Machine learning improves the precision and robustness of high-content screens: using nonlinear multiparametric methods to analyze screening results

J Biomol Screen. 2011 Oct;16(9):1059-67. doi: 10.1177/1087057111414878. Epub 2011 Aug 1.

Abstract

Imaging-based high-content screens often rely on single cell-based evaluation of phenotypes in large data sets of microscopic images. Traditionally, these screens are analyzed by extracting a few image-related parameters and use their ratios (linear single or multiparametric separation) to classify the cells into various phenotypic classes. In this study, the authors show how machine learning-based classification of individual cells outperforms those classical ratio-based techniques. Using fluorescent intensity and morphological and texture features, they evaluated how the performance of data analysis increases with increasing feature numbers. Their findings are based on a case study involving an siRNA screen monitoring nucleoplasmic and nucleolar accumulation of a fluorescently tagged reporter protein. For the analysis, they developed a complete analysis workflow incorporating image segmentation, feature extraction, cell classification, hit detection, and visualization of the results. For the classification task, the authors have established a new graphical framework, the Advanced Cell Classifier, which provides a very accurate high-content screen analysis with minimal user interaction, offering access to a variety of advanced machine learning methods.

MeSH terms

  • Artificial Intelligence*
  • High-Throughput Screening Assays*
  • Models, Statistical*
  • Neural Networks, Computer
  • RNA, Small Interfering
  • Single-Cell Analysis

Substances

  • RNA, Small Interfering