interpretable cell profiling framework that is compatible with data gathered from high-content screening. They demonstrate the effectiveness of their framework by modeling drug differential effects of IC-21 macrophages treated with microtubule and actin disrupting drugs. They identify significant features of cell phenotypes for unsupervised learning based on maximum relevancy and minimum redundancy criteria. A 2-stage clustering approach annotates, clusters cells, and then merges them together to form super-clusters. An interpretable cell profile consisting of super-cluster proportions profiled at each drug treatment, concentration, or duration is obtained. Differential changes in super-cluster profiles are the basis for understanding the drug's differential effect and biology. The authors' method is validated by significant chi-squared statistics obtained from similar drug-treated super-cluster profiles from a 5-fold cross-validation. In addition, drug profiles of 2 microtubule drugs with equivalent mechanisms of action are statistically similar. Several distinct trends are identified for the 5 cytoskeletal drugs profiled under different conditions.
作者提出了一种无监督、可扩展且可解释的细胞分析框架，该框架与从高内涵筛选收集的数据兼容。他们通过对用微管和肌动蛋白破坏药物处理的IC-21巨噬细胞的药物差异效应进行建模，展示了其框架的有效性。他们基于最大相关性和最小冗余标准，为无监督学习识别细胞表型的显著特征。一种两阶段聚类方法对细胞进行注释、聚类，然后将它们合并在一起形成超级聚类。获得了一个由在每种药物处理、浓度或持续时间下分析的超级聚类比例组成的可解释细胞图谱。超级聚类图谱中的差异变化是理解药物差异效应和生物学的基础。作者的方法通过从5折交叉验证中类似药物处理的超级聚类图谱获得的显著卡方统计量得到验证。此外，两种作用机制相同的微管药物的药物图谱在统计学上相似。在不同条件下分析的5种细胞骨架药物确定了几个不同的趋势。
