Harder N, Eils R, Rohr K
Department of Bioinformatics and Functional Genomics, German Cancer Research Center (DKFZ), University of Heidelberg, IPMB Im Neuenheimer Feld 267, D-69120 Heidelberg, Germany.
Methods Cell Biol. 2008;85:539-54. doi: 10.1016/S0091-679X(08)85023-6.
High-throughput screens of the gene function provide rapidly increasing amounts of data. In particular, the analysis of image data acquired in genome-wide cell phenotype screens constitutes a substantial bottleneck in the evaluation process and motivates the development of automated image analysis tools for large-scale experiments. In this chapter, we present a computational scheme to process multicell time-lapse images as they are produced in high-throughput screens. We describe an approach to automatically segment and classify cell nuclei into different mitotic phenotypes. This enables automated identification of cell cultures that show an abnormal mitotic behavior. Our scheme proves high classification accuracy, suggesting a promising future for automating the evaluation of high-throughput experiments.
基因功能的高通量筛选产生的数据量正在迅速增加。特别是，在全基因组细胞表型筛选中获取的图像数据分析构成了评估过程中的一个重大瓶颈，并推动了用于大规模实验的自动化图像分析工具的开发。在本章中，我们提出了一种计算方案，用于处理高通量筛选中产生的多细胞延时图像。我们描述了一种自动分割细胞核并将其分类为不同有丝分裂表型的方法。这使得能够自动识别表现出异常有丝分裂行为的细胞培养物。我们的方案证明了高分类准确率，为高通量实验评估的自动化展现出了光明的前景。
