Machine Learning for Plant Stress Modeling: A Perspective towards Hormesis Management

S. Early detection of abiotic stress in plants through SNARE proteins using hybrid feature fusion model

Agriculture is the main source of livelihood for most of the population across the globe. Plants are often considered life savers for humanity, having evolved complex adaptations to cope with adverse environmental conditions. Protecting agricultural produce from devastating conditions such as stress is essential for the sustainable development of the nation. Plants respond to various environmental stressors such as drought, salinity, heat, cold, etc. Abiotic stress can significantly impact crop yield and development posing a major threat to agriculture. SNARE proteins play a major role in pathological processes as they are vital proteins in the life sciences. These proteins act as key players in stress responses. Feature extraction is essential for visualizing the underlying structure of the SNARE proteins in analyzing the root cause of abiotic stress in plants. To address this issue, we developed a hybrid model to capture the hidden structures of the SNAREs. A feature fusion technique has been devised by combining the potential strengths of convolutional neural networks (CNN) with a high dimensional radial basis function (RBF) network. Additionally, we employ a bi-directional long short-term memory (Bi-LSTM) network to classify the presence of SNARE proteins. Our feature fusion model successfully identified abiotic stress in plants with an accuracy of 74.6%. When compared with various existing frameworks, our model demonstrates superior classification results.

Heat Stress and Plant-Biotic Interactions: Advances and Perspectives

Climate change presents numerous challenges for agriculture, including frequent events of plant abiotic stresses such as elevated temperatures that lead to heat stress (HS). As the primary driving factor of climate change, HS threatens global food security and biodiversity. In recent years, HS events have negatively impacted plant physiology, reducing plant's ability to maintain disease resistance and resulting in lower crop yields. Plants must adapt their priorities toward defense mechanisms to tolerate stress in challenging environments. Furthermore, selective breeding and long-term domestication for higher yields have made crop varieties vulnerable to multiple stressors, making them more susceptible to frequent HS events. Studies on climate change predict that concurrent HS and biotic stresses will become more frequent and severe in the future, potentially occurring simultaneously or sequentially. While most studies have focused on singular stress effects on plant systems to examine how plants respond to specific stresses, the simultaneous occurrence of HS and biotic stresses pose a growing threat to agricultural productivity. Few studies have explored the interactions between HS and plant-biotic interactions. Here, we aim to shed light on the physiological and molecular effects of HS and biotic factor interactions (bacteria, fungi, oomycetes, nematodes, insect pests, pollinators, weedy species, and parasitic plants), as well as their combined impact on crop growth and yields. We also examine recent advances in designing and developing various strategies to address multi-stress scenarios related to HS and biotic factors.

Artificial intelligence models for validating and predicting the impact of chemical priming of hydrogen peroxide (H2O2) and light emitting diodes on in vitro grown industrial hemp (Cannabis sativa L.)

Industrial hemp (Cannabis sativa L.) is a highly recalcitrant plant under in vitro conditions that can be overcome by employing external stimuli. Hemp seeds were primed with 2.0-3.0% hydrogen peroxide (H2O2) followed by culture under different Light Emitting Diodes (LEDs) sources. Priming seeds with 2.0% yielded relatively high germination rate, growth, and other biochemical and enzymatic activities. The LED lights exerted a variable impact on Cannabis germination and enzymatic activities. Similarly, variable responses were observed for H2O2 × Blue-LEDs combination. The results were also analyzed by multiple regression analysis, followed by an investigation of the impact of both factors by Pareto chart and normal plots. The results were optimized by contour and surface plots for all parameters. Response surface optimizer optimized 2.0% H2O2 × 918 LUX LEDs for maximum scores of all output parameters. The results were predicted by employing Multilayer Perceptron (MLP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms. Moreover, the validity of these models was assessed by using six different performance metrics. MLP performed better than RF and XGBoost models, considering all six-performance metrics. Despite the differences in scores, the performance indicators for all examined models were quite close to each other. It can easily be concluded that all three models are capable of predicting and validating data for cannabis seeds primed with H2O2 and grown under different LED lights.

Factors influencing fruit cracking: an environmental and agronomic perspective

Fruit cracking, a widespread physiological disorder affecting various fruit crops and vegetables, has profound implications for fruit quality and marketability. This mini review delves into the multifaceted factors contributing to fruit cracking and emphasizes the pivotal roles of environmental and agronomic factors in its occurrence. Environmental variables such as temperature, relative humidity, and light exposure are explored as determinants factors influencing fruit cracking susceptibility. Furthermore, the significance of mineral nutrition and plant growth regulators in mitigating fruit cracking risk is elucidated, being calcium deficiency identified as a prominent variable in various fruit species. In recent years, precision farming and monitoring systems have emerged as valuable tools for managing environmental factors and optimizing fruit production. By meticulously tracking parameters such as temperature, humidity, soil moisture, and fruit skin temperature, growers can make informed decisions to prevent or alleviate fruit cracking. In conclusion, effective prevention of fruit cracking necessitates a comprehensive approach that encompasses both environmental and agronomic factors.

Radiation Hormesis in Barley Manifests as Changes in Growth Dynamics Coordinated with the Expression of PM19L-like, CML31-like, and AOS2-like

The stimulation of growth and development of crops using ionising radiation (radiation hormesis) has been reported by many research groups. However, specific genes contributing to the radiation stimulation of plant growth are largely unknown. In this work, we studied the impact of the low-dose γ-irradiation of barley seeds on the growth dynamics and gene expression of eight barley cultivars in a greenhouse experiment. Our findings confirmed that candidate genes of the radiation growth stimulation, previously established in barley seedlings (PM19L-like, CML31-like, and AOS2-like), are significant in radiation hormesis throughout ontogeny. In γ-stimulated cultivars, the expression of these genes was aligned with the growth dynamics, yield parameters, and physiological conditions of plants. We identified contrasting cultivars for future gene editing and found that the γ-stimulated cultivar possessed some specific abiotic stress-responsive elements in the promotors of candidate genes, possibly revealing a new level of radiation hormesis effect execution. These results can be used in creating new productive barley cultivars, ecological toxicology of radionuclides, and eustress biology studies.

Drought-responsive genes in tomato: meta-analysis of gene expression using machine learning

Plants have diverse molecular mechanisms to protect themselves from biotic and abiotic stressors and adapt to changing environments. To uncover the genetic potential of plants, it is crucial to understand how they adapt to adverse conditions by analyzing their genomic data. We analyzed RNA-Seq data from different tomato genotypes, tissue types, and drought durations. We used a time series scale to identify early and late drought-responsive gene modules and applied a machine learning method to identify the best responsive genes to drought. We demonstrated six candidate genes of tomato viz. Fasciclin-like arabinogalactan protein 2 (FLA2), Amino acid transporter family protein (ASCT), Arginine decarboxylase 1 (ADC1), Protein NRT1/PTR family 7.3 (NPF7.3), BAG family molecular chaperone regulator 5 (BAG5) and Dicer-like 2b (DCL2b) were responsive to drought. We constructed gene association networks to identify their potential interactors and found them drought-responsive. The identified candidate genes can help to explore the adaptation of tomato plants to drought. Furthermore, these candidate genes can have far-reaching implications for molecular breeding and genome editing in tomatoes, providing insights into the molecular mechanisms that underlie drought adaptation. This research underscores the importance of the genetic basis of plant adaptation, particularly in changing climates and growing populations.

An overview of image-based phenotyping as an adaptive 4.0 technology for studying plant abiotic stress: A bibliometric and literature review

Improving the tolerance of crop species to abiotic stresses that limit plant growth and productivity is essential for mitigating the emerging problems of global warming. In this context, imaged data analysis represents an effective method in the 4.0 technology era, where this method has the non-destructive and recursive characterization of plant phenotypic traits as selection criteria. So, the plant breeders are helped in the development of adapted and climate-resilient crop varieties. Although image-based phenotyping has recently resulted in remarkable improvements for identifying the crop status under a range of growing conditions, the topic of its application for assessing the plant behavioral responses to abiotic stressors has not yet been extensively reviewed. For such a purpose, bibliometric analysis is an ideal analytical concept to analyze the evolution and interplay of image-based phenotyping to abiotic stresses by objectively reviewing the literature in light of existing database. Bibliometricy, a bibliometric analysis was applied using a systematic methodology which involved data mining, mining data improvement and analysis, and manuscript construction. The obtained results indicate that there are 554 documents related to image-based phenotyping to abiotic stress until 5 January 2023. All document showed the future development trends of image-based phenotyping will be mainly centered in the United States, European continent and China. The keywords analysis major focus to the application of 4.0 technology and machine learning in plant breeding, especially to create the tolerant variety under abiotic stresses. Drought and saline become an abiotic stress often using image-based phenotyping. Besides that, the rice, wheat and maize as the main commodities in this topic. In conclusion, the present work provides information on resolutive interactions in developing image-based phenotyping to abiotic stress, especially optimizing high-throughput sensors in image-based phenotyping for the future development.

An artificial intelligence-integrated analysis of the effect of drought stress on root traits of "modern" and "ancient" wheat varieties

Due to drought stress, durum wheat production in the Mediterranean basin will be severely affected in the coming years. Durum wheat cultivation relies on a few genetically uniform "modern" varieties, more productive but less tolerant to stresses, and "traditional" varieties, still representing a source of genetic biodiversity for drought tolerance. Root architecture plasticity is crucial for plant adaptation to drought stress and the relationship linking root structures to drought is complex and still largely under-explored. In this study, we examined the effect of drought stress on the roots' characteristics of the "traditional" Saragolla cultivar and the "modern" Svevo. By means of "SmartRoot" software, we demonstrated that drought stress affected primary and lateral roots as well as root hair at different extents in Saragolla and Svevo cultivars. Indeed, we observed that under drought stress Saragolla possibly revamped its root architecture, by significantly increasing the length of lateral roots, and the length/density of root hairs compared to the Svevo cultivar. Scanning Electron Microscopy analysis of root anatomical traits demonstrated that under drought stress a greater stele area and an increase of the xylem lumen size vessel occurred in Saragolla, indicating that the Saragolla variety had a more efficient adaptive response to osmotic stress than the Svevo. Furthermore, for the analysis of root structural data, Artificial Intelligence (AI) algorithms have been used: Their application allowed to predict from root structural traits modified by the osmotic stress the type of cultivar observed and to infer the relationship stress-cultivar type, thus demonstrating that root structural traits are clear and incontrovertible indicators of the higher tolerance to osmotic stress of the Saragolla cultivar. Finally, to obtain an integrated view of root morphogenesis, phytohormone levels were investigated. According to the phenotypic effects, under drought stress,a larger increase in IAA and ABA levels, as well as a more pronounced reduction in GA levels occurred in Saragolla as compared to Svevo. In conclusion, these results show that the root growth and hormonal profile of Saragolla are less affected by osmotic stress than those of Svevo, demonstrating the great potential of ancient varieties as reservoirs of genetic variability for improving crop responses to environmental stresses.

Plant hormesis: Revising of the concepts of biostimulation, elicitation and their application in a sustainable agricultural production

Current research in basic and applied knowledge of plant science has aimed to unravel the role of the interaction between environmental factors and the genome in the physiology of plants to confer the ability to overcome challenges in a climate change scenario. Evidence shows that factors causing environmental stress (stressors), whether of biological, chemical, or physical origin, induce eustressing or distressing effects in plants depending on the dose. The latter suggests the induction of the "hormesis" phenomenon. Sustainable crop production requires a better understanding of hormesis, its basic concepts, and the input variables to make its management feasible. This implies that acknowledging hormesis in plant research could allow specifying beneficial effects to effectively manage environmental stressors according to cultivation goals. Several factors have been useful in this regard, which at low doses show beneficial eustressing effects (biostimulant/elicitor), while at higher doses, they show distressing toxic effects. These insights highlight biostimulants/elicitors as tools to be included in integrated crop management strategies for reaching sustainability in plant science and agricultural studies. In addition, compelling evidence on the inheritance of elicited traits in plants unfolds the possibility of implementing stressors as a tool in plant breeding.

Antioxidant and drought-acclimation responses in UV-B-exposed transgenic Nicotiana tabacum displaying constitutive overproduction of H2O2

Hydrogen peroxide (H2O2) is an important molecule that regulates antioxidant responses that are crucial for plant stress resistance. Exposure to low levels of ultraviolet-B radiation (UV-B, 280-315 nm) can also activate antioxidant defenses and acclimation responses. However, how H2O2 and UV-B interact to promote stress acclimation remains poorly understood. In this work, a transgenic model of Nicotiana tabacum cv Xanthi nc, with elevated Mn-superoxide dismutase (Mn-SOD) activity, was used to study the interaction between the constitutive overproduction of H2O2 and a 14-day UV-B treatment (1.75 kJ m-2 d-1 biologically effective UV-B). Subsequently, these plants were subjected to a 7-day moderate drought treatment to evaluate the impact on drought resistance of H2O2- and UV-dependent stimulation of the plants' antioxidant system. The UV-B treatment enhanced H2O2 levels and altered the antioxidant status by increasing the epidermal flavonol index, Trolox Equivalent Antioxidant Capacity, and catalase, peroxidase and phenylalanine ammonia lyase activities in the leaves. UV-B also retarded growth and suppressed acclimation responses in highly H2O2-overproducing transgenic plants. Plants not exposed to UV-B had a higher drought resistance in the form of higher relative water content of leaves. Our data associate the interaction between Mn-SOD transgene overexpression and the UV-B treatment with a stress response. Finally, we propose a hormetic biphasic drought resistance response curve as a function of leaf H2O2 content in N. tabacum cv Xanthi.

AI for life: Trends in artificial intelligence for biotechnology

Due to popular successes (e.g., ChatGPT) Artificial Intelligence (AI) is on everyone's lips today. When advances in biotechnology are combined with advances in AI unprecedented new potential solutions become available. This can help with many global problems and contribute to important Sustainability Development Goals. Current examples include Food Security, Health and Well-being, Clean Water, Clean Energy, Responsible Consumption and Production, Climate Action, Life below Water, or protect, restore and promote sustainable use of terrestrial ecosystems, sustainably manage forests, combat desertification, and halt and reverse land degradation and halt biodiversity loss. AI is ubiquitous in the life sciences today. Topics include a wide range from machine learning and Big Data analytics, knowledge discovery and data mining, biomedical ontologies, knowledge-based reasoning, natural language processing, decision support and reasoning under uncertainty, temporal and spatial representation and inference, and methodological aspects of explainable AI (XAI) with applications of biotechnology. In this pre-Editorial paper, we provide an overview of open research issues and challenges for each of the topics addressed in this special issue. Potential authors can directly use this as a guideline for developing their paper.

Artificial neural network modeling for deciphering the in vitro induced salt stress tolerance in chickpea (Cicer arietinum L)

Salt stress is one of the most critical abiotic stresses having significant contribution in global agriculture production. Chickpea is sensitive to salt stress at various growth stages and a better knowledge of salt tolerance in chickpea would enable breeding of salt tolerant varieties. During present investigation, in vitro screening of desi chickpea by continuous exposure of seeds to NaCl-containing medium was performed. NaCl was applied in the MS medium at the rate of 6.25, 12.50, 25, 50, 75, 100, and 125 mM. Different germination indices and growth indices of roots and shoots were recorded. Mean germination (%) of roots and shoots ranged from 52.08 to 100%, and 41.67-100%, respectively. The mean germination time (MGT) of roots and shoots ranged from 2.40 to 4.78 d and 3.23-7.05 d. The coefficient of variation of the germination time (CVt) was recorded as 20.91-53.43% for roots, and 14.53-44.17% for shoots. The mean germination rate (MR) of roots was better than shoots. The uncertainty (U) values were tabulated as 0.43-1.59 (roots) and 0.92-2.33 (shoots). The synchronization index (Z) reflected the negative impact of elevated salinity levels on both root and shoot emergence. Application of NaCl exerted a negative impact on all growth indices compared to control and decreased gradually with elevated NaCl concentration. Results on salt tolerance index (STI) also revealed the reduced STI with elevated NaCl concentration and STI of roots was less than shoot. Elemental analysis revealed more Na and Cl accumulation with respective elevated NaCl concentrations. The In vitro growth parameters and STI values validated and predicted by multilayer perceptron (MLP) model revealed the relatively high R 2 values of all growth indices and STI. Findings of this study will be helpful to broaden the understanding about the salinity tolerance level of desi chickpea seeds under in vitro conditions using various germination indices and seedling growth indices.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12298-023-01282-z.

DeepAProt: Deep learning based abiotic stress protein sequence classification and identification tool in cereals

The impact of climate change has been alarming for the crop growth. The extreme weather conditions can stress the crops and reduce the yield of major crops belonging to Poaceae family too, that sustains 50% of the world's food calorie and 20% of protein intake. Computational approaches, such as artificial intelligence-based techniques have become the forefront of prediction-based data interpretation and plant stress responses. In this study, we proposed a novel activation function, namely, Gaussian Error Linear Unit with Sigmoid (SIELU) which was implemented in the development of a Deep Learning (DL) model along with other hyper parameters for classification of unknown abiotic stress protein sequences from crops of Poaceae family. To develop this models, data pertaining to four different abiotic stress (namely, cold, drought, heat and salinity) responsive proteins of the crops belonging to poaceae family were retrieved from public domain. It was observed that efficiency of the DL models with our proposed novel SIELU activation function outperformed the models as compared to GeLU activation function, SVM and RF with 95.11%, 80.78%, 94.97%, and 81.69% accuracy for cold, drought, heat and salinity, respectively. Also, a web-based tool, named DeepAProt (http://login1.cabgrid.res.in:5500/) was developed using flask API, along with its mobile app. This server/App will provide researchers a convenient tool, which is rapid and economical in identification of proteins for abiotic stress management in crops Poaceae family, in endeavour of higher production for food security and combating hunger, ensuring UN SDG goal 2.0.

Machine Learning-Based Crop Stress Detection in Greenhouses

Greenhouse climate control systems are usually based on greenhouse microclimate settings to exert any control. However, to save energy, water and nutrients, additional parameters related to crop performance and physiology will have to be considered. In addition, detecting crop stress before it is clearly visible by naked eye is an advantage that could aid in microclimate control. In this study, a Machine Learning (ML) model which takes into account microclimate and crop physiological data to detect different types of crop stress was developed and tested. For this purpose, a multi-sensor platform was used to record tomato plant physiological characteristics under different fertigation and air temperature conditions. The innovation of the current model lies in the integration of photosynthesis rate (Ps) values estimated by means of remote sensing using a photochemical reflectance index (PRI). Through this process, the time-series Ps data were combined with crop leaf temperature and microclimate data by means of the ML model. Two different algorithms were evaluated: Gradient Boosting (GB) and MultiLayer perceptron (MLP). Two runs with different structures took place for each algorithm. In RUN 1, there were more feature inputs than the outputs to build a model with high predictive accuracy. However, in order to simplify the process and develop a user-friendly approach, a second, different run was carried out. Thus, in RUN 2, the inputs were fewer than the outputs, and that is why the performance of the model in this case was lower than in the case of RUN 1. Particularly, MLP showed 91% and 83% accuracy in the training sample, and 89% and 82% in testing sample, for RUNs 1 and 2, respectively. GB showed 100% accuracy in the training sample for both runs, and 91% and 83% in testing sample in RUN 1 and RUN 2, respectively. To improve the accuracy of RUN 2, a larger database is required. Both models, however, could easily be incorporated into existing greenhouse climate monitoring and control systems, replacing human experience in detecting greenhouse crop stress conditions.

A Review of Integrative Omic Approaches for Understanding Rice Salt Response Mechanisms

Soil salinity is one of the most serious environmental challenges, posing a growing threat to agriculture across the world. Soil salinity has a significant impact on rice growth, development, and production. Hence, improving rice varieties’ resistance to salt stress is a viable solution for meeting global food demand. Adaptation to salt stress is a multifaceted process that involves interacting physiological traits, biochemical or metabolic pathways, and molecular mechanisms. The integration of multi-omics approaches contributes to a better understanding of molecular mechanisms as well as the improvement of salt-resistant and tolerant rice varieties. Firstly, we present a thorough review of current knowledge about salt stress effects on rice and mechanisms behind rice salt tolerance and salt stress signalling. This review focuses on the use of multi-omics approaches to improve next-generation rice breeding for salinity resistance and tolerance, including genomics, transcriptomics, proteomics, metabolomics and phenomics. Integrating multi-omics data effectively is critical to gaining a more comprehensive and in-depth understanding of the molecular pathways, enzyme activity and interacting networks of genes controlling salinity tolerance in rice. The key data mining strategies within the artificial intelligence to analyse big and complex data sets that will allow more accurate prediction of outcomes and modernise traditional breeding programmes and also expedite precision rice breeding such as genetic engineering and genome editing.

R, Choudhary AK, Salam MD, Sahoo MR, Bhutia TL, Devi SH, Thounaojam AS, Behera C, M. N. H, Kumar A, Dasgupta M, Devi YP, Singh D, Bhagowati S, Devi CP, Singh HR, Khaba CI. Role of biostimulants in mitigating the effects of climate change on crop performance

Climate change is a critical yield-limiting factor that has threatened the entire global crop production system in the present scenario. The use of biostimulants in agriculture has shown tremendous potential in combating climate change-induced stresses such as drought, salinity, temperature stress, etc. Biostimulants are organic compounds, microbes, or amalgamation of both that could regulate plant growth behavior through molecular alteration and physiological, biochemical, and anatomical modulations. Their nature is diverse due to the varying composition of bioactive compounds, and they function through various modes of action. To generate a successful biostimulatory action on crops under different parameters, a multi-omics approach would be beneficial to identify or predict its outcome comprehensively. The 'omics' approach has greatly helped us to understand the mode of action of biostimulants on plants at cellular levels. Biostimulants acting as a messenger in signal transduction resembling phytohormones and other chemical compounds and their cross-talk in various abiotic stresses help us design future crop management under changing climate, thus, sustaining food security with finite natural resources. This review article elucidates the strategic potential and prospects of biostimulants in mitigating the adverse impacts of harsh environmental conditions on plants.