Leaf-GP: an open and automated software application for measuring growth phenotypes for arabidopsis and wheat

BackgroundPlants demonstrate dynamic growth phenotypes that are determined by genetic and environmental factors. Phenotypic analysis of growth features over time is a key approach to understand how plants interact with environmental change as well as respond to different treatments. Although the importance of measuring dynamic growth traits is widely recognised, available open software tools are limited in terms of batch image processing, multiple traits analyses, software usability and cross-referencing results between experiments, making automated phenotypic analysis problematic.ResultsHere, we present Leaf-GP (Growth Phenotypes), an easy-to-use and open software application that can be executed on different computing platforms. To facilitate diverse scientific communities, we provide three software versions, including a graphic user interface (GUI) for personal computer (PC) users, a command-line interface for high-performance computer (HPC) users, and a well-commented interactive Jupyter Notebook (also known as the iPython Notebook) for computational biologists and computer scientists. The software is capable of extracting multiple growth traits automatically from large image datasets. We have utilised it in Arabidopsis thaliana and wheat (Triticum aestivum) growth studies at the Norwich Research Park (NRP, UK). By quantifying a number of growth phenotypes over time, we have identified diverse plant growth patterns between different genotypes under several experimental conditions. As Leaf-GP has been evaluated with noisy image series acquired by different imaging devices (e.g. smartphones and digital cameras) and still produced reliable biological outputs, we therefore believe that our automated analysis workflow and customised computer vision based feature extraction software implementation can facilitate a broader plant research community for their growth and development studies. Furthermore, because we implemented Leaf-GP based on open Python-based computer vision, image analysis and machine learning libraries, we believe that our software not only can contribute to biological research, but also demonstrates how to utilise existing open numeric and scientific libraries (e.g. Scikit-image, OpenCV, SciPy and Scikit-learn) to build sound plant phenomics analytic solutions, in a efficient and effective way.ConclusionsLeaf-GP is a sophisticated software application that provides three approaches to quantify growth phenotypes from large image series. We demonstrate its usefulness and high accuracy based on two biological applications: (1) the quantification of growth traits for Arabidopsis genotypes under two temperature conditions; and (2) measuring wheat growth in the glasshouse over time. The software is easy-to-use and cross-platform, which can be executed on Mac OS, Windows and HPC, with open Python-based scientific libraries preinstalled. Our work presents the advancement of how to integrate computer vision, image analysis, machine learning and software engineering in plant phenomics software implementation. To serve the plant research community, our modulated source code, detailed comments, executables (.exe for Windows; .app for Mac), and experimental results are freely available at https://github.com/Crop-Phenomics-Group/Leaf-GP/releases.

[1]  José Crossa,et al.  A multi-trait multi-environment QTL mixed model with an application to drought and nitrogen stress trials in maize (Zea mays L.) , 2008, Euphytica.

[2]  S. Tsaftaris,et al.  Phenotiki: an open software and hardware platform for affordable and easy image‐based phenotyping of rosette‐shaped plants , 2017, The Plant journal : for cell and molecular biology.

[3]  M. Stitt,et al.  Phytotyping(4D) : a light-field imaging system for non-invasive and accurate monitoring of spatio-temporal plant growth. , 2015, The Plant journal : for cell and molecular biology.

[4]  B. Mueller‐Roeber,et al.  A growth phenotyping pipeline for Arabidopsis thaliana integrating image analysis and rosette area modeling for robust quantification of genotype effects. , 2011, The New phytologist.

[5]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[6]  K. Jarrod Millman,et al.  Python for Scientists and Engineers , 2011, Comput. Sci. Eng..

[7]  Baskar Ganapathysubramanian,et al.  A real-time phenotyping framework using machine learning for plant stress severity rating in soybean , 2017, Plant Methods.

[8]  Debmalya Barh,et al.  PlantOmics: The Omics of Plant Science , 2015, Springer India.

[9]  Hanno Scharr,et al.  Machine Learning for Plant Phenotyping Needs Image Processing. , 2016, Trends in plant science.

[10]  Christine Faulkner,et al.  CalloseMeasurer: a novel software solution to measure callose deposition and recognise spreading callose patterns , 2012, Plant Methods.

[11]  W. Philips,et al.  Rosette Tracker: An Open Source Image Analysis Tool for Automatic Quantification of Genotype Effects1[C][W] , 2012, Plant Physiology.

[12]  François Tardieu,et al.  The growth of vegetative and reproductive structures (leaves and silks) respond similarly to hydraulic cues in maize. , 2016, The New phytologist.

[13]  Silke Robatzek,et al.  NB-LRR signaling induces translational repression of viral transcripts and the formation of RNA processing bodies through mechanisms differing from those activated by UV stress and RNAi. , 2016, Journal of experimental botany.

[14]  Daniel Parnham,et al.  LeafAnalyser: a computational method for rapid and large-scale analyses of leaf shape variation. , 2008, The Plant journal : for cell and molecular biology.

[15]  Astrid Junker,et al.  Optimizing experimental procedures for quantitative evaluation of crop plant performance in high throughput phenotyping systems , 2015, Front. Plant Sci..

[16]  Chi-Ren Shyu,et al.  PhenoPhyte: a flexible affordable method to quantify 2D phenotypes from imagery , 2012, Plant Methods.

[17]  Barbara George-Jaeggli,et al.  Stay-green alleles individually enhance grain yield in sorghum under drought by modifying canopy development and water uptake patterns. , 2014, The New phytologist.

[18]  Roderick Hunt,et al.  Relative growth-rate: its range and adaptive significance in a local flora. , 1975 .

[19]  G. Meyer,et al.  Verification of color vegetation indices for automated crop imaging applications , 2008 .

[20]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[21]  José Eduardo Krieger,et al.  Serum metabolomics profile of type 2 diabetes mellitus in a Brazilian rural population , 2016, Metabolomics.

[22]  Grégoire M. Hummel,et al.  LeasyScan: a novel concept combining 3D imaging and lysimetry for high-throughput phenotyping of traits controlling plant water budget , 2015, Journal of experimental botany.

[23]  H. Scharr,et al.  The leaf angle distribution of natural plant populations: assessing the canopy with a novel software tool , 2015, Plant Methods.

[24]  Julie Johnson.  What is the Rational Unified Process ? , 1999 .

[25]  F. P. Preparata,et al.  Convex hulls of finite sets of points in two and three dimensions , 1977, CACM.

[26]  Ben Scheres,et al.  The plant perceptron connects environment to development , 2017, Nature.

[27]  Patrick Achard,et al.  Integration of Plant Responses to Environmentally Activated Phytohormonal Signals , 2006, Science.

[28]  Wilfried Philips,et al.  Quantitative analysis of venation patterns of Arabidopsis leaves by supervised image analysis. , 2012, The Plant journal : for cell and molecular biology.

[29]  M. M. Christ,et al.  Dynamics of seedling growth acclimation towards altered light conditions can be quantified via GROWSCREEN: a setup and procedure designed for rapid optical phenotyping of different plant species. , 2007, The New phytologist.

[30]  Jan Flusser,et al.  Rotation Moment Invariants for Recognition of Symmetric Objects , 2006, IEEE Transactions on Image Processing.

[31]  E. Peli.  In search of a contrast metric: Matching the perceived contrast of gabor patches at different phases and bandwidths , 1997, Vision Research.

[32]  Harro Bouwmeester,et al.  OSCILLATOR: A system for analysis of diurnal leaf growth using infrared photography combined with wavelet transformation , 2012, Plant Methods.

[33]  B. S. Manjunath,et al.  Biological imaging software tools , 2012, Nature Methods.

[34]  Henning Redestig,et al.  rosettR: protocol and software for seedling area and growth analysis , 2017, Plant Methods.

[35]  William Valdar,et al.  Quantitative trait loci for energy balance traits in an advanced intercross line derived from mice divergently selected for heat loss , 2014, PeerJ.

[36]  Arnold J. Bloom,et al.  Easy Leaf Area: Automated digital image analysis for rapid and accurate measurement of leaf area1 , 2014, Applications in plant sciences.

[37]  Arezki Boudaoud,et al.  Multiscale quantification of morphodynamics: MorphoLeaf software for 2D shape analysis , 2016, Development.

[38]  D. Leister,et al.  Large-scale evaluation of plant growth in Arabidopsis thaliana by non-invasive image analysis , 1999 .

[39]  Simon Griffiths,et al.  CropQuant : An automated and scalable field phenotyping platform for crop 1 monitoring and trait measurements to facilitate breeding and digital agriculture , 2017 .

[40]  B. S. Manjunath,et al.  Color and texture descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[41]  Christine Faulkner,et al.  A Developmental Framework for Complex Plasmodesmata Formation Revealed by Large-Scale Imaging of the Arabidopsis Leaf Epidermis[W] , 2013, Plant Cell.

[42]  Hendrik Poorter,et al.  Avoiding bias in calculations of relative growth rate. , 2002, Annals of botany.

[43]  Karen J. Halliday,et al.  SPATULA Links Daytime Temperature and Plant Growth Rate , 2010, Current Biology.

[44]  Pavel Tomancak,et al.  Current challenges in open-source bioimage informatics , 2012, Nature Methods.

[45]  Maria Petrou,et al.  Image Processing: The Fundamentals: Petrou/Image Processing: The Fundamentals , 2010 .

[46]  K. Mclaren.  XIII—The Development of the CIE 1976 (L* a* b*) Uniform Colour Space and Colour‐difference Formula , 2008 .

[47]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.

[48]  D. MacLean,et al.  Spatio-Temporal Cellular Dynamics of the Arabidopsis Flagellin Receptor Reveal Activation Status-Dependent Endosomal Sorting[C][W] , 2012, Plant Cell.

[49]  Lutz Plümer,et al.  Low-Cost 3D Systems: Suitable Tools for Plant Phenotyping , 2014, Sensors.

[50]  Shih-Fu Chang,et al.  Single color extraction and image query , 1995, Proceedings., International Conference on Image Processing.

[51]  A. Greenberg,et al.  High-Resolution Inflorescence Phenotyping Using a Novel Image-Analysis Pipeline, PANorama1[W][OPEN] , 2014, Plant Physiology.

[52]  Maria Petrou,et al.  Image processing - the fundamentals , 1999 .

[53]  Philippe Lucidarme,et al.  On the use of depth camera for 3D phenotyping of entire plants , 2012 .

[54]  Jan Vos,et al.  The contribution of phenotypic plasticity to complementary light capture in plant mixtures. , 2015, The New phytologist.

[55]  Christian Klukas,et al.  Integrated Analysis Platform: An Open-Source Information System for High-Throughput Plant Phenotyping1[C][W][OPEN] , 2014, Plant Physiology.

[56]  Christine M. Palmer,et al.  LeafJ: an ImageJ plugin for semi-automated leaf shape measurement. , 2013, Journal of visualized experiments : JoVE.

[57]  Peter Eckes,et al.  An automated quantitative image analysis tool for the identification of microtubule patterns in plants , 2017, Traffic.

[58]  Yuhua Jiao,et al.  Functional approach to high-throughput plant growth analysis , 2013, BMC Systems Biology.

[59]  Pavel Senin,et al.  A Point Mutation in Suppressor of Cytokine Signalling 2 (Socs2) Increases the Susceptibility to Inflammation of the Mammary Gland while Associated with Higher Body Weight and Size and Higher Milk Production in a Sheep Model , 2015, PLoS genetics.

[60]  G. E. Briggs,et al.  METHODS AND SIGNIFICANT RELATIONS IN THE QUANTITATIVE ANALYSIS OF PLANT GROWTH. , 1920 .

[61]  Achim Walter,et al.  An image analysis pipeline for automated classification of imaging light conditions and for quantification of wheat canopy cover time series in field phenotyping , 2017, Plant Methods.

[62]  Matej Oresic,et al.  Data standards can boost metabolomics research, and if there is a will, there is a way , 2015, Metabolomics.

[63]  J. Görlach,et al.  Growth Stage–Based Phenotypic Analysis of Arabidopsis , 2001, The Plant Cell Online.

[64]  H. Scharr,et al.  Simultaneous phenotyping of leaf growth and chlorophyll fluorescence via GROWSCREEN FLUORO allows detection of stress tolerance in Arabidopsis thaliana and other rosette plants. , 2009, Functional plant biology : FPB.

[65]  Jarkko Salojärvi,et al.  Large-Scale Phenomics Identifies Primary and Fine-Tuning Roles for CRKs in Responses Related to Oxidative Stress , 2015, PLoS genetics.