Amy Watson, Sreya Ghosh, Matthew J Williams, William S. Cuddy, James Simmonds, María-Dolores Rey, M. Asyraf Md. Hatta, Alison Hinchliffe, Andrew Steed, Daniel Reynolds, Nikolai Adamski, Andy Breakspear, Andrey Korolev, Tracey Rayner, Laura E. Dixon, Adnan Riaz, William Martin, Merrill Ryan, David Edwards, Jacqueline Batley, Harsh Raman, Christian Rogers, Claire Domoney, Graham Moore, Wendy Harwood, Paul Nicholson, Mark J. Dieters, Ian H. DeLacy, Ji Zhou, Cristobal Uauy, Scott A. Boden, Robert F. Park, Brande B. H. Wulff, Lee T. Hickey

The growing human population and a changing environment have raised significant concern for global food security, with the current improvement rate of several important crops inadequate to meet future demand [1]. This slow improvement rate is attributed partly to the long generation times of crop plants. Here we present a method called 'speed breeding', which greatly shortens generation time and accelerates breeding and research programs. Speed breeding can be used to achieve up to 6 generations per year for spring wheat (Triticum aestivum), durum wheat (T. durum), barley (Hordeum vulgare), chickpea (Cicer arietinum), and pea (Pisum sativum) and 4 generations for canola (Brassica napus), instead of 2-3 under normal glasshouse conditions. We demonstrate that speed breeding in fully-enclosed controlled-environment growth chambers can accelerate plant development for research purposes, including phenotyping of adult plant traits, mutant studies, and transformation. The use of supplemental lighting in a glasshouse environment allows rapid generation cycling through single seed descent and potential for adaptation to larger-scale crop improvement programs. Cost-saving through LED supplemental lighting is also outlined. We envisage great potential for integrating speed breeding with other modern crop breeding technologies, including high-throughput genotyping, genome editing, and genomic selection, accelerating the rate of crop improvement.

Gozde S. Demirer, Huan Zhang, Juliana L Matos, Natalie Goh, Francis Cunningham, Younghun Sung, Roger Chang, Abhishek J Aditham, Linda Chio, Myeong-Je Cho, Brian Staskawicz, Markita P. Landry

Genetic engineering of plants is at the core of sustainability efforts, natural product synthesis, and agricultural crop engineering. The plant cell wall is a barrier that limits the ease and throughput with which exogenous biomolecules can be delivered to plants. Current delivery methods either suffer from host range limitations, low transformation efficiencies, tissue damage, or unavoidable DNA integration into the host genome. Here, we demonstrate efficient diffusion-based biomolecule delivery into tissues and organs of intact plants of several species with a suite of pristine and chemically-functionalized high aspect ratio nanomaterials. Efficient DNA delivery and strong protein expression without transgene integration is accomplished in Nicotiana benthamiana (Nb), Eruca sativa (arugula), Triticum aestivum (wheat) and Gossypium hirsutum (cotton) leaves and arugula protoplasts. We also demonstrate a second nanoparticle-based strategy in which small interfering RNA (siRNA) is delivered to Nb leaves and silence a gene with 95% efficiency. We find that nanomaterials not only facilitate biomolecule transport into plant cells but also protect polynucleotides from nuclease degradation. Our work provides a tool for species-independent and passive delivery of genetic material, without transgene integration, into plant cells for diverse biotechnology applications.

Ryan C Lynch, Daniela Vergara, Silas Tittes, Kristin White, C.J. Schwartz, Matthew J Gibbs, Travis C Ruthenburg, Kymron deCesare, Donald P Land, Nolan C Kane

Plants of the Cannabis genus are the only producers of phytocannabinoids, terpenoid compounds that strongly interact with evolutionarily ancient endocannabinoid receptors shared by most bilaterian taxa. For millennia, the plant has been cultivated for these compounds, but also for food, rope, paper, and clothing. Today, specialized varieties yielding high-quality textile fibers, nutritional seed oil or high cannabinoid content are cultivated across the globe. However, the genetic identities and histories of these diverse populations remain largely obscured. We analyzed the nuclear genomic diversity among 340 Cannabis varieties, including fiber and seed oil hemp, high cannabinoid drug-types and feral populations. These analyses demonstrate the existence of at least three major groups of diversity, with European hemp varieties more closely related to narrow leaflet drug-types (NLDT) than to broad leaflet drug-types (BLDT). The BLDT group appears to encompass less diversity than the NLDT, which reflects the larger geographic range of NLDTs, and suggests a more recent origin of domestication of the BLDTs. As well as being genetically distinct, hemp, NLDT and BLDT genetic groups each produce unique cannabinoid and terpenoid content profiles. This combined analysis of population genomic and trait variation informs our understanding of the potential uses of different genetic variants for medicine and agriculture, providing valuable insights and tools for a rapidly emerging, valuable legal industry

Akihiro Shimokawa, Yuki Tonooka, Misato Matsumoto, Hironori Ara, Hiroshi Suzuki, Naoki Yamauchi, Masayoshi Shigyo

Because global climate change has made agricultural supply unstable, plant factories are expected to be a safe and stable means of food production. As the light source of a plant factory or controlled greenhouse, the light emitting diode (LED) is expected to solve cost problems and promote plant growth efficiently. In this study, we examined the light condition created by using monochromatic red and blue LEDs, to provide both simultaneous and alternating irradiation to leaf lettuce. The result was that simultaneous red and blue irradiation promoted plant growth more effectively than monochromatic and fluorescent light irradiation. Moreover, alternating red and blue light accelerated plant growth significantly even when the total light intensity per day was the same as with simultaneous irradiation. The fresh weight in altering irradiation was almost two times higher than with fluorescent light and about 1.6 times higher than with simultaneous irradiation. The growth-promoting effect of alternating irradiation of red and blue light was observed in different cultivars. From the results of experiments, we offer a novel plant growth method named "Shigyo Method", the core concept of which is the alternating irradiation of red and blue light.

Daniela Paula de Toledo Thomazella, Quinton Brail, Douglas Dahlbeck, Brian Staskawicz

Pathogenic microbes are responsible for severe production losses in crops worldwide. The use of disease resistant crop varieties can be a sustainable approach to meet the food demand of the world's growing population. However, classical plant breeding is usually laborious and time-consuming, thus hampering efficient improvement of many crops. With the advent of genome editing technologies, in particular the CRISPR-Cas9 (clustered regularly interspaced short palindromic repeats-Cas9) system, we are now able to introduce improved crop traits in a rapid and efficient manner. In this work, we genome edited durable disease resistance in tomato by modifying a specific gene associated with disease resistance. Recently, it was demonstrated that inactivation of a single gene called DMR6 (downy mildew resistance 6) confers resistance to several pathogens in Arabidopsis thaliana. This gene is specifically up-regulated during pathogen infection, and mutations in the dmr6 gene results in increased salicylic acid levels. The tomato SlDMR6-1 orthologue Solyc03g080190.2 is also up-regulated during infection by Pseudomonas syringae pv. tomato and Phytophthora capsici. Using the CRISPR/Cas-9 system, we generated tomato plants with small deletions in the SlDMR6-1 gene that result in frameshift and premature truncation of the protein. Remarkably, these mutants do not have significant detrimental effects in terms of growth and development under greenhouse conditions and show disease resistance against different pathogens, including P. syringae, P. capsici and Xanthomonas spp.

Cara Doyle, Katie Higginbottom, Thomas A Swift, Mark Winfield, Christopher Bellas, David Benito-Alifonso, Taryn Fletcher, Carmen M Galan, Keith Edwards, Heather M Whitney

Potential innovation in Plant research using gene-edited and genetically modified plants is currently being hindered by inefficient and costly plant transformation. We show that carbon dots formed from natural materials (quasi-spherical, <10nm nanoparticles) can act as a fast vehicle for carrying plasmids into mature plant cells, resulting in transient plant transformation in a number of important crop species with no negative impacts on photosynthesis or growth. We further show that GFP, Cas9, and gRNA introduced into wheat via foliar application (spraying on) of plasmid coated carbon dots are expressed and, in the case of Cas9, make genome edits in SPO11 genes. Therefore, we present a protocol for spray-on gene editing that is simple, inexpensive, fast, transforms in planta , and is applicable to multiple crop species. We believe this technique creates many opportunities for the future of plant transformation in research and shows great promise for plant protein production systems.

Sreya Ghosh, Amy Watson, Oscar E. Gonzalez-Navarro, Ricardo H. Ramirez-Gonzalez, Luis Yanes, Marcela Mendoza-Suárez, James Simmonds, Rachel Wells, Tracey Rayner, Phon Green, Amber Hafeez, Sadiye Hayta, Rachel E. Melton, Andrew Steed, Abhimanyu Sarkar, Jeremy Carter, Lionel Perkins, John Lord, Mark Tester, Anne Osbourn, Matthew J Moscou, Paul Nicholson, Wendy Harwood, Cathie Martin, Claire Domoney, Cristobal Uauy, Brittany Hazard, Brande B. H. Wulff, Lee T. Hickey

To meet the challenge of feeding a growing population, breeders and scientists are continuously looking for ways to increase genetic gain in crop breeding. One way this can be achieved is through 'speed breeding' (SB), which shortens the breeding cycle and accelerates research studies through rapid generation advancement. The SB method can be carried out in a number of ways, one of which involves extending the duration of a plant's daily exposure to light (photoperiod) combined with early seed harvest in order to cycle quickly from seed to seed, thereby reducing the generation times for some long-day (LD) or day-neutral crops. Here we present glasshouse and growth chamber-based SB protocols with supporting data from experimentation with several crop species. These protocols describe the growing conditions, including soil media composition, lighting, temperature and spacing, which promote rapid growth of spring and winter bread wheat, durum wheat, barley, oat, various members of the Brassica family, chickpea, pea, grasspea, quinoa and the model grass Brachypodium distachyon. Points of flexibility within the protocols are highlighted, including how plant density can be increased to efficiently scale-up plant numbers for single seed descent (SSD) purposes. Conversely, instructions on how to perform SB on a small-scale by creating a benchtop SB growth cabinet that enables optimization of parameters at a low cost are provided. We also outline the procedure for harvesting and germinating premature wheat, barley and pea seed to reduce generation time. Finally, we provide troubleshooting suggestions to avoid potential pitfalls.

Christine N Shulse, Benjamin J Cole, Gina M Turco, Yiwen Zhu, Siobhan M. Brady, Diane E. Dickel

Single-cell transcriptome analysis of heterogeneous tissues can provide high-resolution windows into the genomic basis and spatiotemporal dynamics of developmental processes. Here we demonstrate the feasibility of high-throughput single-cell RNA sequencing of plant tissue using the Drop-seq approach. Profiling of >4,000 individual cells from the Arabidopsis root provides transcriptomes and marker genes for a diversity of cell types and illuminates the gene expression changes that occur across endodermis development.

Kelsey A. Maher, Marko Bajic, Kaisa Kajala, Mauricio Reynoso, Germain Pauluzzi, Donnelly A. West, Kristina Zumstein, Margaret Woodhouse, Kerry Bubb, Michael W Dorrity, Christine Queitsch, Julia Bailey-Serres, Neelima Sinha, Siobhan M. Brady, Roger B. Deal

The transcriptional regulatory structure of plant genomes remains poorly defined relative to animals. It is unclear how many cis-regulatory elements exist, where these elements lie relative to promoters, and how these features are conserved across plant species. We employed the Assay for Transposase-Accessible Chromatin (ATAC-seq) in four plant species (Arabidopsis thaliana, Medicago truncatula, Solanum lycopersicum, and Oryza sativa) to delineate open chromatin regions and transcription factor (TF) binding sites across each genome. Despite 10-fold variation in intergenic space among species, the majority of open chromatin regions lie within 3 kb upstream of a transcription start site in all species. We find a common set of four TFs that appear to regulate conserved gene sets in the root tips of all four species, suggesting that TF-gene networks are generally conserved. Comparative ATAC-seq profiling of Arabidopsis root hair and non-hair cell types revealed extensive similarity as well as many cell type-specific differences. Analyzing TF binding sites in differentially accessible regions identified a MYB-driven regulatory module unique to the hair cell, which appears to control both cell fate regulators and abiotic stress responses. Our analyses revealed common regulatory principles among species and shed light on the mechanisms producing cell type-specific transcriptomes during development.

Margaret H Frank, Daniel H. Chitwood

Chimeras, organisms that are composed of cells of more than one genotype, captured the human imagination long before they were formally described and used in the laboratory. These organisms owe their namesake to a fire-breathing monster from Greek mythology that has the head of a lion, the body of a goat, and the tail of a serpent. The first description of a non-fictional chimera dates back to the middle of the seventeenth century when the Florentine gardener Pietro Nati discovered an adventitious shoot growing from the graft junction between sour orange (Citrus aurantium) and citron (C. medica). This perplexing chimera that grows with sectors phenotypically resembling each of the citrus progenitors inspired discussion and wonder from the scientific community and was fittingly named the Bizzaria. Initially, the Bizzaria was believed to be an asexual hybrid that formed from a cellular fusion between the grafted parents; however, in-depth cellular analyses carried out centuries later demonstrated that the Bizzaria, along with other chimeras, owe their unique sectored appearance to a conglomeration of cells from the two donors. Since this pivotal discovery at the turn of the twentieth century, chimeras have served both as tools and as unique biological phenomena that have contributed to our understanding of plant development at the cellular, tissue, and organismal level. Rapid advancements in genome sequencing technologies have enabled the establishment of new model species with novel morphological and developmental features that enable the generation of chimeric organisms. In this review, we show that genetic mosaic and chimera studies provide a technologically simple way to delve into the organismal, genetic, and genomic inner workings underlying the development of diverse model organisms. Moreover, we discuss the unique opportunity that chimeras present to explore universal principles governing intercellular communication and the coordination of organismal biology in a heterogenomic landscape.

Daniel von Wangenheim, Robert Hauschild, Matyáš Fendrych, Vanessa Barone, Jiří Friml

Roots navigate through soil integrating environmental signals to orient their growth. The Arabidopsis root is a widely used model for developmental, physiological and cell biological studies. Live imaging greatly aids these efforts, but the horizontal sample position and continuous root tip displacement present significant difficulties. Here, we develop a confocal microscope setup for vertical sample mounting and integrated directional illumination. We present TipTracker - a custom software for automatic tracking of diverse moving objects usable on various microscope setups. Combined, this enables observation of root tips growing along the natural gravity vector over prolonged periods of time, as well as the ability to induce rapid gravity or light stimulation. We also track migrating cells in the developing zebrafish embryo, demonstrating the utility of this system in the acquisition of high resolution data sets of dynamic samples. We provide detailed descriptions of the tools enabling the easy implementation on other microscopes.

Tatiana Mitiouchkina, Alexander S. Mishin, Louisa Gonzalez Somermeyer, Nadezhda M Markina, Tatiana V Chepurnyh, Elena B Guglya, Tatiana A Karataeva, Kseniia A Palkina, Ekaterina S Shakhova, Liliia I Fakhranurova, Sofia V Chekova, Aleksandra S Tsarkova, Yaroslav V Golubev, Vadim V Negrebetsky, Sergey A Dolgushin, Pavel V Shalaev, Olesya A Melnik, Victoria O Shipunova, Sergey M Deyev, Andrey I Bubyrev, Alexander S Pushin, Vladimir V Choob, Sergey V Dolgov, Fyodor A Kondrashov, Ilia V Yampolsky, Karen S. Sarkisyan

In contrast to fluorescent proteins, light emission from luciferase reporters requires exogenous addition of a luciferin substrate. Bacterial bioluminescence has been the single exception, where an operon of five genes is sufficient to produce light autonomously. Although commonly used in prokaryotic hosts, toxicity of the aldehyde substrate has limited its use in eukaryotes. Here we demonstrate autonomous luminescence in a multicellular eukaryotic organism by incorporating a recently discovered fungal bioluminescent system into tobacco plants. We monitored these light-emitting plants from germination to flowering, observing temporal and spatial patterns of luminescence across time scales from seconds to months. The dynamic patterns of luminescence reflected progression through developmental stages, circadian oscillations, transport, and response to injuries. As with other fluorescent and luminescent reporters, we anticipate that this system will be further engineered for varied purposes, especially where exogenous addition of substrate is undesirable.

Anton Sharakshane

The highest intensity of photosynthesis is obtained under red light, but plants die or their growth gets disrupted if only red light is used. For example, Korean researchers have shown that under pure red light the amount of the grown lettuce is greater than under a combination of red and blue light, but the leaves have a significantly smaller amount of chlorophyll, polyphenols and antioxidants. And the researchers at the Faculty of Biology of the Moscow State University have found that the synthesis of sugars is reduced, growth is inhibited and no blossoming occurs in the leaves of Chinese cabbage under narrow-band red and blue light (as compared to a sodium lamp). What kind of lighting is needed to get a fully developed, large, fragrant and tasty plant with moderate energy consumption?

Kevin J McKernan

Cannabinoid expression is an important genetically determined feature of cannabis that presents clinical and legal implications for patients seeking cannabinoid specific therapies like Cannabidiol (CBD). Cannabinoid, terpenoid, and flavonoid marker assisted selection can accelerate breeding efforts by offering genetic tools to select for desired traits at an early stage in growth. To this end, multiple models for chemotype inheritance have been described suggesting a complex picture for chemical phenotype determination. Here we explore the potential role of copy number variation of THCA Synthase using phased single molecule sequencing and demonstrate that copy number and sequence variation of this gene is common and suggests a more nuanced view of chemotype prediction.

Namrata Sarkar, Emanuel Schmid-Siegert, Christian Iseli, Sandra Calderon, Caroline Gouhier-Darimont, Jacqueline Chrast, Pietro Cattaneo, Frédéric Schütz, Laurent Farinelli, Marco Pagni, Michel Schneider, Jérémie Voumard, Michel Jaboyedoff, Christian Fankhauser, Christian S. Hardtke, Laurent Keller, John R. Pannell, Alexandre Reymond, Marc Robinson-Rechavi, Ioannis Xenarios, Philippe Reymond

Because plants do not possess a proper germline, deleterious somatic mutations can be passed to gametes and a large number of cell divisions separating zygote from gamete formation in long-lived plants may lead to many mutations. We sequenced the genome of two terminal branches of a 234-year-old oak tree and found few fixed somatic single-nucleotide variants (SNVs), whose sequential appearance in the tree could be traced along nested sectors of younger branches. Our data suggest that stem cells of shoot meristems are robustly protected from accumulation of mutations in trees.

Mao Li, Hong An, Ruthie Angelovici, Clement Bagaza, Albert Batushansky, Lynn Clark, Viktoriya Coneva, Michael Donoghue, Erika Edwards, Diego Fajardo, Hui Fang, Margaret Frank, Timothy Gallaher, Sarah Gebken, Theresa Hill, Shelley Jansky, Baljinder Kaur, Philip Klahs, Laura Klein, Vasu Kuraparthy, Jason Londo, Zoë Migicovsky, Allison Miller, Rebekah Mohn, Sean Myles, Wagner Otoni, J. Chris Pires, Edmond Riffer, Sam Schmerler, Elizabeth Spriggs, Christopher Topp, Allen Van Deynze, Kuang Zhang, Linglong Zhu, Braden M. Zink, Daniel H. Chitwood

Current morphometric methods that comprehensively measure shape cannot compare the disparate leaf shapes found in seed plants and are sensitive to processing artifacts. We explore the use of persistent homology, a topological method applied across the scales of a function, to overcome these limitations. The described method isolates subsets of shape features and measures the spatial relationship of neighboring pixel densities in a shape. We apply the method to the analysis of 182,707 leaves, both published and unpublished, representing 141 plant families collected from 75 sites throughout the world. By measuring leaves from throughout the seed plants using persistent homology, a defined morphospace comparing all leaves is demarcated. Clear differences in shape between major phylogenetic groups are detected and estimates of leaf shape diversity within plant families are made. This approach does not only predict plant family, but also the collection site, confirming phylogenetically invariant morphological features that characterize leaves from specific locations. The application of a persistent homology method to measure leaf shape allows for a unified morphometric framework to measure plant form, including shape and branching architectures.

Tae-Wuk Kim, Chan Ho Park, Chuan-Chih Hsu, Jia-Ying Zhu, Yuchun Hsiao, Tess Branon, Shou-Ling Xu, Alice Y. Ting, Zhi-Yong Wang

Transient protein-protein interactions (PPIs), such as those between posttranslational modifying enzymes and their substrates, play key roles in cellular regulation, but are difficult to identify. Here we demonstrate the application of enzyme-catalyzed proximity labeling (PL), using the engineered promiscuous biotin ligase TurboID, as a sensitive method for characterizing PPIs in signaling networks. We show that TurboID fused with the GSK3-like kinase BIN2 or a PP2A phosphatase biotinylates their known substrate, the BZR1 transcription factor, with high specificity and efficiency. We optimized the protocol of biotin labeling and affinity purification in transgenic Arabidopsis expressing a BIN2-TurboID fusion protein. Subsequent quantitative mass spectrometry (MS) analysis identified about three hundred proteins biotinylated by BIN2-TurboID more efficiently than the YFP-TurboID control. These include a significant subset of previously proven BIN2 interactors and a large number of new BIN2-proximal proteins that uncover a broad BIN2 signaling network. Our study illustrates that PL-MS using TurboID is a powerful tool for mapping signaling networks, and reveals broad roles of BIN2 kinase in cellular signaling and regulation in plants.

Chia-Yi Cheng, Vivek Krishnakumar, Agnes Chan, Seth Schobel, Christopher D. Town

The flowering plant Arabidopsis thaliana is a dicot model organism for research in many aspects of plant biology. A comprehensive annotation of its genome paves the way for understanding the functions and activities of all types of transcripts, including mRNA, noncoding RNA, and small RNA. The most recent annotation update (TAIR10) released more than five years ago had a profound impact on Arabidopsis research. Maintaining the accuracy of the annotation continues to be a prerequisite for future progress. Using an integrative annotation pipeline, we assembled tissue-specific RNA-seq libraries from 113 datasets and constructed 48,359 transcript models of protein-coding genes in eleven tissues. In addition, we annotated various classes of noncoding RNA including small RNA, long intergenic RNA, small nucleolar RNA, natural antisense transcript, small nuclear RNA, and microRNA using published datasets and in-house analytic results. Altogether, we identified 738 novel protein-coding genes, 508 novel transcribed regions, 5,051 non-coding genes, and 35,846 small-RNA loci that formerly eluded annotation. Analysis on the splicing events and RNA-seq based expression profile revealed the landscapes of gene structures, untranslated regions, and splicing activities to be more intricate than previously appreciated. We also present 692 uniformly expressed housekeeping genes, 43% of whose human orthologs are also housekeeping genes. This updated Arabidopsis genome annotation with a substantially increased resolution of gene models will not only further our understanding of the biological processes of this plant model but also of other species.

Remco Stam, Graham B. Motion, Petra C. Boevink, Edgar Huitema

Phytophthora spp. secrete vast arrays of effector molecules upon infection. A main class of intracellular effectors are the CRNs. They are translocated into the host cell and specifically localise to the nucleus where they are thought to perturb many different cellular processes. Although CRN proteins have been implicated as effectors, direct evidence of CRN mediated perturbation of host processes has been lacking. Here we show that a conserved CRN effector from P. capsici directly binds to tomato transcription factor SlTCP14-2. Previous studies in Arabidopsis thaliana have revealed that transcription factor TCP14 may be key immune signalling protein, targeted by effectors from divergent species. We extend on our understanding of TCP targeting by pathogen effectors by showing that the P. capsici effector CRN12_997 binds to SlTCP14-2 in plants. SlTCP14-2 over-expression enhances immunity to P. capsici, a phenotypic outcome that can be abolished by co-expression of CRN12_997. We show that in the presence of CRN12_997, SlTCP14-2 association with nuclear chromatin is diminished, resulting in altered SlTCP14 subnuclear localisation. These results suggest that CRN12_997 prevents SlTCP14 from positively regulating defence against P. capsici. Our work demonstrates a direct interaction between an oomycete CRN and a host target required for suppression of immunity. Collectively, our results hint at a virulence strategy that is conserved within the oomycetes and may allow engineering of resistance to a wide range of crop pathogens.

Sarah Taghavi Namin, Mohammad Esmaeilzadeh, Mohammad Najafi, Tim B. Brown, Justin O Borevitz

High resolution and high throughput, genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. Complex developmental phenotypes are observed by imaging a variety of accessions in different environment conditions, however extracting the genetically heritable traits is challenging. In the recent years, deep learning techniques and in particular Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Long-Short Term Memories (LSTMs), have shown great success in visual data recognition, classification, and sequence learning tasks. In this paper, we proposed a CNN-LSTM framework for plant classification of various genotypes. Here, we exploit the power of deep CNNs for joint feature and classifier learning, within an automatic phenotyping scheme for genotype classification. Further, plant growth variation over time is also important in phenotyping their dynamic behavior. This was fed into the deep learning framework using LSTMs to model these temporal cues for different plant accessions. We generated a replicated dataset of four accessions of Arabidopsis and carried out automated phenotyping experiments. The results provide evidence of the benefits of our approach over using traditional hand-crafted image analysis features and other genotype classification frameworks. We also demonstrate that temporal information further improves the performance of the phenotype classification system.