Application of image analysis with neural network for plant somatic embryo culture

Deep learning for automated segmentation and counting of hypocotyl and cotyledon regions in mature Pinus radiata D. Don. somatic embryo images

In commercial forestry and large-scale plant propagation, the utilization of artificial intelligence techniques for automated somatic embryo analysis has emerged as a highly valuable tool. Notably, image segmentation plays a key role in the automated assessment of mature somatic embryos. However, to date, the application of Convolutional Neural Networks (CNNs) for segmentation of mature somatic embryos remains unexplored. In this study, we present a novel application of CNNs for delineating mature somatic conifer embryos from background and residual proliferating embryogenic tissue and differentiating various morphological regions within the embryos. A semantic segmentation CNN was trained to assign pixels to cotyledon, hypocotyl, and background regions, while an instance segmentation network was trained to detect individual cotyledons for automated counting. The main dataset comprised 275 high-resolution microscopic images of mature Pinus radiata somatic embryos, with 42 images reserved for testing and validation sets. The evaluation of different segmentation methods revealed that semantic segmentation achieved the highest performance averaged across classes, achieving F1 scores of 0.929 and 0.932, with IoU scores of 0.867 and 0.872 for the cotyledon and hypocotyl regions respectively. The instance segmentation approach demonstrated proficiency in accurate detection and counting of the number of cotyledons, as indicated by a mean squared error (MSE) of 0.79 and mean absolute error (MAE) of 0.60. The findings highlight the efficacy of neural network-based methods in accurately segmenting somatic embryos and delineating individual morphological parts, providing additional information compared to previous segmentation techniques. This opens avenues for further analysis, including quantification of morphological characteristics in each region, enabling the identification of features of desirable embryos in large-scale production systems. These advancements contribute to the improvement of automated somatic embryogenesis systems, facilitating efficient and reliable plant propagation for commercial forestry applications.

Protoplast Technology and Somatic Hybridisation in the Family Apiaceae

Species of the family Apiaceae occupy a major market share but are hitherto dependent on open pollinated cultivars. This results in a lack of production uniformity and reduced quality that has fostered hybrid seed production. The difficulty in flower emasculation led breeders to use biotechnology approaches including somatic hybridization. We discuss the use of protoplast technology for the development of somatic hybrids, cybrids and in-vitro breeding of commercial traits such as CMS (cytoplasmic male sterility), GMS (genetic male sterility) and EGMS (environment-sensitive genic male sterility). The molecular mechanism(s) underlying CMS and its candidate genes are also discussed. Cybridization strategies based on enucleation (Gamma rays, X-rays and UV rays) and metabolically arresting protoplasts with chemicals such as iodoacetamide or iodoacetate are reviewed. Differential fluorescence staining of fused protoplast as routinely used can be replaced by new tagging approaches using non-toxic proteins. Here, we focused on the initial plant materials and tissue sources for protoplast isolation, the various digestion enzyme mixtures tested, and on the understanding of cell wall re-generation, all of which intervene in somatic hybrids regeneration. Although there are no alternatives to somatic hybridization, various approaches also discussed are emerging, viz., robotic platforms, artificial intelligence, in recent breeding programs for trait identification and selection.

Application of artificial intelligence models and optimization algorithms in plant cell and tissue culture

Artificial intelligence (AI) models and optimization algorithms (OA) are broadly employed in different fields of technology and science and have recently been applied to improve different stages of plant tissue culture. The usefulness of the application of AI-OA has been demonstrated in the prediction and optimization of length and number of microshoots or roots, biomass in plant cell cultures or hairy root culture, and optimization of environmental conditions to achieve maximum productivity and efficiency, as well as classification of microshoots and somatic embryos. Despite its potential, the use of AI and OA in this field has been limited due to complex definition terms and computational algorithms. Therefore, a systematic review to unravel modeling and optimizing methods is important for plant researchers and has been acknowledged in this study. First, the main steps for AI-OA development (from data selection to evaluation of prediction and classification models), as well as several AI models such as artificial neural networks (ANNs), neurofuzzy logic, support vector machines (SVMs), decision trees, random forest (FR), and genetic algorithms (GA), have been represented. Then, the application of AI-OA models in different steps of plant tissue culture has been discussed and highlighted. This review also points out limitations in the application of AI-OA in different plant tissue culture processes and provides a new view for future study objectives. KEY POINTS: • Artificial intelligence models and optimization algorithms can be considered a novel and reliable computational method in plant tissue culture. • This review provides the main steps and concepts for model development. • The application of machine learning algorithms in different steps of plant tissue culture has been discussed and highlighted.

Clustering gene expression pattern and extracting relationship in gene network based on artificial neural networks

Massive datasets such as gene expression profiles are accumulating along with the development of DNA microarray technologies. In this paper, we focus on mining biological relevant information such as typical expression patterns and the interconnections of gene networks from massive datasets. At first, the algorithm of a self-organizing map (SOM) was used to cluster gene expression data. Then, for the typical patterns extracted by the SOM, a three-layer artificial neural network (ANN) model was used to extract the relationships between the expression patterns. In order to evaluate the clustering analysis based on the SOM, biological and statistical indices were introduced. To validate the efficiency of the scheme proposed for extracting the relationships between the expression patterns with the ANN, a test dataset was created and used for the test. Finally, the interconnections of a typical pattern of early G1, late G1, S, G2, and M phases in a yeast cell cycle were extracted and visualized.

Large-scale plant micropropagation

Plant micropropagation is an efficient method of propagating disease-free, genetically uniform and massive amounts of plants in vitro. The micropropagation from cells can be achieved by direct organogenesis from hairy roots or regeneration via somatic tissue. Once the availability of embryogenic cell and hairy root systems based on liquid media has been demonstrated, the scale-up of the whole process should be established by an economically feasible technology for their large-scale production in appropriate bioreactors. It is necessary to design a suitable bioreactor configuration that can provide adequate mixing and mass transfer while minimizing the intensity of shear stress and hydrodynamic pressure. Automatic selection of embryogenic calli and regenerated plantlets using an image analysis procedure should be associated with the system. Using the above systems, it will be possible to establish an advanced plant micropropagation system in which the plantlets can be propagated without soil under optimal conditions controlled in plant factory. The aim of this review is to identify the problems related to large-scale plant micropropagation via somatic embryogenesis and hairy roots, and to summarize the most recent developments in bioreactor design. Emphasis is placed on micropropagation technology and computer-aided image analysis, including the successful results obtained in our laboratories.

Biomass quantification by image analysis

Microbiologists have always rely on microscopy to examine microorganisms. When microscopy, either optical or electron-based, is coupled to quantitative image analysis, the spectrum of potential applications is widened: counting, sizing, shape characterization, physiology assessment, analysis of visual texture, motility studies are now easily available for obtaining information on biomass. In this chapter the main tools used for cell visualization as well as the basic steps of image treatment are presented. General shape descriptors can be used to characterize the cell morphology, but special descriptors have been defined for filamentous microorganisms. Physiology assessment is often based on the use of fluorescent dyes. The quantitative analysis of visual texture is still limited in bioengineering but the characterization of the surface of microbial colonies may open new prospects, especially for cultures on solid substrates. In many occasions, the number of parameters extracted from images is so large that data-mining tools, such as Principal Components Analysis, are useful for summarizing the key pieces of information.

Knowledge-based design and operation of bioprocess systems

Almost twenty years have passed since the first applications of the knowledge-based approach to bioprocess operations were reported. During this period, approaches such as fuzzy logic, artificial neural network modeling, expert systems and genetic algorithms have been extensively studied and successfully used in the design and control of various bioprocesses. The recent development of these approaches in the design and operation of biological processes is summarized and reviewed, especially focusing on the studies reported in biochemical engineering journals.

Release of embryogenic carrot cells with high regeneration potency from immobilized alginate beads

For the mass-production of regenerated carrot plantlets, embryogenic carrot callus immobilized in calcium alginate gel beads was cultivated in a growth medium and the regeneration frequency of cells released from alginate gel beads was compared with that in a suspension culture. Cells released in the immobilized culture were regenerated at a frequency which was about 1.5 times higher than that obtained in the suspension culture. When CaCl2 was added to the growth medium at 5 mM, repeated batch culture for plantlet production continued for 245 d with no significant decrease in the productivity (1.6 x 10(5) plantlets/l-medium/d).