Phenotype Classification of Zebrafish Embryos by Supervised Learning

Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances on embryo survival and development are generally evaluated manually through microscopic observation by an expert and documented by several typical photographs. Here, we present a methodology to automatically classify brightfield images of wildtype zebrafish embryos according to their defects by using an image analysis approach based on supervised machine learning. We show that, compared to manual classification, automatic classification results in 90 to 100% agreement with consensus voting of biological experts in nine out of eleven considered defects in 3 days old zebrafish larvae. Automation of the analysis and classification of zebrafish embryo pictures reduces the workload and time required for the biological expert and increases the reproducibility and objectivity of this classification.

[1]  Raphaël Marée,et al.  A rich internet application for remote visualization and collaborative annotation of digital slides in histology and cytology , 2013, Diagnostic Pathology.

[2]  Jeanne Garric,et al.  Development of a zebrafish 4-day embryo-larval bioassay to assess toxicity of chemicals. , 2006, Ecotoxicology and environmental safety.

[3]  T. Braunbeck,et al.  Zebrafish teratogenicity test with metabolic activation (mDarT): effects of phase I activation of acetaminophen on zebrafish Danio rerio embryos. , 2010, Toxicology.

[4]  P. Geurts,et al.  Random subwindows and extremely randomized trees for image classification in cell biology , 2007, BMC Cell Biology.

[5]  Robert Rallo,et al.  Automated Phenotype Recognition for Zebrafish Embryo Based In Vivo High Throughput Toxicity Screening of Engineered Nano-Materials , 2012, PloS one.

[6]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[7]  M. Kent,et al.  The State of the Art of the Zebrafish Model for Toxicology and Toxicologic Pathology Research—Advantages and Current Limitations , 2003, Toxicologic pathology.

[8]  Raphaël Marée,et al.  Automated processing of zebrafish imaging data: a survey. , 2013, Zebrafish.

[9]  Lixin Yang,et al.  Methyl mercury suppresses the formation of the tail primordium in developing zebrafish embryos. , 2010, Toxicological sciences : an official journal of the Society of Toxicology.

[10]  I. Velcheva,et al.  Effects of zinc on morphology of erythrocytes and spleen in Carassius gibelio. , 2008, Journal of environmental biology.

[11]  Melek Küçükoğlu,et al.  The effects of zinc chloride during early embryonic development in zebrafish ( Brachydanio rerio ) , 2013 .

[12]  K. Pancharatna,et al.  Effects of acetaminophen (paracetamol) in the embryonic development of zebrafish, Danio rerio , 2009, Journal of applied toxicology : JAT.

[13]  Mehmet Fatih Yanik,et al.  Fully automated cellular-resolution vertebrate screening platform with parallel animal processing. , 2011, Lab on a chip.

[14]  Michael Tsang,et al.  Automated image‐based phenotypic analysis in zebrafish embryos , 2009, Developmental dynamics : an official publication of the American Association of Anatomists.

[15]  Markus Reischl,et al.  Methods for Automated High-Throughput Toxicity Testing Using Zebrafish Embryos , 2010, KI.

[16]  Jiangfei Chen,et al.  Developmental lead acetate exposure induces embryonic toxicity and memory deficit in adult zebrafish. , 2012, Neurotoxicology and teratology.

[17]  T. Viraraghavan,et al.  Thallium: a review of public health and environmental concerns. , 2005, Environment international.

[18]  Wu Dong,et al.  Zebrafish as a novel experimental model for developmental toxicology , 2003, Congenital anomalies.

[19]  M. Westerfield The zebrafish book : a guide for the laboratory use of zebrafish (Danio rerio) , 1995 .

[20]  L. Zon,et al.  Zebrafish: a model system for the study of human disease. , 2000, Current opinion in genetics & development.

[21]  J. Martial,et al.  A panel of biological tests reveals developmental effects of pharmaceutical pollutants on late stage zebrafish embryos. , 2012, Reproductive toxicology.

[22]  J. Dowling,et al.  Small molecule developmental screens reveal the logic and timing of vertebrate development. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[23]  H. Harn,et al.  The toxic effect of Amiodarone on valve formation in the developing heart of zebrafish embryos. , 2012, Reproductive toxicology.

[24]  L Shamir,et al.  Assessing the efficacy of low‐level image content descriptors for computer‐based fluorescence microscopy image analysis , 2011, Journal of microscopy.

[25]  Raphaël Marée,et al.  Automatic Localization of Interest Points in Zebrafish Images with Tree-Based Methods , 2011, PRIB.

[26]  Ying Cao,et al.  Chemical modifier screen identifies HDAC inhibitors as suppressors of PKD models , 2009, Proceedings of the National Academy of Sciences.

[27]  Donald R Love,et al.  Technology for high-throughput screens: the present and future using zebrafish. , 2004, Current opinion in biotechnology.

[28]  Ben S. Wittner,et al.  Association of valproate‐induced teratogenesis with histone deacetylase inhibition in vivo , 2005, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[29]  Lior Shamir,et al.  Pattern Recognition Software and Techniques for Biological Image Analysis , 2010, PLoS Comput. Biol..

[30]  C. Kimmel,et al.  Stages of embryonic development of the zebrafish , 1995, Developmental dynamics : an official publication of the American Association of Anatomists.

[31]  Mingyao Liu,et al.  Zebrafish cancer and metastasis models for in vivo drug discovery. , 2013, Drug discovery today. Technologies.

[32]  Gabryelak Teresa,et al.  Carp erythrocyte lipids as a potential target for the toxic action of zinc ions. , 2002, Toxicology letters.

[33]  Stephen T. C. Wong,et al.  Phenotypic analysis of images of zebrafish treated with Alzheimer's γ-secretase inhibitors , 2010, BMC biotechnology.

[34]  Mehmet Fatih Yanik,et al.  High-throughput hyperdimensional vertebrate phenotyping , 2013, Nature Communications.