Integrating artificial intelligence and high-throughput phenotyping for crop improvement

Crop improvement is crucial for addressing the global challenges of food security and sustainable agriculture.Recent advancements in high-throughput phenotyping(HTP)technologies and artificial intelligence(AI)have revolutionized the field,enabling rapid and accurate assessment of crop traits on a large scale.The integration of AI and machine learning algorithms with HTP data has unlocked new opportunities for crop improvement.AI algorithms can analyze and interpret large datasets,and extract meaningful patterns and correlations between phenotypic traits and genetic factors.These technologies have the potential to revolutionize plant breeding programs by providing breeders with efficient and accurate tools for trait selection,thereby reducing the time and cost required for variety development.However,further research and collaboration are needed to overcome the existing challenges and fully unlock the power of HTP and AI in crop improvement.By leveraging AI algorithms,researchers can efficiently analyze phenotypic data,uncover complex patterns,and establish predictive models that enable precise trait selection and crop breeding.The aim of this review is to explore the transformative potential of integrating HTP and AI in crop improvement.This review will encompass an in-depth analysis of recent advances and applications,highlighting the numerous benefits and challenges associated with HTP and AI.

Use of Unmanned Aerial System (UAS) Phenotyping to Predict Pod and Seed Yield in Organic Peanuts

Peanut (Arachis hypogaea L.) is a highly nutritious food that is an excellent source of protein and is associated with increased coronary health, lower risk of type-2 diabetes, lower risk of breast cancer and a healthy profile of inflammatory biomarkers. The domestic demand for organic peanuts has significantly increased, requiring new breeding efforts to develop peanut varieties adapted to the organic farming system. The use of unmanned aerial system (UAS) has gained scientific attention because of the ability to generate high-throughput phenotypic data. However, it has not been fully investigated for phenotyping agronomic traits of organic peanuts. Peanuts are beneficial for cardio system protection and are widely used. Within the U.S., peanuts are grown in 11 states on roughly 600,000 hectares and averaging 4500 kg/ha. This study’s objective was to test the accuracy of UAS data in the phenotyping pod and seed yield of organic peanuts. UAS data was collected from a field plot with 20 Spanish peanut breeding lines on July 07, 2021 and September 27, 2021. The study was a randomized complete block design (RCBD) with 3 blocks. Twenty-five vegetation indices (VIs) were calculated. The analysis of variance showed significant genotypic effects on all 25 vegetation indices for both flights (p < 0.05). The vegetation index Red edge (RE) from the first flight was the most significantly correlated with both pod (r = 0.44) and seed yield (r = 0.64). These results can be used to further advance organic peanut breeding efforts with high-throughput data collection.

High-throughput phenotyping: Breaking through the bottleneck in future crop breeding

With the rapid development of genetic analysis techniques and crop population size,phenotyping has become the bottleneck restricting crop breeding.Breaking through this bottleneck will require phenomics,defined as the accurate,high-throughput acquisition and analysis of multi-dimensional phenotypes during crop growth at organism-wide levels,ranging from cells to organs,individual plants,plots,and fields.Here we offer an overview of crop phenomics research from technological and platform viewpoints at various scales,including microscopic,ground-based,and aerial phenotyping and phenotypic data analysis.We describe recent applications of high-throughput phenotyping platforms for abiotic/biotic stress and yield assessment.Finally,we discuss current challenges and offer perspectives on future phenomics research.

A deep learning-integrated phenotyping pipeline for vascular bundle phenotypes and its application in evaluating sap flow in the maize stem

Plant vascular bundles are responsible for water and material transportation, and their quantitative and functional evaluation is desirable in plant research. At the single-plant level, the number, size, and distribution of vascular bundles vary widely, posing a challenge to automatically and accurately identifying and quantifying them. In this study, a deep learning-integrated phenotyping pipeline was developed to robustly and accurately detect vascular bundles in Computed Tomography(CT) images of stem internodes. Two semantic indicators were used to evaluate and identify a suitable feature extraction network for semantic segmentation models. The epidermis thickness of maize stem was evaluated for the first time and adjacent vascular bundles were improved using an adaptive watershed-based approach. The counting accuracy(R^(2)) of vascular bundles was 0.997 for all types of stem internodes, and the measured accuracy of size traits was over 0.98. Combining sap flow experiments, multiscale traits of vascular bundles were evaluated at the single-plant level, which provided an insight into the water use efficiency of the maize plant.

Precision phenotyping of contrasting potato(Solanum tuberosum L.) varieties in a novel aeroponics system for improving nitrogen use efficiency: In search of key traits and genes

With increasing population, degrading soil health, limited arable land area, and high cost of nitrogen(N) fertilizers, improving nitrogen use efficiency(NUE) of potato is an inevitable approach to save the environment and achieve sufficient tuber yields with less N fertilizer supply. Recently, we have developed an aeroponics system to study NUE in potato using genomics, physiology, and breeding approaches. This study aims on precision phenotyping of plants of two distinct potato varieties(Kufri Gaurav, N efficient;Kufri Jyoti, N inefficient) in the novel aeroponics system. Plants were grown in aeroponics under controlled conditions with low N(0.75 mmol L^-1NO3^-) and high N(7.5 mmol L^-1NO3^-) levels. Plant biomass, root traits, total chlorophyll content, and plant N were increased with increasing N supply, whereas higher NUE parameters namely NUE, agronomic NUE(Ag NUE), N uptake efficiency(NUp E), harvest index(HI), and N harvest index(NHI) were observed at low N. An NUE efficient cv. Kufri Gaurav showed higher tuber dry weight, fresh tuber yield, tuber number per plant, early start of tuber harvesting, root traits, stolon traits, NUE parameters, and higher amino acid(aspartic acid and asparagine) content at low N supply. Higher expression of nitrate reductase(NR), nitrite reductase(NIR), and asparagine synthetase(AS) genes was observed in the leaf tissues of Kufri Gaurav at high N. Thus, aeroponics-based precision phenotyping enables identification of NUE efficient genotypes based on key traits and genes involved in improving NUE in potato. Further, this study suggests that the potential of aeroponics can be utilized to investigate N biology in potato under different N regimes.

Digital phenotyping in depression diagnostics: Integrating psychiatric and engineering perspectives

Depression is a serious medical condition and is a leading cause of disability worldwide.Current depression diagnostics and assessment has significant limitations due to heterogeneity of clinical presentations,lack of objective assessments,and assessments that rely on patients'perceptions,memory,and recall.Digital phenotyping(DP),especially assessments conducted using mobile health technologies,has the potential to greatly improve accuracy of depression diagnostics by generating objectively measurable endophenotypes.DP includes two primary sources of digital data generated using ecological momentary assessments(EMA),assessments conducted in real-time,in subjects'natural environment.This includes active EMA,data that require active input by the subject,and passive EMA or passive sensing,data passively and automatically collected from subjects'personal digital devices.The raw data is then analyzed using machine learning algorithms to identify behavioral patterns that correlate with patients'clinical status.Preliminary investigations have also shown that linguistic and behavioral clues from social media data and data extracted from the electronic medical records can be used to predict depression status.These other sources of data and recent advances in telepsychiatry can further enhance DP of the depressed patients.Success of DP endeavors depends on critical contributions from both psychiatric and engineering disciplines.The current review integrates important perspectives from both disciplines and discusses parameters for successful interdisciplinary collaborations.A clinically-relevant model for incorporating DP in clinical setting is presented.This model,based on investigations conducted by our group,delineates development of a depression prediction system and its integration in clinical setting to enhance depression diagnostics and inform the clinical decision making process.Benefits,challenges,and opportunities pertaining to clinical integration of DP of depression diagnostics are discussed from interdisciplinary perspectives.

High-throughput phenotyping in cotton:a review

Recent technological advances in cotton(Gossypium hirsutum L.) phenotyping have offered tools to improve the efficiency of data collection and analysis.High-throughput phenotyping(HTP) is a non-destructive and rapid approach of monitoring and measuring multiple phenotypic traits related to the growth,yield,and adaptation to biotic or abiotic stress.Researchers have conducted extensive experiments on HTP and developed techniques including spectral,fluorescence,thermal,and three-dimensional imaging to measure the morphological,physiological,and pathological resistance traits of cotton.In addition,ground-based and aerial-based platforms were also developed to aid in the implementation of these HTP systems.This review paper highlights the techniques and recent developments for HTP in cotton,reviews the potential applications according to morphological and physiological traits of cotton,and compares the advantages and limitations of these HTP systems when used in cotton cropping systems.Overall,the use of HTP has generated many opportunities to accurately and efficiently measure and analyze diverse traits of cotton.However,because of its relative novelty,HTP has some limitations that constrains the ability to take full advantage of what it can offer.These challenges need to be addressed to increase the accuracy and utility of HTP,which can be done by integrating analytical techniques for big data and continuous advances in imaging.

Combined Drought and Heat Stress in Rice: Responses, Phenotyping and Strategies to Improve Tolerance

Simultaneous occurrence of drought and heat stress will have significant negative impact on rice yield,especially under upland conditions.The projected increase in global temperatures and reduced precipitation will increase the frequency of occurrence and intensity of these stresses,threatening rice production.Despite recognizing the importance of combined stress in rice,the knowledge generated in this area is very limited.Though complex,understanding combined stress tolerance of rice under water saving cultivation is more critical towards development of climate resilient rice cultivars.Here,we summarized the effects of combined stress on rice physiology with more emphasis on reproductive stage.Omics responses,phenotyping and physiology challenges and potential strategies for improving combined stress tolerance in rice are also discussed.

Comparison of Blood Group Molecular Genotyping to Traditional Serological Phenotyping in Patients with Chronic or Recent Blood Transfusion

Objectives: Accurately identifying the Antigens (Ags) on recipient red blood cells (RBCs) is critical in prevention of RBC alloimmunization in chronically transfused patients. The goal of this study was to compare RBC molecular genotyping to serological phenotyping in those patients. Methods: Serological phenotyping and molecular genotyping methods were used to study blood samples from 18 healthy blood donors and 16 transfused patients. Reticulocyte harvesting or hypotonic cell separation was added to recheck RBC phenotypes of the patients with discrepancies between phenotyping and genotyping. Results: No discrepancies were found between the two genotyping methods in all the donors and patients. 1 of 9 sickle-cell disease (SCD) patients and all 3 thalassemia patients demonstrated discrepancies in multiple blood groups between phenotyping and genotyping, which were not corrected by reticulocyte harvesting or hypotonic cell separation. Conclusions: These findings suggest that RBC molecular genotyping is superior to serological phenotyping in chronically transfused SCD or thalassemia patients.

A Phenotyping Protocol for Detailed Evaluation of Apple Root Resistance Responses Utilizing Tissue Culture Micropropagated Apple Plants

In the post-genomics era, reliable phenotypes are considered the bottleneck for unraveling the genetic control over the biology of interest. Phenotyping resistance response of roots to infection by soilborne pathogen is more challenging compared to that of plant aerial parts. In additional to the hidden nature and small stature of fine roots where infection occurs, extra obstacles exist for rosaceae tree crops such as apple. Due to self-incompatible reproduction and high-level heterozygosity of apple genome, genetically identical apple plants cannot be produced through apple seed germination. Here we report an established phenotyping protocol which includes a streamlined tissue culture procedure for micropropagation of uniform apple plants, standardized inoculation procedure using Pythium ultimum, and multilayered evaluating methods on apple root resistance traits. Because of the implementation of tissue culture based micropropagation procedure, constant availability of the uniform plants with defined genetic background, equivalent age and non-contaminated roots overcame a longstanding barrier of systematic and detailed phenotypic characterization of apple root resistance traits. Repeated infection assays by root-dipping inoculation demonstrated the reproducible and wide-range plant survival rates, from single-digit to over 90% survived plants for a given genotype. Genotype-specific values due to P. ultimum inoculation on shoot and root biomass reduction, maximum root lengths, leaf number and cumulative leaf areas were quantified between mock-inoculated and P. ultimum infected plants. Use of a glass-box container offered enhanced accessibility and minimized invasiveness for continuous and non-disruptive observation on the necrosis progression patterns along inoculated roots. With the assistance of a dissecting microscope, the genotype-specific resistance responses along the infected apple roots were captured and analyzed in detail. This reported phenotyping protocol represents a major development and should be easily adopted for other rosacea tree fruit crops with minor modifications.

Rapid three-dimensional phenotyping of congenital heart disease in mouse by micro-CT

Objective To establish three-dimensional phenotyping system for congenital heart disease in mouse and to lay a foundation for the study of phenotype identification and mechanism of congenital heart disease.Methods Twelve SPF C57BL/6 J wild type pregnant mice(8-10 week-old)were randomly divided into control group(n=6)and experimental group(n=6).

High-throughput phenotyping identifies plant growth differences under well-watered and drought treatments

The ability to screen larger populations with fewer replicates and non-destructive measurements is one advantage of high-throughput phenotyping(HTP)over traditinal phenotyping techniques.In this study,two wheat accessions were grown in a controlled-environment with a moderate drought imposed from stem elongation to post-anthesis.Red-green-blue(RGB)imaging was performed on 17 of the 22 d following the start of drought imposition.Destructive measurements from all plants were performed at the conclusion of the experiment.The effect of line was signifcant for shoot dry matter,spike dry matter,root dry matter,and tller number,while the water treatment was significant on shoot dry matter and root dry matter.The temporal,non-destructive nature of HTP allowed the drought treatment to be significantly differentiated from the well-watered treatment after 6 d in a line from Argentina and 9 d in a line from Chile.This difference of 3 d indicated an increased degree of drought tolerance in the line from Chile.Furthermore,HTP from the final day of imaging accurately predicted reference plant height(r=1),shoot dry matter(r=0.95)and tller number(r=0.91).This experiment ilustrates the potential of HTP and its use in modeling plant growth and development.

Image-based root phenotyping for field-grown crops:An example under maize/soybean intercropping

Root architecture,which determines the water and nutrient uptake ability of crops,is highly plastic in response to soil environmental changes and different cultivation patterns.Root phenotyping for field-grown crops,especially topological trait extraction,is rarely performed.In this study,an image-based semi-automatic root phenotyping method for field-grown crops was developed.The method consisted of image acquisition,image denoising and segmentation,trait extraction and data analysis.Five global traits and 40 local traits were extracted with this method.A good consistency in 1st-order lateral root branching was observed between the visually counted values and the values extracted using the developed method,with R^(2)=0.97.Using the method,we found that the interspecific advantages for maize mainly occurred within 5 cm from the root base in the nodal roots of the 5th-7th nodes,and that the obvious inhibition of soybean was mostly reflected within 20 cm from the root base.Our study provides a novel approach with high-throughput and high-accuracy for field research on root morphology and branching features.It could be applied to the 3D reconstruction of field-grown root system architecture to improve the inputs to data-driven models(e.g.,OpenSimRoot)that simulate root growth,solute transport and water uptake.

Initiation of Unmanned Aerial System (UAS) Phenotyping of Plant Height and Canopy Width in Guar

The use of the Unmanned Aerial System (UAS) has attracted scientific attention because of its potential to generate high-throughput phenotyping data. The application of UAS to guar phenotyping remains limited. Guar is multi-purpose legume species. India and Pakistan are the world’s top guar producers. The U.S. is the world guar largest market with an import value of >$1 billion annually. The objective of this study was to test the feasibility of UAS phenotyping of plant height and canopy width in guar. The UAS data were collected from a field plot of 10 guar accessions on July 7, 2021, and September 27, 2021. The study was organized in a Randomized Complete Block Design (RCBD) with 3 blocks. A total of 23 Vegetation Indices (VIs) were computed. The analysis of variance showed significant genotypic effects on plant weight (p < 0.05) and canopy width (p on plant height (p most VIs were significant for both flights (p Vegetation Index (NDVI) and Red Edge Normalized Difference Vegetation Index (NDRE) were significantly and highly correlated with plant height (r = 0.74) and canopy width (r = 0.68). The results will be of interest in developing high throughput phenotyping approach for guar breeding.

Development of Root Phenotyping Platforms for Identification of Root Architecture Mutations in EMS-Induced and Low-Path-Sequenced Sorghum Mutant Population

Sorghum’s natural adaptation to a wide range of abiotic stresses provides diverse genetic reserves for potential improvement in crop stress tolerance. Growing interest in sorghum research has led to the expansion of genetic resources though establishment of the sorghum association panel (SAP), generation of mutagenized populations, and recombinant inbred line (RIL) populations, etc. Despite rapid improvement in biotechnological tools, lack of efficient phenotyping platforms remains one of the major obstacles in utilizing these genetic resources. Scarcity of efforts in root system phenotyping hinders identification and integration of the superior root traits advantageous to stress tolerance. Here, we explored multiple approaches in root phenotyping of an ethyl methanesulfonate (EMS)-mutagenized sorghum population. Paper-based growth pouches (PGP) and hydroponics were employed to analyze root system architecture (RSA) variations induced by mutations and to test root development flexibility in response to phosphorus deficiency in early growing stages. PGP method had improved capabilities compared to hydroponics providing inexpensive, space-saving, and high-throughput phenotyping of sorghum roots. Preliminary observation revealed distinct phenotypic variations which were qualitatively and quantitatively systemized for association analysis. Phenotypes/ideotypes with root architecture variations potentially correlated with Pi acquisition were selected to evaluate their contribution to P-efficiency (PE). Sand mixed with P-loaded activated alumina substrate (SAS) provided closely to natural but still controlled single-variable conditions with regulated Pi availability. Due to higher labor and cost input we propose SAS to be used for evaluating selected sorghum candidates for PE. The ability of rapidly screening root phenotypes holds great potential for discovering genes responsible for relevant root traits and utilizing mutations to improve nutrient efficiency and crop productivity.

Assessment of a new strategy for selective phenotyping applied to complex traits in <i>Brassica napus</i>

The accurate mapping of quantitative trait loci (QTL) depends notably on the number of recombination events occurring in the segregating population. The cost of phenotyping often limits the sample size used in QTL mapping. To get round this problem, we assessed a selective phenotyping method, called qtlRec sampling. In order to improve the accuracy of QTL mapping, a subset of individuals was selected to maximize the number of recombination events at putative QTL positions;the usefulness of this subset was compared to a selected sample built to maximize the recombination rate over the whole genome. We assessed this method on the quantitative oil content trait in Brassica napus. We showed that the qtlRec strategy could allow increasing accuracy (both support interval and position) of QTL location while it maintained a similar power of detection. We then applied this approach to the B. napus—Leptosphaeria maculans pathosystem for which resistance QTL with minor effect were previously identified. This allowed the validation of the QTL in six genomic regions. The qtlRec method is an attractive strategy for validating QTL in multiple year and/or location trials for a trait which requires costly and time-consuming phenotyping.

Clinical asthma phenotyping:A trial for bridging gaps in asthma management

Asthma is a common disease affecting millions of people worldwide and exerting an enormous strain on health resources in many countries. Evidence is increasing that asthma is unlikely to be a single disease but rather a series of complex, overlapping individual diseases or phenotypes, each defined by its unique interaction between genetic and environmental factors. Asthma phenotypes were initially focused on combinations ofclinical characteristics, but they are now evolving to link pathophysiological mechanism to subtypes of asthma. Better characterization of those phenotypes is expected to be most useful for allocating asthma therapies. This article reviews different published researches in terms of unbiased approaches to phenotype asthma and emphasizes how the phenotyping exercise is an important step towards proper asthma treatment. It is structured into three sections; the heterogeneity of asthma, the impact of asthma heterogeneity on asthma management and different trials for phenotyping asthma.

Phenotyping of Hybrid Maize (<i>Zea mays</i>L.) at Seedling Stage under Drought Condition

Drought is envisaged as the greatest demolishing natural impacts throughout the world since it has observed extensive place of agronomical land sterile almost the world. It’s the significant crop output-limiting producer, and elaborated learning of its result on plant enhancement dictation is diametrical. At present, drought tolerant hybrid maize has been trying to induce Bangladesh especially drought affected zone to identify the drought endurance maize genotypes. Consequently, a feasible pot study of 49 hybrid maize genotypes were directed to determine an adequate drought level to promote aliment and promotion of maize plant below the water stress conditions with treatment (control and drought) and three replications. The data were received after 35 days of sowing using appropriate procedures. Specially, the stomata were collected by the white transparent nail polish from the lower part of leaves. Descriptive statistic of the all traits like percentage of SPAD, leaf rolling (LR), maximum root length (MRL), maximum shoot length (MSL), root dry matter (RDM), shoot dry matter (SDM), length of stomata (LS), width of stomata (WS), thickness of stomata (TS), total dry matter (TDM) and ANOVA for control and drought condition individually showed significant (P < 0.05) variations among the germplasm for their genotypes, treatment and interaction. The first fourth principal components (PCs) narrated about 82.0% of the total variation. Cluster analysis placed the 49 hybrid into 6 main groups among those cluster;groups five showed the maximum number mean value of traits. The highest positive relationship was obtained from TS, WS, RDM, SDM and TDM traits by forming genotype-traits bi-plot of 11traits of 49 genotypes. After analyzing, it is explicit that G18 (CML-80 × IPB911-16) and G22 (CZI-04 × IPB911-16) were the most tolerant hybrids maize genotypes and very susceptible hybrids maize genotypes were G16 (P-12 × CML487), G34 (CML-32 × PB911-16) and G37 (P-33 × CML487). It is expected that the higher expression of considered traits might be obligate for better yield under drought stress.

Phenotyping emphysema and airways disease: Clinical value of quantitative radiological techniques

The pathophysiology of chronic obstructive pulmonary disease(COPD) and Alpha one antitrypsin deficiency is increasingly recognised as complex such that lung function alone is insufficient for early detection, clinical categorisation and dictating management. Quantitative imaging techniques can detect disease earlier and more accurately, and provide an objective tool to help phenotype patients into predominant airways disease or emphysema. Computed tomography provides detailed information relating to structural and anatomical changes seen in COPD, and magnetic resonance imaging/nuclear imaging gives functional and regional information with regards to ventilation and perfusion. It is likely imaging will become part of routine clinical practice, and an understanding of the implications of the data is essential. This review discusses technical and clinical aspects of quantitative imaging in obstructive airways disease.

Laboratory-and Field-Phenotyping for Drought Stress Tolerance and Diversity Study in Lentil (Lens culinaris Medik.)

Drought susceptibility and low genetic variability are the major constraints of lentil(Lens culinaris Medik.)production worldwide.Development of an efficient pre-field drought phenotyping technique and identification of diversified drought tolerant lentil genotype(s)are therefore vital and necessary.Two separate experiments were conducted using thirty diverse lentil genotypes to isolate drought tolerant genotype(s)as well as to assess their diversity.In both of the experiments,significant(p≤0.01)variation in genotype(G),treatment(T)and G X T was observed for most of the studied traits.In experiment I,genotypes were examined for drought tolerance at the seedlings stage under hydroponic conditions by assessing root and shoot traits.Among the 30 genotypes studied,BM-1247,BM-1227 and BM-502 were selected as highly tolerant to drought stress as they showed maximum seedling survivability and minimum reduction in growth parameters under drought stress.In experiment II,the genotypes were assayed for diversity and drought stress tolerance based on morphological traits grown under field condition.Drought stress caused a substantial reduction in yield attributing traits,however,the genotypes BM-1247,BM-981,BM-1227 and BM-502 were categorized as drought tolerant genotypes with less than 20%yield reduction.The field screening result of drought stress tolerance was coincided well with the results of laboratory screening.Genetic divergence study reflected the presence of considerable diversity among the genotypes.Considering laboratory and field screening results,the genotypes,BM-1247,BM-1227,BM-981 and BM-502 were selected as the best drought tolerant genotypes.This information can be exploited for further breeding in developing drought tolerance in lentil.