An image classification approach to analyze the suppression of plant immunity by the human pathogen Salmonella Typhimurium

A Comprehensive Review of High Throughput Phenotyping and Machine Learning for Plant Stress Phenotyping

During the last decade, there has been rapid adoption of ground and aerial platforms with multiple sensors for phenotyping various biotic and abiotic stresses throughout the developmental stages of the crop plant. High throughput phenotyping (HTP) involves the application of these tools to phenotype the plants and can vary from ground-based imaging to aerial phenotyping to remote sensing. Adoption of these HTP tools has tried to reduce the phenotyping bottleneck in breeding programs and help to increase the pace of genetic gain. More specifically, several root phenotyping tools are discussed to study the plant's hidden half and an area long neglected. However, the use of these HTP technologies produces big data sets that impede the inference from those datasets. Machine learning and deep learning provide an alternative opportunity for the extraction of useful information for making conclusions. These are interdisciplinary approaches for data analysis using probability, statistics, classification, regression, decision theory, data visualization, and neural networks to relate information extracted with the phenotypes obtained. These techniques use feature extraction, identification, classification, and prediction criteria to identify pertinent data for use in plant breeding and pathology activities. This review focuses on the recent findings where machine learning and deep learning approaches have been used for plant stress phenotyping with data being collected using various HTP platforms. We have provided a comprehensive overview of different machine learning and deep learning tools available with their potential advantages and pitfalls. Overall, this review provides an avenue for studying various HTP platforms with particular emphasis on using the machine learning and deep learning tools for drawing legitimate conclusions. Finally, we propose the conceptual challenges being faced and provide insights on future perspectives for managing those issues.

Data-mining Techniques for Image-based Plant Phenotypic Traits Identification and Classification

Statistical data-mining (DM) and machine learning (ML) are promising tools to assist in the analysis of complex dataset. In recent decades, in the precision of agricultural development, plant phenomics study is crucial for high-throughput phenotyping of local crop cultivars. Therefore, integrated or a new analytical approach is needed to deal with these phenomics data. We proposed a statistical framework for the analysis of phenomics data by integrating DM and ML methods. The most popular supervised ML methods; Linear Discriminant Analysis (LDA), Random Forest (RF), Support Vector Machine with linear (SVM-l) and radial basis (SVM-r) kernel are used for classification/prediction plant status (stress/non-stress) to validate our proposed approach. Several simulated and real plant phenotype datasets were analyzed. The results described the significant contribution of the features (selected by our proposed approach) throughout the analysis. In this study, we showed that the proposed approach removed phenotype data analysis complexity, reduced computational time of ML algorithms, and increased prediction accuracy.

Detection of Bacterial Quorum Sensing Molecules

Bacterial cells use the quorum sensing system to communicate with each other. The gram-negative species very often use N-acyl homoserine lactones for this purpose. One of the easiest ways to detect these molecules is the use of particular reporter strains, which possess different kinds of reporter genes under the control of AHL-responsive promoters. Here we present some of the possibilities available today, even for not specialized researchers.

Deep phenotyping: deep learning for temporal phenotype/genotype classification

BACKGROUND

High resolution and high throughput genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. In the recent years, deep learning techniques and in particular Convolutional Neural Networks (CNNs), Recurrent Neural Networks and Long-Short Term Memories (LSTMs), have shown great success in visual data recognition, classification, and sequence learning tasks. More recently, CNNs have been used for plant classification and phenotyping, using individual static images of the plants. On the other hand, dynamic behavior of the plants as well as their growth has been an important phenotype for plant biologists, and this motivated us to study the potential of LSTMs in encoding these temporal information for the accession classification task, which is useful in automation of plant production and care.

METHODS

In this paper, we propose a CNN-LSTM framework for plant classification of various genotypes. Here, we exploit the power of deep CNNs for automatic joint feature and classifier learning, compared to using hand-crafted features. In addition, we leverage the potential of LSTMs to study the growth of the plants and their dynamic behaviors as important discriminative phenotypes for accession classification. Moreover, we collected a dataset of time-series image sequences of four accessions of Arabidopsis, captured in similar imaging conditions, which could be used as a standard benchmark by researchers in the field. We made this dataset publicly available.

CONCLUSION

The results provide evidence of the benefits of our accession classification approach over using traditional hand-crafted image analysis features and other accession classification frameworks. We also demonstrate that utilizing temporal information using LSTMs can further improve the performance of the system. The proposed framework can be used in other applications such as in plant classification given the environment conditions or in distinguishing diseased plants from healthy ones.

Sewage sludge amendment and inoculation with plant-parasitic nematodes do not facilitate the internalization of Salmonella Typhimurium LT2 in lettuce plants

Contamination of fruits and vegetables with Salmonella is a serious threat to human health. In order to prevent possible contaminations of fresh produce it is necessary to identify the contributing ecological factors. In this study we investigated whether the addition of sewage sludge or the presence of plant-parasitic nematodes foster the internalization of Salmonella enterica serovar Typhimurium LT2 into lettuce plants, posing a potential threat for human health. Greenhouse experiments were conducted to investigate whether the amendment of sewage sludge to soil or the presence of plant-parasitic nematodes Meloidogyne hapla or Pratylenchus crenatus promote the internalization of S. Typhimurium LT2 from soil into the edible part of lettuce plants. Unexpectedly, numbers of cultivable S. Typhimurium LT2 decreased faster in soil with sewage sludge than in control soil but not in root samples. Denaturing gradient gel electrophoresis analysis revealed shifts of the soil bacterial communities in response to sewage sludge amendment and time. Infection and proliferation of nematodes inside plant roots were observed but did not influence the number of cultivable S. Typhimurium LT2 in the root samples or in soil. S. Typhimurium LT2 was not detected in the leaf samples 21 and 49 days after inoculation. The results indicate that addition of sewage sludge, M. hapla or P. crenatus to soil inoculated with S. Typhimurium LT2 did not result in an improved survival in soil or internalization of lettuce plants.

Deep phenotyping: deep learning for temporal phenotype/genotype classification

BACKGROUND

High resolution and high throughput genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. In the recent years, deep learning techniques and in particular Convolutional Neural Networks (CNNs), Recurrent Neural Networks and Long-Short Term Memories (LSTMs), have shown great success in visual data recognition, classification, and sequence learning tasks. More recently, CNNs have been used for plant classification and phenotyping, using individual static images of the plants. On the other hand, dynamic behavior of the plants as well as their growth has been an important phenotype for plant biologists, and this motivated us to study the potential of LSTMs in encoding these temporal information for the accession classification task, which is useful in automation of plant production and care.

METHODS

In this paper, we propose a CNN-LSTM framework for plant classification of various genotypes. Here, we exploit the power of deep CNNs for automatic joint feature and classifier learning, compared to using hand-crafted features. In addition, we leverage the potential of LSTMs to study the growth of the plants and their dynamic behaviors as important discriminative phenotypes for accession classification. Moreover, we collected a dataset of time-series image sequences of four accessions of Arabidopsis, captured in similar imaging conditions, which could be used as a standard benchmark by researchers in the field. We made this dataset publicly available.

CONCLUSION

The results provide evidence of the benefits of our accession classification approach over using traditional hand-crafted image analysis features and other accession classification frameworks. We also demonstrate that utilizing temporal information using LSTMs can further improve the performance of the system. The proposed framework can be used in other applications such as in plant classification given the environment conditions or in distinguishing diseased plants from healthy ones.

Machine Learning for High-Throughput Stress Phenotyping in Plants

Advances in automated and high-throughput imaging technologies have resulted in a deluge of high-resolution images and sensor data of plants. However, extracting patterns and features from this large corpus of data requires the use of machine learning (ML) tools to enable data assimilation and feature identification for stress phenotyping. Four stages of the decision cycle in plant stress phenotyping and plant breeding activities where different ML approaches can be deployed are (i) identification, (ii) classification, (iii) quantification, and (iv) prediction (ICQP). We provide here a comprehensive overview and user-friendly taxonomy of ML tools to enable the plant community to correctly and easily apply the appropriate ML tools and best-practice guidelines for various biotic and abiotic stress traits.

Rapid, automated detection of stem canker symptoms in woody perennials using artificial neural network analysis

BACKGROUND

Pseudomonas syringae can cause stem necrosis and canker in a wide range of woody species including cherry, plum, peach, horse chestnut and ash. The detection and quantification of lesion progression over time in woody tissues is a key trait for breeders to select upon for resistance.

RESULTS

In this study a general, rapid and reliable approach to lesion quantification using image recognition and an artificial neural network model was developed. This was applied to screen both the virulence of a range of P. syringae pathovars and the resistance of a set of cherry and plum accessions to bacterial canker. The method developed was more objective than scoring by eye and allowed the detection of putatively resistant plant material for further study.

CONCLUSIONS

Automated image analysis will facilitate rapid screening of material for resistance to bacterial and other phytopathogens, allowing more efficient selection and quantification of resistance responses.

Advanced phenotyping and phenotype data analysis for the study of plant growth and development

Due to an increase in the consumption of food, feed, fuel and to meet global food security needs for the rapidly growing human population, there is a necessity to breed high yielding crops that can adapt to the future climate changes, particularly in developing countries. To solve these global challenges, novel approaches are required to identify quantitative phenotypes and to explain the genetic basis of agriculturally important traits. These advances will facilitate the screening of germplasm with high performance characteristics in resource-limited environments. Recently, plant phenomics has offered and integrated a suite of new technologies, and we are on a path to improve the description of complex plant phenotypes. High-throughput phenotyping platforms have also been developed that capture phenotype data from plants in a non-destructive manner. In this review, we discuss recent developments of high-throughput plant phenotyping infrastructure including imaging techniques and corresponding principles for phenotype data analysis.

Advanced phenotyping and phenotype data analysis for the study of plant growth and development

Due to an increase in the consumption of food, feed, fuel and to meet global food security needs for the rapidly growing human population, there is a necessity to breed high yielding crops that can adapt to the future climate changes, particularly in developing countries. To solve these global challenges, novel approaches are required to identify quantitative phenotypes and to explain the genetic basis of agriculturally important traits. These advances will facilitate the screening of germplasm with high performance characteristics in resource-limited environments. Recently, plant phenomics has offered and integrated a suite of new technologies, and we are on a path to improve the description of complex plant phenotypes. High-throughput phenotyping platforms have also been developed that capture phenotype data from plants in a non-destructive manner. In this review, we discuss recent developments of high-throughput plant phenotyping infrastructure including imaging techniques and corresponding principles for phenotype data analysis.

N-acyl-homoserine lactones-producing bacteria protect plants against plant and human pathogens

The implementation of beneficial microorganisms for plant protection has a long history. Many rhizobia bacteria are able to influence the immune system of host plants by inducing resistance towards pathogenic microorganisms. In this report, we present a translational approach in which we demonstrate the resistance-inducing effect of Ensifer meliloti (Sinorhizobium meliloti) on crop plants that have a significant impact on the worldwide economy and on human nutrition. Ensifer meliloti is usually associated with root nodulation in legumes and nitrogen fixation. Here, we suggest that the ability of S. meliloti to induce resistance depends on the production of the quorum-sensing molecule, oxo-C14-HSL. The capacity to enhanced resistance provides a possibility to the use these beneficial bacteria in agriculture. Using the Arabidopsis-Salmonella model, we also demonstrate that the application of N-acyl-homoserine lactones-producing bacteria could be a successful strategy to prevent plant-originated infections with human pathogens.

Image-based Analysis to Study Plant Infection with Human Pathogens

Our growing awareness that contaminated plants, fresh fruits and vegetables are responsible for a significant proportion of food poisoning with pathogenic microorganisms indorses the demand to understand the interactions between plants and human pathogens. Today we understand that those pathogens do not merely survive on or within plants, they actively infect plant organisms by suppressing their immune system. Studies on the infection process and disease development used mainly physiological, genetic, and molecular approaches, and image-based analysis provides yet another method for this toolbox. Employed as an observational tool, it bears the potential for objective and high throughput approaches, and together with other methods it will be very likely a part of data fusion approaches in the near future.

Common duckweed (Lemna minor) is a versatile high-throughput infection model for the Burkholderia cepacia complex and other pathogenic bacteria

Members of the Burkholderia cepacia complex (Bcc) have emerged in recent decades as problematic pulmonary pathogens of cystic fibrosis (CF) patients, with severe infections progressing to acute necrotizing pneumonia and sepsis. This study presents evidence that Lemna minor (Common duckweed) is useful as a plant model for the Bcc infectious process, and has potential as a model system for bacterial pathogenesis in general. To investigate the relationship between Bcc virulence in duckweed and Galleria mellonella (Greater wax moth) larvae, a previously established Bcc infection model, a duckweed survival assay was developed and used to determine LD₅₀ values. A strong correlation (R² = 0.81) was found between the strains’ virulence ranks in the two infection models, suggesting conserved pathways in these vastly different hosts. To broaden the application of the duckweed model, enteropathogenic Escherichia coli (EPEC) and five isogenic mutants with previously established LD₅₀ values in the larval model were tested against duckweed, and a strong correlation (R² = 0.93) was found between their raw LD₅₀ values. Potential virulence factors in B. cenocepacia K56-2 were identified using a high-throughput screen against single duckweed plants. In addition to the previously characterized antifungal compound (AFC) cluster genes, several uncharacterized genes were discovered including a novel lysR regulator, a histidine biosynthesis gene hisG, and a gene located near the gene encoding the recently characterized virulence factor SuhB_Bc. Finally, to demonstrate the utility of this model in therapeutic applications, duckweed was rescued from Bcc infection by treating with bacteriophage at 6-h intervals. It was observed that phage application became ineffective at a timepoint that coincided with a sharp increase in bacterial invasion of plant tissue. These results indicate that common duckweed can serve as an effective infection model for the investigation of bacterial virulence factors and therapeutic strategies to combat them.

Salmonella, a cross-kingdom pathogen infecting humans and plants

Infections with non-typhoidal Salmonella strains are constant and are a non-negligible threat to the human population. In the last two decades, salmonellosis outbreaks have increasingly been associated with infected fruits and vegetables. For a long time, Salmonellae were assumed to survive on plants after a more or less accidental infection. However, this notion has recently been challenged. Studies on the infection mechanism in vegetal hosts, as well as on plant immune systems, revealed an active infection process resembling in certain features the infection in animals. On one hand, Salmonella requires the type III secretion systems to effectively infect plants and to suppress their resistance mechanisms. On the other hand, plants recognize these bacteria and react to the infection with an induced defense mechanism similar to the reaction to other plant pathogens. In this review, we present the newest reports on the interaction between Salmonellae and plants. We discuss the possible ways used by these bacteria to infect plants as well as the plant responses to the infection. The recent findings indicate that plants play a central role in the dissemination of Salmonella within the ecosystem.