Use of a Machine Learning-Based High Content Analysis Approach to Identify Photoreceptor Neurite Promoting Molecules

  • John A. FullerEmail author
  • Cynthia A. Berlinicke
  • James Inglese
  • Donald J. Zack
Conference paper
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 854)


High content analysis (HCA) has become a leading methodology in phenotypic drug discovery efforts. Typical HCA workflows include imaging cells using an automated microscope and analyzing the data using algorithms designed to quantify one or more specific phenotypes of interest. Due to the richness of high content data, unappreciated phenotypic changes may be discovered in existing image sets using interactive machine-learning based software systems. Primary postnatal day four retinal cells from the photoreceptor (PR) labeled QRX-EGFP reporter mice were isolated, seeded, treated with a set of 234 profiled kinase inhibitors and then cultured for 1 week. The cells were imaged with an Acumen plate-based laser cytometer to determine the number and intensity of GFP-expressing, i.e. PR, cells. Wells displaying intensities and counts above threshold values of interest were re-imaged at a higher resolution with an INCell2000 automated microscope. The images were analyzed with an open source HCA analysis tool, PhenoRipper (Rajaram et al., Nat Methods 9:635–637, 2012), to identify the high GFP-inducing treatments that additionally resulted in diverse phenotypes compared to the vehicle control samples. The pyrimidinopyrimidone kinase inhibitor CHEMBL-1766490, a pan kinase inhibitor whose major known targets are p38α and the Src family member lck, was identified as an inducer of photoreceptor neuritogenesis by using the open-source HCA program PhenoRipper. This finding was corroborated using a cell-based method of image analysis that measures quantitative differences in the mean neurite length in GFP expressing cells. Interacting with data using machine learning algorithms may complement traditional HCA approaches by leading to the discovery of small molecule-induced cellular phenotypes in addition to those upon which the investigator is initially focusing.


Photoreceptor Neuritogenesis Imaging qHTS High content analysis Machine learning Phenotypic screening Protein kinase Inhibitor 


  1. Altschuler SJ, Wu LF (2010) Cellular heterogeneity: do differences make a difference? Cell 141:559–563CrossRefPubMedPubMedCentralGoogle Scholar
  2. Aouadi M, Bost F, Caron L et al (2006) p38 mitogen-activated protein kinase activity commits embryonic stem cells to either neurogenesis or cardiomyogenesis. Stem Cells 24:1399–1406CrossRefPubMedGoogle Scholar
  3. Burrell RA, McGranahan N, Bartek J et al (2013) The causes and consequences of genetic heterogeneity in cancer evolution. Nature 501:338–345CrossRefPubMedGoogle Scholar
  4. Carpenter AE, Jones TR, Lamprecht MR et al (2006) CellProfiler: image analysis software for identifying and quantifying cell phenotypes. Genome Biol 7:R100CrossRefPubMedPubMedCentralGoogle Scholar
  5. Csurka G, Dance C, Fan L et al (2004) Visual categorization with bags of keypoints. Proc Workshop Statistical Learning Comput Vis 1:22Google Scholar
  6. Fuller JA, Shaw GC, Bonnet-Wersinger D et al (2014) A high content screening approach to identify molecules neuroprotective for photoreceptor cells. Adv Exp Med Biol 801:773–781CrossRefPubMedPubMedCentralGoogle Scholar
  7. Goldstein DM et al (2011) Discovery of 6-(2,4-difluorophenoxy)-2-[3-hydroxy-1-(2-hydroxyethyl)propylamino]– 8-methyl-8H-p yrido[2,3-d]pyrimidin-7-one (pamapimod) and 6-(2,4-difluorophenoxy)-8-methyl-2-(tetrahydro-2H-pyran-4-ylamino)pyrido[2,3-d]py rimidin-7(8H)-one (R1487) as orally bioavailable and highly selective inhibitors of p38alpha mitogen-activated protein kinase. J Med Chem 54:2255–2265CrossRefPubMedGoogle Scholar
  8. Gough AH, Chen N, Shun TY et al (2014) Identifying and quantifying heterogeneity in high content analysis: application of heterogeneity indices to drug discovery. PLoS One 9:e102678CrossRefPubMedPubMedCentralGoogle Scholar
  9. Held M, Schmitz MH, Fischer B et al (2010) CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging. Nat Methods 7:747–754CrossRefPubMedGoogle Scholar
  10. Huang S (2009) Non-genetic heterogeneity of cells in development: more than just noise. Development 136:3853–3862CrossRefPubMedPubMedCentralGoogle Scholar
  11. Iwasaki S, Iguchi M, Watanabe K et al (1999) Specific activation of the p38 mitogen-activated protein kinase signaling pathway and induction of neurite outgrowth in PC12 cells by bone morphogenetic protein-2. J Biol Chem 274:26503–26510CrossRefPubMedGoogle Scholar
  12. Morooka T, Nishida E (1998) Requirement of p38 mitogen-activated protein kinase for neuronal differentiation in PC12 cells. J Biol Chem 273:24285–24288CrossRefPubMedGoogle Scholar
  13. Rajaram S, Pavie B, Wu LF et al (2012) PhenoRipper: software for rapidly profiling microscopy images. Nat Methods 9:635–637CrossRefPubMedGoogle Scholar
  14. Sommer C, Strähle C, Köthe U, Hamprecht FA (2011) in: Eighth IEEE International Symposium on Biomedical Imaging (ISBI). Proceedings, 230–233Google Scholar
  15. Wang QL, Chen S, Esumi N et al (2004) QRX, a novel homeobox gene, modulates photoreceptor gene expression. Hum Mol Genet 13:1025–1040CrossRefPubMedGoogle Scholar
  16. Welsbie DS et al (2013) Functional genomic screening identifies dual leucine zipper kinase as a key mediator of retinal ganglion cell death. Proc Natl Acad Sci U S A 110:4045–4050CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • John A. Fuller
    • 1
    Email author
  • Cynthia A. Berlinicke
    • 1
  • James Inglese
    • 2
  • Donald J. Zack
    • 1
  1. 1.Ophthalmology, Molecular Biology & Genetics, Neuroscience, and Institute of Genetic MedicineWilmer Eye Institute, Johns Hopkins University School of MedicineBaltimoreUSA
  2. 2.NCATS, NHGRINational Institutes of HealthRockvilleUSA

Personalised recommendations