Clustering phenotype populations by genome‐wide RNAi and multiparametric imaging

Abstract

How to predict gene function from phenotypic cues is a longstanding question in biology.Using quantitative multiparametric imaging, RNAi-mediated cell phenotypes were measured on a genome-wide scale.On the basis of phenotypic ‘neighbourhoods', we identified previously uncharacterized human genes as mediators of the DNA damage response pathway and the maintenance of genomic integrity.The phenotypic map is provided as an online resource at http://www.cellmorph.org for discovering further functional relationships for a broad spectrum of biological module

Widespread genetic epistasis among cancer genes

“…Connected regions that are larger than 4,000 pixels in the nucleus channel were removed from subsequent processing in all three channels. Nuclei and cell segmentations were performed following the protocols described in Fuchs et al 54 The images were first normalized for better segmentation while the raw images were kept for raw intensity calculation. Nuclei were segmented by adaptive thresholding of the DNA channel with the threshold set to 0.01.…”

“…Cell masks were calculated by using the summation of the actin, tubulin and DNA channel signals. Cell boundaries were then separated by location of the nucleus by using the Voronoi segmentation algorithm through the 'propagate' function incorporated in EBImage 54 . Cells that were too large (4145,000 pixels), too small (o150 pixels), too dark (average intensity o0.1) or too close to the border (edge/peripheral length 40.3) were removed as artefacts.…”

Machine learning in cell biology – teaching computers to recognize phenotypes

“…Supervised machine learning has been an important backbone for analysis pipelines in many high-content screening projects Machine learning in cell biology 5533 (Kittler et al, 2007;Fuchs et al, 2010;Neumann et al, 2010;Schmitz et al, 2010;Mercer et al, 2012). The strengths of supervised machine learning are intuitive assay development based on examples, the versatility and applicability to diverse assays, and efficient and robust computation of large datasets.…”

“…The simplest implementation is a linear decision boundary (or a hyperplane in high-dimensional feature space). Linear discriminant methods are very robust towards noise in the data, yet their decision boundaries cannot accurately discriminate objects of different classes if they are distributed in complex patterns, such as typically observed for cell morphologies (Meyer et al, 2003;Loo et al, 2007;Fuchs et al, 2010;Held et al, 2010;Neumann et al, 2010). Most discriminant methods used in cell biological applications, therefore, use non-linear classifiers, which can express more complex decision boundaries.…”

“…This type of learning is termed 'supervised' machine learning, and its principal goal is to infer general properties of the data distribution from a few annotated examples (Hastie et al, 2005;Bishop, 2006;Tarca et al, 2007;de Ridder et al, 2013). Supervised machine learning has been successfully applied in diverse biological disciplines, such as high-content screening (Kittler et al, 2004;Lansing Taylor et al, 2007;Doil et al, 2009;Collinet et al, 2010;Fuchs et al, 2010;Neumann et al, 2010;Schmitz et al, 2010;Mercer et al, 2012), drug development (Perlman et al, 2004;Slack et al, 2008;Loo et al, 2009;Castoreno et al, 2010;Murphy, 2011), DNA sequence analysis (Castelo and Guigó, 2004;Ben-Hur et al, 2008) and proteomics (Yang and Chou, 2004;Datta and Pihur, 2010;Reiter et al, 2011), as well as in many other fields outside of biology, such as speech (Rabiner, 1989) and face recognition (Viola and Jones, 2004), and prediction of stock market trends (Kim, 2003).…”