Plant Methods最新文献

{"title":"A reproducible compartment-aware k-mer set-algebra and MAW workflow for plant genomes maps contrasting nuclear-organelle sharing landscapes in Arabidopsis and rice.","authors":"Ryo Ootsuki","doi":"10.1186/s13007-026-01547-0","DOIUrl":"10.1186/s13007-026-01547-0","url":null,"abstract":"<p><strong>Background: </strong>Plant cells contain three genetically distinct DNA compartments-nuclear, chloroplast, and mitochondrial-and biologically meaningful sequence sharing among them is expected because organellar DNA can move into the nucleus and, in some cases, between organelles. This complicates alignment-free k-mer analysis, the interpretation of compartment-specific sequence vocabularies, and the evaluation of missing-sequence signals such as minimal absent words (MAWs). A reproducible workflow that treats these compartments explicitly is therefore useful both for plant genome analysis and for read-backed quality control.</p><p><strong>Results: </strong>A fully scripted workflow was applied to a telomere-to-telomere-scale Arabidopsis thaliana nuclear reference (Col-CEN v1.2) and a chromosome-level Oryza sativa ssp. japonica reference (GCF_034140825.1), together with chloroplast, mitochondrial, and raw-read datasets. Distinct canonical k-mer types were counted for k = 11-31 and decomposed into mutually exclusive set-algebra categories. The same framework was then used for read-backed validation and for MAW/nullomer testing under Markov models with false-discovery-rate (FDR) control. The two plant species showed markedly different sharing landscapes. In Arabidopsis, chloroplast k-mers became largely compartment-specific by k = 31 (85.6% of the chloroplast set), whereas mitochondrial k-mers remained dominated by nuclear overlap (93.4% of the mitochondrial set at k = 31). In rice, chloroplast k-mers remained strongly shared with the nuclear genome across the entire range (88.6% of the chloroplast set at k = 31), whereas mitochondrial-nuclear sharing remained high but lower than that in Arabidopsis (77.5% at k = 31). Raw-read validation showed that assembly-derived k-mers were almost completely supported by reads in both species (> 99.7% at k = 31 and KMC3 -ci = 1), whereas the read-only fraction collapsed sharply as the minimum-occurrence threshold (-ci) increased from 1 to 10. Because one raw-read dataset was analyzed per species, these contrasts are best interpreted as species-specific workflow case studies rather than as a direct sequencing-platform benchmark. MAW lists derived from chloroplast, mitochondrial, nuclear, and raw-read datasets contained many candidates, but all FDR-adjusted runs returned zero significant nullomers, consistent with the corresponding sequence-based null models rather than with biologically exceptional absence.</p><p><strong>Conclusions: </strong>This workflow provides a reproducible framework for quantifying compartment-specific and shared plant sequence vocabularies, validating those vocabularies against raw reads, and testing absent-word candidates under explicit null models. The two-species application shows that chloroplast and mitochondrial compartments need not behave similarly and that raw-read-only vocabularies are highly sensitive to low-support k-mers. Together, these analyses provide a robust ","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13459230/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148163910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing a sinusoidal-polynomial fitting model for deriving the structural and biochemical circadian rhythms for different parts of Birch from hyperspectral LiDAR data.","authors":"Shao Dong, Yi Lin","doi":"10.1186/s13007-026-01548-z","DOIUrl":"10.1186/s13007-026-01548-z","url":null,"abstract":"<p><p>A deeper understanding of circadian rhythms in plants, especially trees, is crucial for uncovering how structural and physiological processes align with daily environmental cycles. However, most studies analyze biochemical changes and positional variations separately, with limited exploration of their coordination within the whole-plant system. Hyperspectral light detection and ranging (HSL) integrates three-dimensional (3D) structural mapping with hyperspectral reflectance, enabling non-destructive assessment of plant biochemistry. Previous work showed that HSL can detect nocturnal vertical canopy displacements with centimeter accuracy, but organ-level rhythmic patterns (e.g., branches vs. leaves) remain poorly studied. Here, we developed a hyperspectral point cloud classification method combining spectral and spatial data to separate branches from leaves and analyze their sleep movements independently. A novel sinusoidal-polynomial fitting model was then proposed to characterize circadian rhythms in both sleep movements and reflectance variations. We applied HSL data from a single birch tree (Betula pendula) collected at 30 distinct HSL measurement times over 24 h to develop a 3D canopy partitioning approach that divides the canopy into nine grids (3 × 3) and ten vertical layers per grid. Results revealed near-24-hour rhythmic patterns (max R² = 0.5841, P < 0.05) and stratified sleep movements: branches exhibited larger amplitudes than the corresponding canopy layers, with the overall maximum movement amplitude occurring shortly before sunrise (04:00-06:30) and recovering after sunrise. The model also effectively characterized diurnal reflectance variations (max R² = 0.5812, P < 0.05). In addition, chlorophyll-related spectral indices exhibited a sinusoidal variation, reaching a minimum around 03:00. These findings highlight the potential of HSL for the joint analysis of structural and biochemical circadian rhythms, providing a non-destructive approach to investigate plant rhythmicity in both structural and physiological domains.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13449568/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148157638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"2NPLGBM: a genomic model that merges the strengths of classical and machine learning methods in genomic prediction.","authors":"Bright Enogieru Osatohanmwen, Indalécio Cunha Vieira, Ahmad Reza Sharifi, Timothy M Beissinger","doi":"10.1186/s13007-026-01545-2","DOIUrl":"10.1186/s13007-026-01545-2","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Genomic prediction (GP) is a central component of modern plant breeding, enabling the early selection of superior genotypes based on genomic marker data. Classical GP models, such as genomic best linear unbiased prediction (GBLUP), operate within the data modeling culture and typically assume additive genetic effects, with extensions required to model non-additive effects such as dominance and epistasis. In contrast, machine learning (ML) models from the algorithmic modeling culture can flexibly model complex, non-additive genetic relationship but often lack direct grounding in quantitative genetic theory and interpretability. To bridge these gaps, we propose 2NPLGBM, a hybrid genomic prediction approach that integrates quantitative genetics with ML. This method introduces a two-matrix (2NP) genotype representation by concatenating additive (Z) and dominance (W) matrices, which are then used as input to a Light Gradient Boosting Machine (LGBM), enabling the simultaneous modeling of additive, dominance, and higher-order genetic interactions (AA, AD, DD).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The 2NPLGBM model was evaluated using six years of test-cross hybrid maize trial data across four agronomic traits (grain yield, plant height, days to silking, and days to anthesis) under five cross-validation schemes simulating temporal: Leave-One-Year-Out (LOYO), Rolling Window (RW), and genetic generalization: Five-Fold, and tester-based schemes (Tester CV0 and Tester CV00). Compared to GBLUP, 2NPLGBM achieved an average of 5% improvement in predictive accuracy under temporal validations and over 15% gains under tester-based schemes, particularly for flowering traits (days to silking and days to anthesis). Performance was generally comparable to LGBM, with both ML models outperforming GBLUP for most traits. Under Tester CV0, 2NPLGBM showed its strongest relative advantage over LGBM for flowering traits, suggesting improved capture of interaction-related genetic signals, whereas LGBM generally performed best for plant height and grain yield. In five-fold CV and Tester CV00, GBLUP remained competitive for some traits, while both machine learning models showed reduced gains, with LGBM slightly outperforming 2NPLGBM. In addition, 2NPLGBM generally improved selection efficiency over GBLUP and, in most cases, LGBM, indicating enhanced ability to capture complex genetic signals relevant for hybrid ranking, particularly for flowering traits, whereas LGBM tended to achieve the highest selection efficiency for plant height and grain yield. Feature interpretation using Shapley Additive exPlanations (SHAP) confirmed that non-additive interactions contributed substantially to prediction accuracy for highly heritable traits. It also revealed trait-specific architectures, additive effects dominated flowering traits, while dominance effects contributed more to plant height and yield. Classical variance component analysis supported these findings, ","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13221760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148055992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coformer: a deep learning-based framework for cross-environment and multi-year cotton phenotype prediction and interpretation.","authors":"Huan Liu, Longyu Huang, Jiale Li, Zikang He, Xiaoyan Zhao, Qingzhuo Chen, Jian Wang, Guomin Zhou, Jianhua Zhang","doi":"10.1186/s13007-026-01528-3","DOIUrl":"10.1186/s13007-026-01528-3","url":null,"abstract":"<p><p>Accurate prediction of key agronomic traits in cotton is crucial for advancing its genetic improvement and enabling breeding-by-design. However, when using high-dimensional genomic data (e.g., massive SNP markers) for prediction, traditional models often suffer from overfitting and poor generalization. To address this, we propose an innovative deep learning model-Coformer. Coformer is a hybrid Transformer-autoencoder model: a self-attention Transformer encoder captures long-range SNP dependencies and compresses high-dimensional genotypes into a compact latent representation, which is then decoded by a supervised prediction head to the target phenotype. Through rigorous evaluation on a combined multi-environment, multi-year dataset, Coformer maintains outstanding predictive robustness even without explicitly modeling environmental factors. The model integrates a normalization module and a linear projection layer to enable adaptive input processing and end-to-end training, effectively improving generalization across varying data dimensionalities. Importantly, Coformer is interpretable: it can precisely pinpoint key genetic loci that influence target traits, providing a solid theoretical basis for deeper insight into the genetic underpinnings of phenotypes and for implementing precision breeding. In addition, to accelerate application and dissemination, we have concurrently developed a browser-based Cotton Phenotype Prediction System (CPPS) that seamlessly integrates the full workflow of \"data preparation-model training-result interpretation\" into a unified graphical interface. The system supports batch processing and result visualization, substantially lowering the barrier for non-specialists and offering an efficient, user-friendly solution to bridge genomics research and breeding practice.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13495428/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148006392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When methods matter: solvent effects on pollinator responses to quantum-dot-labeled pollen.","authors":"Barbara Płaskonka, Marcin Zych, Alina Liersch, Joanna Wolko, Maria Woszczenko, Katarzyna Roguz","doi":"10.1186/s13007-026-01544-3","DOIUrl":"10.1186/s13007-026-01544-3","url":null,"abstract":"<p><strong>Background: </strong>Pollination, one of the key plant-animal interactions, has been intensively studied, yet a major gap remains in our ability to track the fate of individual pollen grains. Since 2019, the use of quantum dots (QDs) as an easy, cost-effective in situ pollen-labeling technique has begun to fill this gap by allowing direct, fine-scale tracking of pollen without impeding its transport. QDs are typically applied in a volatile organic solvent, a methodological step that is usually assumed to be behaviorally neutral, but could in principle alter floral visual and olfactory cues. Because accurate pollen tracking requires labeling methods that do not themselves affect pollinator behavior, we ask whether and how insect pollinators respond to flowers whose anthers have been treated with QDs and their solvent carrier.</p><p><strong>Results: </strong>Using a common-garden experiment with genetically uniform Brassica napus plants, we compared pollinator visitation and foraging behavior among flowers bearing QDs-solvent treatments, solvent-only controls, and untreated controls. Overall, our results support the use of QDs as a powerful and generally acceptable tool for tracking pollen transfer: pollinators did not avoid flowers with QDs-labeled pollen. Visitation did not differ among flowers labeled with different QDs colors, supporting within-study comparisons of multiple QDs colors. However, we detected an effect of the solvent: flowers exposed to QDs-solvent and solvent-only treatments received fewer visits and, in some cases, reduced foraging activity, particularly in honeybees.</p><p><strong>Conclusions: </strong>Because accurate pollen tracking requires labeling methods that do not themselves affect pollinator behavior, our findings show that quantum dots meet this requirement. However, the solvent used for their application can influence pollinator behavior. These effects, although moderate, indicate that potential side effects of solvents and labeling procedures should be carefully considered, controlled, and reported when designing QDs-based experiments and interpreting pollinator behavior.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13455316/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148006422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coupling of high-resolution mass spectrometer and photosynthesis system for comprehensive leaf volatile metabolite profiling.","authors":"Kelsey R Carter, Christian Mark Salvador, Savana Colegate, Alyssa Carrell, Jun Hyung Lee, Robert Smith, Marshal McDonnell, Sara Jawdy, David McLennen, Tyler Hackworth, Lianhong Gu, Melanie A Mayes, Udaya Kalluri, Thomas D Sharkey, David J Weston","doi":"10.1186/s13007-026-01531-8","DOIUrl":"10.1186/s13007-026-01531-8","url":null,"abstract":"<p><strong>Background: </strong>Leaf-level biogenic volatile organic compounds (BVOCs) emissions represent a major source of organic gases in the atmosphere, influencing both climate and air quality. These emissions are strongly driven by environmental perturbations, which affect individual plant- to ecosystem-level processes. Uncovering all the BVOCs and understanding how their emissions respond to altered environmental conditions provide critical insights into vegetation-driven changes in atmospheric chemistry. We developed a tandem instrumentation setup that integrates a proton transfer reaction time-of-flight mass spectrometer (PTR-ToF-MS) with parts-per-trillion detection limits and a photosynthetic infrared gas exchange system for the untargeted survey of all the BVOCs. This novel system enables simultaneous, real-time monitoring of BVOC emissions and photosynthetic parameters at the leaf level, offering new opportunities to disentangle the physiological and environmental drivers of VOC release. Furthermore, we established the VOC Analysis and Processing Optimization Resource (VAPOR), an open-access software tool designed for rapid data post-processing and the analysis of the variability of hundreds of BVOCs. We assessed the performance of the tandem system under varying background conditions, using standard gas mixtures and a range of environmental factors.</p><p><strong>Results: </strong>Blank emissions were substantially lower for major BVOCs (e.g., isoprene) compared to those observed in plant emissions. Despite this, the observation of background-level VOCs highlights the importance of routinely acquiring and accounting for blank measurements in analyses using the coupled instrumentation. Introduction of known VOC concentrations to the system demonstrated a linear response across different compounds with varying molecular compositions, indicating minimal gas loss regardless of chemical moieties within the coupled instrumentation. We applied the optimized system to investigate the physiological mechanisms driving BVOC emissions across different genotypes of poplar and pennycress. The high mass resolution capabilities of the PTR-ToF-MS, coupled with comprehensive VAPOR-driven data analysis, enabled the identification of several important BVOCs, including methanol and methanethiol; these BVOCs displayed substantial variation across pennycress genotypes and showed concentrations ~ 100-350% higher than the blank. Moreover, isoprene emissions varied significantly among poplar genotypes grown in different potting media.</p><p><strong>Conclusions: </strong>Tandem instrumentation offers a powerful tool for profiling volatile molecular markers and elucidating their genetic and environmental underpinnings. This approach enhances our ability to predict BVOC emissions in response to genotype by environmental interactions and contributes to a deeper understanding of vegetation responses to environmental changes.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13308210/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148006441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Improving 3D reconstruction quality for root phenotyping: assessing the impact of camera calibration and imaging parameters.","authors":"Peter Pietrzyk, Suxing Liu, Alexander Bucksch","doi":"10.1186/s13007-026-01542-5","DOIUrl":"10.1186/s13007-026-01542-5","url":null,"abstract":"","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"22 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13188273/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147974547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Projecting 2D top-view of PSII efficiency onto 3D plant models to quantify PSII efficiency across canopy layers.","authors":"Mieke van Vlaardingen, Aparna Thulaseedharan, Luisa M Trindade, Lucia Sandra Perez-Borroto, Eibertus N van Loo","doi":"10.1186/s13007-026-01536-3","DOIUrl":"10.1186/s13007-026-01536-3","url":null,"abstract":"<p><strong>Background: </strong>High-throughput automated image analysis holds great promise for plant breeding by enabling faster, more accurate assessment of traits relevant to crop improvement. Imaging-based systems, such as the CropReporter, allow automated quantification of photosynthetic parameters like PSII efficiency under ambient light from a top-down 2D perspective. However, standard analysis tools average values across the 2D top view, overrepresenting upper leaves and underrepresenting those in the lower canopy. Upper leaves may occlude lower ones, and due to the pinhole projection of the camera, lower leaves of the same size appear smaller in the image. Consequently, vertical heterogeneity in PSII efficiency within the canopy cannot be resolved using a single 2D image.</p><p><strong>Results: </strong>To address these issues, we integrated top-view PSII efficiency data (by CropReporter) with 3D structural data from RGB point clouds (by MaxiMarvin). Alignment accuracy between MaxiMarvin and CropReporter was high, with R² ≥ 0.98 for the x-axis and R² ≥ 0.99 for the y-axis. The method was tested using Chenopodium quinoa, Glycine max, and Solanum tuberosum, exposed to salinity, waterlogging and drought stress respectively. In Chenopodium quinoa, it allowed precise determination of when senescence began in the lower leaves. In Solanum tuberosum, the reduction in PSII efficiency by drought was the same for all leaf layers, while in Glycine max, waterlogging stress most strongly affected the middle layer of the canopy.</p><p><strong>Conclusions: </strong>This framework enables the 3D mapping of PSII efficiency across the vertical plant profile by combining top-view chlorophyll fluorescence imaging (CropReporter) with 3D structural data (MaxiMarvin). It reveals vertical variation in photosynthetic activity across canopy layers. With standard 2D chlorophyll fluorescence imaging it is difficult to distinguish between non-photosynthetic tissues like flower heads and lower layers of leaves, that might have the same PSII values. Using height-based filtering, taking data from the 3D mapping, such distinction can be made with the method presented in this paper. This allows estimating the PSII efficiencies of leaves only. By capturing layer-specific responses to abiotic stress and developmental changes, the method provides physiologically relevant input for crop growth modelling and highlights the importance of accounting for canopy structure in photosynthetic analyses.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13523333/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147932410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid metaheuristic optimization of a DeepFusionNet for plant leaf disease diagnosis and recommendation.","authors":"Shantilata Palei, Puspanjali Mohapatra, Soubhagya Ranjan Mallick, Princy Diwan","doi":"10.1186/s13007-026-01535-4","DOIUrl":"10.1186/s13007-026-01535-4","url":null,"abstract":"<p><p>Early diagnosis of plant leaf diseases plays an important role in protecting crop yields and supporting sustainable agriculture. This paper proposes an improved DeepFusionNet model optimized through a hybrid Flower Pollination Algorithm and Butterfly Optimization Algorithm, balancing global exploration with local refinement for faster and more stable convergence. The model combines DenseNet201 and MobileNetV2 by compressing their final convolutional feature maps with 1×1 convolutions and fusing them along the channel dimension to form a compact and discriminative representation. This fused representation is then classified using a Random Forest classifier. This framework consistently achieves high accuracy on all eight datasets, with performance ranging between 97.07% and 99.66%. Extensive experiments are performed that include statistical validation, convergence studies, and reliability tests to prove the robustness of the approach. Furthermore, to make it practically useful, the whole system is embedded into a mobile application capable of real-time disease detection and providing actionable recommendations to farmers for the effective treatment and prevention of diseases.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13285044/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147819596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ADAM: advanced design and AI-driven modeling for plant tissue culture media optimization.","authors":"Hans Bethge, Traud Winkelmann, Tomás A Arteta, Esmaeil Nezami, Marco Pepe, Mohsen Hesami, Andrew Maxwell Phineas Jones, Mariana Landin, Pedro P Gallego","doi":"10.1186/s13007-026-01534-5","DOIUrl":"10.1186/s13007-026-01534-5","url":null,"abstract":"<p><strong>Background: </strong>Optimization of biotechnological processes is traditionally limited by time-consuming trial-and-error approaches and the complexity of simultaneously optimizing multiple, often conflicting objectives. This applies particularly to plant tissue culture medium design, which therefore serves as the application case in this study. Recent advances in machine learning and evolutionary algorithms offer powerful alternatives, yet 80% of published studies rely on licensed software, and systematic data-driven optimization frameworks remain scarce. This creates significant barriers to adoption in both academic and commercial plant biotechnology.</p><p><strong>Results: </strong>We introduce ADAM (Advanced Design and AI-Driven Modeling for Plant Tissue Culture Media Optimization), an open-access, web-based platform that transforms protocol development into a data-driven computational process. ADAM implements a complete ML-EA workflow through five integrated modules: 1. Design of Experiments (five different concepts) for systematic parameter exploration, 2. Data Preparation with automated quality control, and 3. Model Building using nine machine learning algorithms with automated selection. The platform enables Optimization (4.) through four advanced evolutionary algorithms (genetic algorithm, particle swarm optimization, NSGA-II, SMS-EMOA) for single- and multi-objective problems, with Evaluation (5.) tools to compare original versus optimized solutions. Validation across two plant tissue culture applications showed that ADAM's models matched or exceeded the predictive performance of manually optimized approaches in the original studies. The platform successfully identified multiple optimal culture conditions balancing conflicting objectives, providing experimentally testable predictions that reduce the trial-and-error cycle.</p><p><strong>Conclusions: </strong>Deployed as a browser-based application requiring neither specialized hardware nor software licenses, ADAM democratizes advanced AI optimization for plant biotechnology, eliminating traditional barriers to entry while maintaining the rigor and flexibility required for scientific research.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":"22 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13130802/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147777852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}