Motivation: Transposable elements (TEs) classification is an essential step to decode their roles in genome evolution. With a large number of genomes from non-model species becoming available, accurate and efficient TE classification has emerged as a new challenge in genomic sequence analysis. Results: We developed a novel tool, DeepTE, which classifies unknown TEs using convolutional neural networks (CNNs). DeepTE transferred sequences into input vectors based on k-mer counts. A tree structured classification process was used where eight models were trained to classify TEs into super families and orders. DeepTE also detected domains inside TEs to correct false classification. An additional model was trained to distinguish between non-TEs and TEs in plants. Given unclassified TEs of different species, DeepTE can classify TEs into seven orders, which include 15, 24 and 16 super families in plants, metazoans and fungi, respectively. In several benchmarking tests, DeepTE outperformed other existing tools for TE classification. In conclusion, DeepTE successfully leverages CNN for TE classification, and can be used to precisely classify TEs in newly sequenced eukaryotic genomes. Availability and implementation: DeepTE is accessible at https://github.com/LiLabAtVT/DeepTE. Supplementary information: Supplementary data are available at Bioinformatics online.

Recent advancements in hyperspectral imaging (HSI) for early disease detection have shown promising results, yet there is a lack of validated high-resolution (spatial and spectral) HSI data representing the responses of plants at different stages of leaf disease progression. To address these gaps, we used bacterial leaf spot (Xanthomonas perforans) of tomato as a model system. Hyperspectral images of tomato leaves, validated against in planta pathogen populations for seven consecutive days, were analyzed to reveal differences between infected and healthy leaves. Machine learning models were trained using leaf-level full spectra data, leaf-level Vegetation index (VI) data, and pixel-level full spectra data at four disease progression stages. The results suggest that HSI can detect disease on tomato leaves at pre-symptomatic stages and differentiate bacterial disease spots from abiotic leaf spots. Using VI data as features for machine learning improved overall classification performance by 26–37% compared to the direct use of raw data. Critical wavelength bands and VIs varied across disease progression stages, suggesting that pre-symptomatic disease detection relied more on changes in leaf water content (1400 nm) and plant defense hormone‐mediated responses (750 nm) rather than changes in leaf pigments or internal structure (800–900 nm), which may become more crucial during symptomatic stages. In conclusion, this study provides valuable insights into the dynamics of bacterial spot disease, revealing the potential benefits of leaf structure segmentation and VI group pattern analysis in HSI studies for the early detection of leaf diseases.

Recent advances in genomic technologies have generated data on large-scale protein–DNA interactions and open chromatin regions for many eukaryotic species. How to identify condition-specific functions of transcription factors using these data has become a major challenge in genomic research. To solve this problem, we have developed a method called ConSReg, which provides a novel approach to integrate regulatory genomic data into predictive machine learning models of key regulatory genes. Using Arabidopsis as a model system, we tested our approach to identify regulatory genes in data sets from single cell gene expression and from abiotic stress treatments. Our results showed that ConSReg accurately predicted transcription factors that regulate differentially expressed genes with an average auROC of 0.84, which is 23.5–25% better than enrichment-based approaches. To further validate the performance of ConSReg, we analyzed an independent data set related to plant nitrogen responses. ConSReg provided better rankings of the correct transcription factors in 61.7% of cases, which is three times better than other plant tools. We applied ConSReg to Arabidopsis single cell RNA-seq data, successfully identifying candidate regulatory genes that control cell wall formation. Our methods provide a new approach to define candidate regulatory genes using integrated genomic data in plants.

Hyperspectral sensors combined with machine learning are increasingly utilized in agricultural crop systems for diverse applications, including plant disease detection. This study was designed to identify the most important wavelengths to discriminate between healthy and diseased peanut (Arachis hypogaea L.) plants infected with Athelia rolfsii, the causal agent of peanut stem rot, using in-situ spectroscopy and machine learning. In greenhouse experiments, daily measurements were conducted to inspect disease symptoms visually and to collect spectral reflectance of peanut leaves on lateral stems of plants mock-inoculated and inoculated with A. rolfsii. Spectrum files were categorized into five classes based on foliar wilting symptoms. Five feature selection methods were compared to select the top 10 ranked wavelengths with and without a custom minimum distance of 20 nm. Recursive feature elimination methods outperformed the chi-square and SelectFromModel methods. Adding the minimum distance of 20 nm into the top selected wavelengths improved classification performance. Wavelengths of 501–505, 690–694, 763 and 884 nm were repeatedly selected by two or more feature selection methods. These selected wavelengths can be applied in designing optical sensors for automated stem rot detection in peanut fields. The machine-learning-based methodology can be adapted to identify spectral signatures of disease in other plant-pathogen systems.

Single-cell RNA sequencing (scRNA-seq) is widely used in plant biology and is a powerful tool for studying cell identity and differentiation. However, the scarcity of known cell-type marker genes and the divergence of marker expression patterns limit the accuracy of cell-type identification and our capacity to investigate cell-type conservation in many species. To tackle this challenge, we devise a novel computational strategy called Orthologous Marker Gene Groups (OMGs), which can identify cell types in both model and non-model plant species and allows for rapid comparison of cell types across many published single-cell maps. Our method does not require cross-species data integration, while still accurately determining inter-species cellular similarities. We validate the method by analyzing published single-cell data from species with well-annotated single-cell maps, and we show our methods can capture majority of manually annotated cell types. The robustness of our method is further demonstrated by its ability to pertinently map cell clusters from 1 million cells, 268 cell clusters across 15 diverse plant species. We reveal 14 dominant groups with substantial conservation in shared cell-type markers across monocots and dicots. To facilitate the use of this method by the broad research community, we launch a user-friendly web-based tool called the OMG browser, which simplifies the process of cell-type identification in plant datasets for biologists.

Pathogen detection, identification, and tracking is shifting from non-molecular methods, DNA fingerprinting methods, and single gene methods to methods relying on whole genomes. Viral Ebola and influenza genome data are being used for real-time tracking, while food-borne bacterial pathogen outbreaks and hospital outbreaks are investigated using whole genomes in the UK, Canada, the USA and the other countries. Also, plant pathogen genomes are starting to be used to investigate plant disease epidemics such as the wheat blast outbreak in Bangladesh. While these genome-based approaches provide never-seen advantages over all previous approaches with regard to public health and biosecurity, they also come with new vulnerabilities and risks with regard to cybersecurity. The more we rely on genome databases, the more likely these databases will become targets for cyber-attacks to interfere with public health and biosecurity systems by compromising their integrity, taking them hostage, or manipulating the data they contain. Also, while there is the potential to collect pathogen genomic data from infected individuals or agricultural and food products during disease outbreaks to improve disease modeling and forecast, how to protect the privacy of individuals, growers, and retailers is another major cyberbiosecurity challenge. As data become linkable to other data sources, individuals and groups become identifiable and potential malicious activities targeting those identified become feasible. Here, we define a number of potential cybersecurity weaknesses in today's pathogen genome databases to raise awareness, and we provide potential solutions to strengthen cyberbiosecurity during the development of the next generation of pathogen genome databases.