Plant Methods最新文献

{"title":"Enhanced corn leaf disease detection using sharpness-aware minimization optimized CNNs.","authors":"Manoj Kumar Sharma, Richa Sharma, Gireesh Kumar","doi":"10.1186/s13007-026-01514-9","DOIUrl":"10.1186/s13007-026-01514-9","url":null,"abstract":"<p><p>Crop diseases significantly threaten global food security by directly affecting the crop yield and quality. The traditional diagnostic methods are labour intensive and human error prone. However, the existing deep learning solutions suffer with poor generalization due to the sharp loss landscapes. The proposed work addresses this limitation and optimizes the Convolutional Neural Network (CNN) using the Sharpness-Aware Minimization (SAM). This method minimizes both the training loss and loss landscape sharpness and enables the model to converge to a flatter-minima with improved generalization. The proposed work is evaluated on 60,000 corn leaf image samples for four classes with 15,000 balanced samples per class after augmentation. The optimized CNN model has achieved 99.66% test accuracy at 0.33% classification error rate and outperforms the conventional optimizers like Adam (98.44% accuracy) and the Stochastic Gradient Descent (SGD). The state-of-the-art analysis presents a 99% average precision rate along with 99.66% F1-score and 0.0013% mean squared error (MSE). The quantized model achieves an inference latency of 22.7 ms/image (≈44 FPS) on a Raspberry Pi 4 and reduces model overfitting and enhances feature discriminability. These results underscore the potential of SAM-based optimization in precision agriculture by driving a scalable automation of disease management. This work bridges the gap between theoretical advances in deep learning optimization and practical deployment in resource-constrained farming environments.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13200352/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147593831","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":"Controlling heterologous protein synthesis through a plant RNA ThermoSwitch.","authors":"Filip Lastovka, Hadrien Peyret, George P Lomonossoff, Betty Y-W Chung","doi":"10.1186/s13007-026-01517-6","DOIUrl":"10.1186/s13007-026-01517-6","url":null,"abstract":"<p><strong>Background: </strong>Plants are far from passive in the face of changing temperatures and have evolved transcriptional, post-transcriptional, and post-translational strategies to stay one step ahead of the environment. Among the most exciting recent discoveries are RNA ThermoSwitches, embedded within 5' untranslated regions (UTR) of several mRNAs. These cis-acting RNA elements sense temperature shifts and instantly tune translational output, acting as molecular thermostats inside the cell. First uncovered in Arabidopsis thaliana, ThermoSwitches are now emerging as a powerful new frontier for biotechnology, offering a programmable way to modulate protein production through temperature adjustments.</p><p><strong>Results: </strong>Using a dual fluorescence reporter construct introduced by Agrobacterium-mediated transient expression, we have demonstrated that the native ThermoSwitch within the 5' UTR of the Arabidopsis phytochrome-interacting factor 7 (PIF7) mRNA functions as a potent temperature-responsive module in Nicotiana benthamiana leaves. A shift from 17 to 27 °C triggered a pronounced increase in reporter translation, delivering ~ 70% higher output within one day. This magnitude of enhancement mirrors the rise in endogenous PIF7 translation observed in Arabidopsis following the same temperature shift. The response remained even when the native upstream 5' UTR context was replaced with an unrelated sequence, demonstrating that the ThermoSwitch operates autonomously. Crucially, locking the hairpin into a strengthened, rigid conformation abolished the temperature response entirely.</p><p><strong>Conclusions: </strong>This work provides the first in vivo evidence that a native plant RNA ThermoSwitch functions effectively in an Agrobacterium-mediated transient expression system, establishing a homogeneous, temperature-responsive gene regulation system, free from chemical inducers or repressors. Demonstrating that the Arabidopsis PIF7 ThermoSwitch operates autonomously in Nicotiana benthamiana highlights its value as a versatile plug-and-play module that can be readily deployed across plant systems for broad biotechnological applications.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13353011/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147575171","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":"Investigating phloem transport dynamics in Arabidopsis through compartmental modelling of positron emission tomography data.","authors":"Jens Mincke, Karen J Kloth, Sarah Verbeke, Ken Kersemans, Stefaan Vandenberghe, Christian Vanhove, Kathy Steppe","doi":"10.1186/s13007-026-01525-6","DOIUrl":"10.1186/s13007-026-01525-6","url":null,"abstract":"<p><strong>Background: </strong>Phloem is the long-distance transport tissue of vascular plants in which photoassimilates are distributed from sources (e.g., leaves) to sinks (e.g., roots, fruits). Phloem transport occurs under pressure, making it very sensitive to manipulation and almost experimentally inaccessible. Therefore, functional data on phloem speed and dynamic distribution of photoassimilates along the transport pathway are still scarce, both in trees and herbaceous plants. This study presents a methodological pipeline to image phloem transport in very thin shoots of the model plant Arabidopsis using photosynthetic uptake of ¹¹CO₂ and state-of-the-art positron emission tomography (PET).</p><p><strong>Results: </strong>Successful application of the latest generation preclinical PET scanners allowed in vivo visualization of internal movement of ¹¹C-labelled photoassimilates inside primary and secondary shoots of 1 to 2 mm diameter every 5 min. Using this data as input in a compartmental model enabled estimation of (i) phloem front speed, and (ii) radial carbon partitioning between leakage-retrieval phloem, carbon storage and respiratory efflux. The methodology shows that the phloem front speed of recently fixed carbon in primary shoots was almost two-fold the speed in secondary shoots (128 vs. 70 µm s^-1). Furthermore, it was estimated that the fraction of recently fixed ¹¹CO₂ that was unloaded from the phloem to the surrounding storage cells and retrieved back into the phloem was higher in primary shoots than in secondary shoots, and that allocation to the storage compartment was higher in secondary shoots. Within the primary shoot, the fraction of unloading and retrieval of the ¹¹C-labelled photosynthates increased towards the inflorescence.</p><p><strong>Conclusion: </strong>Here, we demonstrate the synergistic application of high-resolution PET scanning and compartmental modelling as a promising approach to advance our understanding of phloem dynamics in small-dimension plants, such as the model plant Arabidopsis. With this, an opportunity is created to explore the genetic basis of phloem dynamics.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13154432/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147582010","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":"Enhancing hybridization potential through standardizing emasculation techniques and molecular marker integration in finger millet (Eleusine coracana L.).","authors":"Jwala Pranati, Priyanka Joshi, Himabindu Kudapa, Hrishikesh Pravin Ingole, Srikanth Panthulugiri, Mani Vetriventhan, Kalakanti Ramya, Shaik Abdul Muqsith, Srinivasulu Pannem, Anilkumar Vemula, Yashoda Jadhav, Manda Sriswathi, Shashi Kumar Gupta, Sean Mayes, Kuldeep Singh, Sobhan Sajja","doi":"10.1186/s13007-026-01522-9","DOIUrl":"10.1186/s13007-026-01522-9","url":null,"abstract":"<p><strong>Background: </strong>Finger millet (Eleusine coracana L.) has been cultivated for thousands of years in semi-arid regions of Asia and Africa. The grains have immense nutritional potential, but the genetic gains needed for high yield are yet to be realized. In the absence of an efficient crossing technique, recombination breeding is still challenging in finger millet genetic improvement programs, owing to its small floret size and highly self-fertilizing nature. In this study, we evaluated three different emasculation methods for finger millet, including a modified hot water technique and different concentrations of two gametocides, trifluoromethanesulfonamide (TFMSA) and gibberellic acid (GA₃) at different plant growth stages.</p><p><strong>Results: </strong>The study revealed a successful emasculation rate of up to 80% using modified hot water treatment at 52 °C for 2 min, when treated on the second day of anthesis in the designated panicles. Further, a similar success rate was noted with a single dose of TFMSA @ 10 mg or two doses of GA₃ @ 1500 ppm applied during the booting stage (7-9 days prior to panicle emergence). To validate the efficiency of these hybridization methods and to test the genetic purity of hybrids generated in this study, a set of 10 single nucleotide polymorphism (SNP) markers were used.</p><p><strong>Conclusion: </strong>These improved emasculation methods (Modified hot water, TFMSA, GA₃) integrated with molecular markers for hybridity testing represent an important step forward in finger millet crop improvement.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13151259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147575079","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":"Go Big or go home: a new gene ontology subset that improves plant gene function prediction.","authors":"Leila Fattel, Carolyn J Lawrence-Dill","doi":"10.1186/s13007-026-01523-8","DOIUrl":"10.1186/s13007-026-01523-8","url":null,"abstract":"<p><strong>Background: </strong>The availability of gene function prediction datasets helps researchers to consider possible functions for uncharacterized genes for hypothesis generation, candidate gene prioritization, and many other applications. Many such datasets are based on the Gene Ontology (GO) function graph. For plants this can be problematic because the most specific GO terms available are often derived from the biology of non-plant taxa (e.g., functions specific to nerve function would not seem likely to map to plant biological processes given that plants lack nerves). To balance the need for functional specificity while limiting to functions relevant to plant biology, researchers often limit to the GO Slim plant subset, but, by design, that subset consists of very general terms and limits real utility for, e.g., specific hypothesis generation. Worse yet, sometimes researchers choose to simply throw out terms if they are not relevant to plant biology (rather than traversing the GO graph to select the most specific term in that hierarchy that is compatible with plant biology).</p><p><strong>Results: </strong>We created GO Big, a Gene Ontology subset type, to improve the biological relevance of gene function predictions for taxon-specific biology applications. GO Big plant subsets retain maximal functional specificity for hypothesis generation while limiting to terms applicable to the biology of plants. In brief, we used a curatorial approach to generate two GO Big subsets, a general subset derived from terms with experimentally validated functions across Viridiplantae species, and a species-specific subset for maize (Zea mays ssp. mays).</p><p><strong>Conclusion: </strong>Annotating genes with assignments that better reflect the biology of a taxon can pave the way for more biologically accurate and testable hypotheses for genes of interest. The subsets produced here can help plant biologists limit genome-wide gene function prediction sets to functions possible for plant genes, and the process to generate GO Big subsets is described in detail to enable others to create GO Big subsets for additional taxon sets, including ones for protists, fungi, and other phylogenetic categories.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13154503/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147575143","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":"Enhancing plant disease detection through multi-modal integration of visual and textual data.","authors":"Xuewei Wang, Jun Liu","doi":"10.1186/s13007-026-01521-w","DOIUrl":"10.1186/s13007-026-01521-w","url":null,"abstract":"<p><p>Plant diseases pose a significant threat to global agriculture, impacting crop yields and quality. Early and accurate detection is essential for effective health management but remains challenging due to visual similarity among diseases and complex field backgrounds. This study introduces AgriMM, a novel multi-modal detection framework that integrates visual images with expert-validated textual descriptions to improve diagnostic precision. The framework features three key innovations: a Hybrid Convolutional-Attention Collaborative Backbone (HCACB) to capture both fine-grained lesions and global context; a Context-enhanced Visual-Language Path Aggregation Network (CVL-PAN) for multi-scale feature fusion; and an Adaptive Region-Text Contrastive Learning (AR-TCL) module to enforce precise semantic alignment. We constructed a comprehensive dataset comprising 30,000 images and detailed symptom descriptions across five major crops (tomato, cucumber, pepper, eggplant, and squash). Experimental results demonstrate that AgriMM achieves a mean Average Precision (mAP) of 95.2%, significantly outperforming state-of-the-art unimodal baselines by 11.6%. These findings confirm that integrating linguistic semantic priors effectively resolves visual ambiguity, providing a robust tool for precision agriculture and sustainable crop protection.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13034609/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147513907","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":"PestDetectSim: an integrated approach for crop pest diagnosis using object detection and similarity-based image retrieval.","authors":"Jimin Lee, Helin Yin, Dong Jin, Subin Park, Ri Zheng, Yeong Hyeon Gu","doi":"10.1186/s13007-026-01520-x","DOIUrl":"10.1186/s13007-026-01520-x","url":null,"abstract":"<p><strong>Background: </strong>Rapid and accurate pest diagnosis is essential for reducing crop losses and improving agricultural productivity. Most existing methods rely on deep learning-based object detection to classify pests into predefined categories. However, these models typically select the highest-probability class, which can lead to misclassification and limit practical usability due to the lack of user verification or intervention. Therefore, a framework that integrates model-based prediction with user-assisted validation is needed to enhance diagnostic reliability in real-world agricultural environments.</p><p><strong>Results: </strong>We propose PestDetectSim, an integrated framework that combines object detection with similarity-based image retrieval. In PestDetectSim, pest objects are first detected using the YOLO v8 model, and detected regions are processed through a backbone network augmented with a Squeeze-and-Excitation (SE-Net) module to extract feature vectors. These feature vectors are then used to retrieve visually similar pest images, enabling users to cross-check and refine the diagnosis. PestDetectSim produces two outputs: object detection results and a ranked list of similar reference images. We evaluated the framework using a real-world field dataset comprising 30 pest species. On a real-world field dataset of 30 pest species, PestDetectSim attains 98.82% end-to-end diagnostic accuracy while providing case-based visual evidence via retrieved similar images, enabling user verification in ambiguous cases. The end-to-end inference time is approximately 60 ms per image, including both detection and retrieval. This value represents the overall performance of the full pipeline, which integrates the detection stage with the similarity based retrieval stage, making the system suitable for real time deployment on resource limited devices.</p><p><strong>Conclusions: </strong>PestDetectSim integrates automated detection with user-assisted verification, offering practical reliability through case-based visual evidence, with modest accuracy gains complemented by improved interpretability. Furthermore, a prototype smartphone application was developed to validate its practicality in real-world conditions. This application allows users to capture pest images, receive instant detection results, and review retrieved similar images for verification. These findings demonstrate PestDetectSim's potential as a reliable and interactive diagnostic tool for real-time pest monitoring and sustainable agricultural management.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122962/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147486995","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":"FloraSyntropy-net: scalable deep learning with novel FloraSyntropy archive for large-scale plant disease diagnosis.","authors":"Saif Ur Rehman Khan, Muhammad Nabeel Asim, Sebastian Vollmer, Andreas Dengel","doi":"10.1186/s13007-026-01519-4","DOIUrl":"10.1186/s13007-026-01519-4","url":null,"abstract":"<p><p>Early diagnosis of plant diseases is critical for global food safety, yet most AI solutions lack the generalization required for real-world agricultural diversity. These models are typically constrained to specific species, failing to perform accurately across the broad spectrum of cultivated plants. To address this gap, we first introduce the FloraSyntropy Archive, a large-scale dataset of 178,922 images across 35 plant species, annotated with 97 distinct disease classes. We establish a benchmark by evaluating numerous existing models on this archive, revealing a significant performance gap. We then propose FloraSyntropy-Net, a novel federated learning framework (FL) that integrates a Memetic Algorithm (MAO) for optimal base model selection (DenseNet201), a novel Deep Block for enhanced feature representation, and a client-cloning strategy for scalable, privacy-preserving training. FloraSyntropy-Net achieves a state-of-the-art accuracy of 96.38% on the FloraSyntropy benchmark. Crucially, to validate its generalization capability, we test the model on the unrelated multiclass Pest dataset, where it demonstrates exceptional adaptability, achieving 99.84% accuracy. This work provides not only a valuable new resource but also a robust and highly generalizable framework that advances the field towards practical, large-scale agricultural AI applications.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13064331/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147475030","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":"Coleaf, an image recognition-driven approach facilitates the genome-wide association study with tea leaf morphology.","authors":"Mengwei Jiang, Shuai Chen, Weilong Kong, Yibin Wang, Shenyang Qu, Zhenyang Liao, Pedro García, Noor-Ul-Áin, Qian Zhao, Haibao Tang, Xingtan Zhang","doi":"10.1186/s13007-026-01518-5","DOIUrl":"10.1186/s13007-026-01518-5","url":null,"abstract":"<p><p>Leaf morphology in tea plants (Camellia sinensis L.) profoundly influences tea quality and agronomic value, yet its genetic basis remains elusive due to labor-intensive phenotyping, foliage architecture, and ecological sensitivity of traits. Moreover, traditional methods forfeit quantitative color gradients and population-level morphological complexity. To address this challenge, we developed coleaf, an open-source image recognition-based software that demonstrated 97.6% accuracy over conventional ImageJ measurements, while offering higher efficiency and color hues quantification. We then estimated 7 key morphological traits focusing on leaves from a collection of ~ 4,200 mature leaves and ~ 5,000 bud-leaf samples across 167 genetically diverse tea accessions by coleaf. While classical understanding suggests leaf shape differentiation between two varieties in genus sinensis assamica (CSA) and sinensis (CSS), our phenotypic clustering revealed incomplete congruence with phylogenetic relationships, suggesting the presence of additional genetic or environmental modulators beyond population divergence. Furthermore, we integrated phenotypic data with whole-genome resequencing for multi-model genome-wide association studies (GWAS). Candidate genes associated with leaf architecture were involved in plant development (e.g., CsFAS2), cell division and elongation (e.g., CsFIP1), and cellular morphogenesis (e.g., CsRLK), whereas those associated with leaf color, regulated pigment accumulation (e.g., ABC transporters, CsMYB113). In conclusion, this study establishes a standardized computational framework validating automated image recognition for plant leaf phenomics. The end-to-end framework from high-throughput phenotyping to gene discovery provides critical genetic targets for tea breeding, demonstrating transformative potential in accelerating the genetic improvement of tea plants.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13107895/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147469098","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":"Integrated single marker scanning and sparse Bayesian learning improves performance of detection for GWAS.","authors":"Jin Zhang, Zhenghan Wu, Mingzhi Cai, Ke Liu, Xiaoyu Han, Chang Liu, Gang Han, Yangjun Wen","doi":"10.1186/s13007-026-01516-7","DOIUrl":"10.1186/s13007-026-01516-7","url":null,"abstract":"<p><p>Single-locus and multi-locus models provide a statistical framework for conducting genome-wide association studies (GWAS). However, mainstream GWAS algorithms face challenges such as low detection power, high false positive rates, and slow computational efficiency as the dimensionality of genomic data continues to grow. We introduce KinLmSBL, a two-stage approach that integrates single-locus scanning with polygenic background control and multi-locus sparse Bayesian learning. We validate the approach through a series of simulations and demonstrate that KinLmSBL outperforms four other single- and multi-locus approaches in detecting low heritability variants, controlling the false positive rate, and increasing efficiency. We apply KinLmSBL to maize, rice, and human datasets, further investigating its performance in identifying more known genes with lower computational cost. Overall, KinLmSBL provides an efficient GWAS tool for mining genes in high-dimensional biological data.</p>","PeriodicalId":20100,"journal":{"name":"Plant Methods","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13093979/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147444603","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}