Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “genomic methods”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Spaceflight Autonomous Multigenerational Microbial Sequencer in Support of Plant-Growth Systems

The CubeSat platform has proven successful in obtaining meaningful life science information when biological payloads are incorporated. Examples include: 1) the first-ever CubeSat with a biological payload, GeneSat-1, which demonstrated decreased growth rates for flight samples of Escherichia coli in low Earth orbit (Parra et al. 2008); 2) PharmaSat, demonstrated that Saccharomyces cerevisiae in the microgravity environment exhibits a significant level of metabolic activity even at high doses of applied antifungal (Ricco et al. 2011); 3) O/OREOS, which used Bacillus subtilis(bacteria) to demonstrate for the first time that microorganisms can be loaded in a dried, dormant form and then rehydrated and grown in orbit months after launch (Nicholson et al. 2011; Ehrenfreund et al. 2014; 4) the SporeSat payload, which investigated Ceratopteris richardii(fern spores) using lab-on-a-chip devices (BioCDs) and minicentrifuges to produce artificial gravitational forces in ground studies (Park et al. 2017), with demonstration of the BioCD and minicentrifuge in space; 5) EcAMSat, the first CubeSat to be directly deployed from the ISS for an experiment assessing antibiotic resistance of E. coli in the microgravity environment (Padgen et al. 2020); 6) BioSentinel, exposed a culture of yeast to galactic cosmic radiation (GCR) and solar particle events while in heliocentric orbit to measure the rate of double-strand-break repair using DNA-repair-deficient mutants. This effort measures the metabolic parameters of yeast in a deep-space environment compared to Earth ambient conditions using a 3-color LED detection system (Ricco et al. 2020; Padgen et al. 2021). We aim to expand this list to include a Spaceflight Autonomous Multigenerational Microbial Sequencer (SAMMS). SAMMS will allow for the genome level understanding of changes in growth and metabolic activity for any organism. While microbes are suitable for early studies in our proposed platform because of their small size, small and relatively less-complicated genomes, fast generation times, and relevance to life support systems; multicellular organisms can similarly be evaluated for their genetic response to the spaceflight environment. The Spaceflight Autonomous Multigenerational Microbial Sequencer (SAMMS) will enable autonomous sequencing of biological samples in plant production units, cislunar orbit and on the lunar surface to examine spaceflight effects (ie. radiation, altered gravity, reduced pressures) on plant and microbial genomes.On this team a Kennedy Space Center (KSC) space crop production and water systems microbiologist/molecular biologist works with a Johnson Space Center (JSC) International Space Station (ISS) microbial sequencing expert and an Ames Research Center (ARC) CubeSat Engineering team to convert an automated Oxford Nanopore librarypreparation and sequencing method to a fluidic CubeSat payload system. The Oxford Nanopore MinION sequencing platform has proven successful in the spaceflight environment onboard the ISS (Stahl-Rommel et al. 2021). Further long-duration spaceflight and exposure to high levels of radiation will cause genotypic effects in biological organisms that may affect their function. Monitoring the adaption of a population to the spaceflight environment and any subsequent beneficial mutations will allow for the harnessing of organisms best suited for use in life support systems. This will ensure that the selected life support-essential microorganisms maintain their intended specified function over generations of culturing in the relevant spaceflight environment without becoming hazardous to crew or spacecraft systems.

Aubrie E Orourke↗
NASA NTRS2015

The Twins Study: NASA's First Foray into 21st Century Omics Research

The full array of 21st century omics-based research methods should be intelligently employed to reduce the health and performance risks that astronauts will be exposed to during exploration missions beyond low Earth Orbit. In March of 2015, US Astronaut Scott Kelly will launch to the International Space Station for a one year mission while his twin brother, Mark Kelly, a retired US Astronaut, remains on the ground. This situation presents an extremely rare flight opportunity to perform an integrated omics-based demonstration pilot study involving identical twin astronauts. A group of 10 principal investigators has been competitively selected, funded, and teamed together to form the Twins Study. A very broad range of biological function are being examined including the genome, epigenome, transcriptome, proteome, metabolome, gut microbiome, immunological response to vaccinations, indicators of atherosclerosis, physiological fluid shifts, and cognition. The plans for the Twins Study and an overview of initial results will be described as well as the technological and ethical issues raised for such spaceflight studies. An anticipated outcome of the Twins Study is that it will place NASA on a trajectory of using omics-based information to develop precision countermeasures for individual astronauts.

Kundrot, C. E.↗
NASA NTRS2006

Computer Modeling of Protocellular Functions: Peptide Insertion in Membranes

Lipid vesicles became the precursors to protocells by acquiring the capabilities needed to survive and reproduce. These include transport of ions, nutrients and waste products across cell walls and capture of energy and its conversion into a chemically usable form. In modem organisms these functions are carried out by membrane-bound proteins (about 30% of the genome codes for this kind of proteins). A number of properties of alpha-helical peptides suggest that their associations are excellent candidates for protobiological precursors of proteins. In particular, some simple a-helical peptides can aggregate spontaneously and form functional channels. This process can be described conceptually by a three-step thermodynamic cycle: 1 - folding of helices at the water-membrane interface, 2 - helix insertion into the lipid bilayer and 3 - specific interactions of these helices that result in functional tertiary structures. Although a crucial step, helix insertion has not been adequately studied because of the insolubility and aggregation of hydrophobic peptides. In this work, we use computer simulation methods (Molecular Dynamics) to characterize the energetics of helix insertion and we discuss its importance in an evolutionary context. Specifically, helices could self-assemble only if their interactions were sufficiently strong to compensate the unfavorable Free Energy of insertion of individual helices into membranes, providing a selection mechanism for protobiological evolution.

Rodriquez-Gomez, D.↗
DOE OSTI2021

Cytogenetic follow-up studies on humans with internal and external exposure to ionizing radiation

Cells exposed to ionizing radiation have a wide spectrum of DNA lesions that include DNA single-strand breaks, DNA double-strand breaks (DSBs), oxidative base damage and DNA-protein crosslinks. Among them, DSB is the most critical lesion, which when mis-repaired leads to unstable and stable chromosome aberrations. Currently, chromosome aberration analysis is the preferred method for biological monitoring of radiation-exposed humans. Here, stable chromosome aberrations, such as inversions and balanced translocations, persist in the peripheral blood lymphocytes of radiation-exposed humans for several years and, therefore, are potentially useful tools to prognosticate the health risks of radiation exposure, particularly in the hematopoietic system. In this review, we summarize the cytogenetic follow-up studies performed by REAC/TS (Radiation Emergency Assistance Center/Training site, Oak Ridge, USA) on humans exposed to internal and external radiation. In the light of our observations as well as the data existing in the literature, this review attempts to highlight the importance of follow-up studies for predicting the extent of genomic instability and its impact on delayed health risks in radiation-exposed victims.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2024

Improved detection of low-frequency within-host variants from deep sequencing: A case study with human papillomavirus

Abstract High-coverage sequencing allows the study of variants occurring at low frequencies within samples, but is susceptible to false-positives caused by sequencing error. Ion Torrent has a very low single nucleotide variant (SNV) error rate and has been employed for the majority of human papillomavirus (HPV) whole genome sequences. However, benchmarking of intrahost SNVs (iSNVs) has been challenging, partly due to limitations imposed by the HPV life cycle. We address this problem by deep sequencing three replicates for each of 31 samples of HPV type 18 (HPV18). Errors, defined as iSNVs observed in only one of three replicates, are dominated by C→T (G→A) changes, independently of trinucleotide context. True iSNVs, defined as those observed in all three replicates, instead show a more diverse SNV type distribution, with particularly elevated C→T rates in CCG context (CCG→CTG; CGG→CAG) and C→A rates in ACG context (ACG→AAG; CGT→CTT). Characterization of true iSNVs allowed us to develop two methods for detecting true variants: (1) VCFgenie, a dynamic binomial filtering tool which uses each variant’s allele count and coverage instead of fixed frequency cut-offs; and (2) a machine learning binary classifier which trains eXtreme Gradient Boosting models on variant features such as quality and trinucleotide context. Each approach outperforms fixed-cut-off filtering of iSNVs, and performance is enhanced when both are used together. Our results provide improved methods for identifying true iSNVs in within-host applications across sequencing platforms, specifically using HPV18 as a case study.

Virology↗
DOE OSTI2025

Genetic Identification of Lamprey Genera and Anadromous Ecotypes in Watersheds of the Northeastern Pacific Ocean

ABSTRACT Nonparasitic, nonmigratory Western Brook Lamprey (WBL; Lampetra ayresii ), and parasitic, anadromous Western River Lamprey (WRL; L. ayresii ) are sympatric lampreys that likely represent different life history variations of a single species. Novel genetic tools are critical for differentiating WBL and WRL, whose larvae preclude morphological identification (ID) and will enable comprehensive assessment of imperiled native lampreys of the Northeastern Pacific (including WBL, WRL, and Pacific Lamprey, Entosphenus tridentatus ). We developed 47 candidate single nucleotide polymorphism (SNP) markers using whole genome resequencing of WBL ( N = 24) and WRL ( N = 15) from Ksi Ts'oohl Ts'ap Creek (Nass River, British Columbia, Canada) which are likely ecotypes distinguished by few divergent SNPs across multiple chromosomes. We used five novel candidate SNPs to perform genetic ID of WBL and WRL ecotypes in collections of mixed native lampreys from lower Columbia River tributaries ( N = 1474), Ksi Ts'oohl Ts'ap Creek ( N = 352), and ocean phase WRL from the Georgia Basin (Salish Sea, British Columbia, Canada; N = 91). Two previously published SNPs were used to ID genera, Entosphenus versus Lampetra . Morphological ID utilized photographs collected from a subset of genotyped lampreys, and high concordance was demonstrated between ID methods for genera (99%) and Lampetra ecotypes (> 98%). We characterized spatial and temporal composition of lamprey genera and ecotypes surveyed across NE Pacific tributaries under the expectation these compositions would be similar across nearby sites and across years at the same site. Proportions of lamprey genera were highly variable within regions and across years; however, Lampetra ecotypic proportions were spatially and temporally stable. WRL were rare in lower Columbia tributaries (~1% average rate among Lampetra ) and common further north (> 40% of Lampetra ). Genetic ID methods are powerful monitoring tools that create the novel ability to ascertain genera and ecotypes regardless of life stage, while increasing the efficiency of surveys by eliminating time‐intensive morphological data collection.

Silver, G. S. [Columbia River Inter‐Tribal Fish Co↗
DOE OSTI2024

Intraspecific variability in plant and soil chemical properties in a common garden plantation of the energy crop Populus

Optimizing crops for synergistic soil carbon (C) sequestration can enhance CO 2 removal in food and bioenergy production systems. Yet, in bioenergy systems, we lack an understanding of how intraspecies variation in plant traits correlates with variation in soil biogeochemistry. This knowledge gap is exacerbated by both the heterogeneity and difficulty of measuring belowground traits. Here, we provide initial observations of C and nutrients in soil and root and stem tissues from a common garden field site of diverse, natural variant, Populus trichocarpa genotypes—established for aboveground biomass-to-biofuels research. Our goal was to explore the value of such field sites for evaluating genotype-specific effects on soil C, which ultimately informs the potential for optimizing bioenergy systems for both aboveground productivity and belowground C storage. To do this, we investigated variation in chemical traits at the scale of individual trees and genotypes and we explored correlations among stem, root, and soil samples. We observed substantial variation in soil chemical properties at the scale of individual trees and specific genotypes. While correlations among elements were observed both within and among sample types (soil, stem, root), above-belowground correlations were generally poor. We did not observe genotype-specific patterns in soil C in the top 10 cm, but we did observe genotype associations with soil acid-base chemistry (soil pH and base cations) and bulk density. Finally, a specific phenotype of interest (high vs low lignin) was unrelated to soil biogeochemistry. Our pilot study supports the usefulness of decade-old, genetically-variable, Populus bioenergy field test plots for understanding plant genotype effects on soil properties. Finally, this study contributes to the advancement of sampling methods and baseline data for Populus systems in the Pacific Northwest, USA. Further species- and region-specific efforts will enhance C predictability across scales in bioenergy systems and, ultimately, accelerate the identification of genotypes that optimize yield and carbon storage.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design

The Joint Automated Repository for Various Integrated Simulations (JARVIS) is an integrated infrastructure to accelerate materials discovery and design using density functional theory (DFT), classical force-fields (FF), and machine learning (ML) techniques. JARVIS is motivated by the Materials Genome Initiative (MGI) principles of developing open-access databases and tools to reduce the cost and development time of materials discovery, optimization, and deployment. The major features of JARVIS are: JARVIS-DFT, JARVIS-FF, JARVIS-ML, and JARVIS-tools. To date, JARVIS consists of ≈40,000 materials and ≈1 million calculated properties in JARVIS-DFT, ≈500 materials and ≈110 force-fields in JARVIS-FF, and ≈25 ML models for material-property predictions in JARVIS-ML, all of which are continuously expanding. JARVIS-tools provides scripts and workflows for running and analyzing various simulations. We compare our computational data to experiments or high-fidelity computational methods wherever applicable to evaluate error/uncertainty in predictions. In addition to the existing workflows, the infrastructure can support a wide variety of other technologically important applications as part of the data-driven materials design paradigm. The JARVIS datasets and tools are publicly available at the website: https://jarvis.nist.gov .

36 MATERIALS SCIENCE↗
DOE OSTI2022

Deep Learning‐Assisted Automated Single Cell Electroporation Platform for Effective Genetic Manipulation of Hard‐to‐Transfect Cells

Abstract Genome engineering of cells using CRISPR/Cas systems has opened new avenues for pharmacological screening and investigating the molecular mechanisms of disease. A critical step in many such studies is the intracellular delivery of the gene editing machinery and the subsequent manipulation of cells. However, these workflows often involve processes such as bulk electroporation for intracellular delivery and fluorescence activated cell sorting for cell isolation that can be harsh to sensitive cell types such as human‐induced pluripotent stem cells (hiPSCs). This often leads to poor viability and low overall efficacy, requiring the use of large starting samples. In this work, a fully automated version of the nanofountain probe electroporation (NFP‐E) system, a nanopipette‐based single‐cell electroporation method is presented that provides superior cell viability and efficiency compared to traditional methods. The automated system utilizes a deep convolutional network to identify cell locations and a cell‐nanopipette contact algorithm to position the nanopipette over each cell for the application of electroporation pulses. The automated NFP‐E is combined with microconfinement arrays for cell isolation to demonstrate a workflow that can be used for CRISPR/Cas9 gene editing and cell tracking with potential applications in screening studies and isogenic cell line generation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

PathTracer Comprehensively Identifies Hypoxia-Induced Dormancy Adaptations in Mycobacterium tuberculosis

Mining large-scale data to discover biologically relevant information remains a challenge despite the rapid development of bioinformatics tools. Here, we have developed a new tool, PathTracer, to identify biologically relevant information flows by mining genome-wide protein–protein interaction networks following integration of gene expression data. PathTracer successfully mines interactions between genes and traces the most perturbed paths of perceived activities under the conditions of the study. Here, we further demonstrated the utility of this tool by identifying adaptation mechanisms of hypoxia-induced dormancy in Mycobacterium tuberculosis (Mtb).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

HtPIP: High-throughput phage isolation platform increases diversity and reduces isolation time using multiple bacteria

Bacteriophages are ubiquitous in nature, but relatively few have been isolated and characterized compared to the number of bacterial strains. Phage biotechnology applications benefit from a diverse library of isolated phages to kill or transfer genetic material to a bacterium of interest. However, scaling up phage discovery for diverse bacterial hosts can be time-consuming and costly. Here, we developed an approach to capture novel phages for multiple bacterial strains in parallel from an environmental sample using commercially available 0.2-μM filter plates. Using this High-throughput Phage Isolation Platform (HtPIP), 12 novel phages were isolated spanning 9 diverse bacterial host genera. Eleven of the isolated phages define new phage species, with nine also defining new genera. The HtPIP was used to discover both DNA and RNA phages, including a Tectiviridae infecting Pseudomonas putida mt-2 and a Leviviricetes infecting a Microbacterium isolate, which represents the first cultured RNA phage infecting a host outside of Proteobacteria. Using a metagenomic approach, we demonstrate that the HtPIP captures a higher proportion of novel phages compared to traditional low-throughput methods.

High-throughput↗
DOE OSTI2022

Data for Efficient Delivery of a DNA Aptamer-Based Biosensor into Plant Cells for Glucose Sensing through Thiol-Mediated Uptake

DNA aptamers have been widely used as biosensors for detecting a variety of targets. Despite decades of success, they have not been applied to monitor any targets in plants, even though plants are a major platform for providing oxygen, food, and sustainable products ranging from energy fuels to chemicals, and high-value products such as pharmaceuticals. A major barrier to progress is a lack of efficient methods to deliver DNA into plant cells. We herein report a thiol-mediated uptake method that more efficiently delivers DNA into Arabidopsis and tobacco leaf cells than another state-of-the-art method, DNA nanostructures. Such a method allowed efficient delivery of a glucose DNA aptamer sensor into Arabidopsis for sensing glucose. This demonstration opens a new avenue to apply DNA aptamer sensors for functional studies of various targets, including metabolites, plant hormones, metal ions, and proteins in plants for a better understanding of the biodistribution and regulation of these species and their functions.

Conversion↗
DOE OSTI2020

Multitask Recommender Systems for Cancer Drug Response

The problem we are currently trying to address is that there are many types of cancer drugs and many types of cancers and there is not always experimental data for a specific cancer type and cancer drug interaction. While there is a large possible set of feasible drug and cancer combinations, testing each pair is not realistic due to the high monetary cost of cell-based assays. Thus, this leaves researchers with a difficult choice of what drugs they should test on specific cancer types. This issue is known as the cold-start problem. Our focus is on developing recommender systems capable of addressing the cold-start problem as it relates to interaction between cancer types and cancer drugs. One of the most effective ways to address the cold-start problem is through large data analysis, however due to the cost prohibitive nature of cancer research the largest available data set size is the Genomics of Drug Sensitivity in Cancer with 494,973 genomic associations. To achieve optimal model performance on the cold-start problem, it is advantageous to employ multitask algorithms that are capable of transferring information between cancer datasets. The aim of this report is to draw from adaptations and state of the art developments in both algorithms for recommender systems and multitask learning to model the interaction between cancer cell lines and cancer drugs. Cancer cell lines are defined by the US National Cancer Institute as "cancer cells that keep dividing and growing over time, under certain conditions in a laboratory". This paper will focus on evaluating the performance of Neural Collaborative Filtering and Gaussian Processes, as well as their multitask adaptations, on cancer datasets from CCLE, NCI60, GDSC and CTRP. These methods will be evaluated on model performance in regression prediction but also in interpretability.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Subsampling and DNA pooling can increase gains through genomic selection in switchgrass

Genomic selection (GS) can accelerate breeding cycles in perennial crops such as the bioenergy grass switchgrass (Panicum virgatum L.). The sequencing costs of GS can be reduced by pooling DNA samples in the training population (TP), only sequencing TP phenotypic outliers, or pooling candidate population (CP) samples. These strategies were simulated for two traits (spring vigor and anthesis date) in three breeding populations. Sequencing only the outlier 50% of the TP phenotype distribution resulted in a penalty of <5% of the predictive ability, measured using cross-validation. Predictive ability also decreased when sequencing progressively fewer TP DNA pools, but TPs constructed from only two phenotypically contrasting DNA samples retained a mean of >80% predictive ability relative to individual TP sequencing. Novel group testing methods allowed greater than one CP individual to be screened per sequenced DNA sample but resulted in a predictive ability penalty. To determine the impact of reduced sequencing, genetic gain was calculated for seven GS scenarios with variable sequencing budgets. Reduced TP sequencing and most CP pooling methods were superior to individual sequence-based GS when sequencing resources were restricted (2,000 DNA samples per 5-yr cycle). Only one scenario was superior to individual sequencing when sequencing budgets were large (8,000 DNA samples per 5-yr cycle). This study highlights multiple routes for reduced sequencing costs in GS.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

A metabolic modeling platform for the computation of microbial ecosystems in time and space (COMETS)

Genome-scale stoichiometric modeling of metabolism has become a standard systems biology tool for modeling cellular physiology and growth. Extensions of this approach are emerging as a valuable avenue for predicting, understanding and designing microbial communities. Computation of microbial ecosystems in time and space (COMETS) extends dynamic flux balance analysis to generate simulations of multiple microbial species in molecularly complex and spatially structured environments. Here we describe how to best use and apply the most recent version of COMETS, which incorporates a more accurate biophysical model of microbial biomass expansion upon growth, evolutionary dynamics and extracellular enzyme activity modules. In addition to a command-line option, COMETS includes user-friendly Python and MATLAB interfaces compatible with the well-established COBRA models and methods, as well as comprehensive documentation and tutorials. Overall, this protocol provides a detailed guideline for installing, testing and applying COMETS to different scenarios, generating simulations that take from a few minutes to several days to run, with broad applicability to microbial communities across biomes and scales.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Tag you're it: Application of stable isotope labeling and LC-MS to identify the precursors of specialized metabolites in plants

Untargeted liquid chromatography/mass spectrometry (LC-MS) can contribute a comprehensive and unbiased picture of the metabolic space of plants. These data can be used to quantify natural metabolite variation for genome wide association studies, to compare global metabolic responses from environmental or genetic perturbations, and to identify previously undescribed metabolites in Nature. A major limitation with untargeted metabolomics is the classification and identification of the thousands of metabolite features that can be detected in a single analytical run. Isotopic labeling improves the informational value of these datasets by categorizing metabolites as being derived from specific upstream precursors and/or to known metabolic pathways. When a 13 C-labeled precursor is fed to either a plant or tissue, the downstream metabolites produced from it have a higher m/z value than the molecules in the pre-existing pool, generating an m/z peak pair that can be specifically identified within the MS data. In this paper, we outline methods and principles to consider when supplementing untargeted MS data with isotopic labeling, including how to choose the appropriate isotopic label, grow and feed plant tissues to maximize label uptake and incorporation into derivatives, optimize LC-MS methods, and interpret the resulting labeling data. Although the focus here is on annotation of amino acid-derived metabolites using LC-MS, we anticipate that the methods are generally adaptable to other precursors, plant species, and chromatographic approaches.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Quantum-parallel vectorized data encodings and computations on trapped-ion and transmon QPUs

Compact data representations in quantum systems are crucial for the development of quantum algorithms for data analysis. In this study, we present two innovative data encoding techniques, known as QCrank and QBArt, which exhibit significant quantum parallelism via uniformly controlled rotation gates. The QCrank method encodes a series of real-valued data as rotations on data qubits, resulting in increased storage capacity. On the other hand, QBArt directly incorporates a binary representation of the data within the computational basis, requiring fewer quantum measurements and enabling well-established arithmetic operations on binary data. We showcase various applications of the proposed encoding methods for various data types. Notably, we demonstrate quantum algorithms for tasks such as DNA pattern matching, Hamming weight computation, complex value conjugation, and the retrieval of a binary image with 384 pixels, all executed on the Quantinuum trapped-ion QPU. Furthermore, we employ several cloud-accessible QPUs, including those from IBMQ and IonQ, to conduct supplementary benchmarking experiments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

scPlantAnnotate: an accurate and robust transformer-based model for plant cell type annotation

Accurate cell type annotation remains a major bottleneck in plant single-cell RNA sequencing (scRNA-seq), where existing tools are often adapted from animal studies and perform sub-optimally on plant data. The lack of plant-specific computational frameworks limits the construction of plant cell atlases and downstream biological discovery. We develop and evaluate scPlantAnnotate, a Transformer-based reference annotation framework tailored for plant scRNA-seq data, and benchmark it against state-of-the-art deep learning and conventional methods across multiple plant species. Species-specific scPlantAnnotate models were trained using curated datasets from Arabidopsis thaliana, Zea mays, Oryza sativa, and Glycine max. We compared scPlantAnnotate with leading baselines under both standard random-split evaluation and a more stringent leave-one-dataset-out setting, which tests robustness to completely unseen datasets and tissue types. scPlantAnnotate consistently outperforms existing approaches across all four species under random-split evaluation. In the leave-one-dataset-out setting for A. thaliana, where performance drops markedly for all methods due to strong batch effects and dataset heterogeneity, scPlantAnnotate nonetheless achieves the highest Accuracy, Macro-F1, Balanced Accuracy, and Macro-AUROC on average and ranks first on most held-out datasets. These results demonstrate improved robustness to dataset shifts, a critical yet underexplored challenge in plant scRNA-seq analysis. A freely accessible web server enables users to annotate their own datasets using pretrained models. scPlantAnnotate provides a plant-specific, Transformer-based framework for single-cell annotation that delivers state-of-the-art performance and enhanced robustness to unseen datasets. By addressing limitations of existing tools and enabling scalable reference-based annotation, scPlantAnnotate supports the development of comprehensive plant cell atlases and facilitates broader use of single-cell genomics in plant biology.

Bioinformatics↗