Pollen analysis using multispectral imaging flow cytometry and deep learning

A user-friendly method to get automated pollen analysis from environmental samples

Automated pollen analysis is not yet efficient on environmental samples containing many pollen taxa and debris, which are typical in most pollen-based studies. Contrary to classification, detection remains overlooked although it is the first step from which errors can propagate. Here, we investigated a simple but efficient method to automate pollen detection for environmental samples, optimizing workload and performance. We applied the YOLOv5 algorithm on samples containing debris and c. 40 Mediterranean plant taxa, designed and tested several strategies for annotation, and analyzed variation in detection errors. About 5% of pollen grains were left undetected, while 5% of debris were falsely detected as pollen. Undetected pollen was mainly in poor-quality images, or of rare and irregular morphology. Pollen detection remained effective when applied to samples never seen by the algorithm, and was not improved by spending time to provide taxonomic details. Pollen detection of a single model taxon reduced annotation workload, but was only efficient for morphologically differentiated taxa. We offer guidelines to plant scientists to analyze automatically any pollen sample, providing sound criteria to apply for detection while using common and user-friendly tools. Our method contributes to enhance the efficiency and replicability of pollen-based studies.

Unveiling the epigenetic landscape of plants using flow cytometry approach

Plants are sessile creatures that have to adapt constantly changing environmental circumstances. Plants are subjected to a range of abiotic stressors as a result of unpredictable climate change. Understanding how stress-responsive genes are regulated can help us better understand how plants can adapt to changing environmental conditions. Epigenetic markers that dynamically change in response to stimuli, such as DNA methylation and histone modifications are known to regulate gene expression. Individual cells or particles' physical and/or chemical properties can be measured using the method known as flow cytometry. It may therefore be used to evaluate changes in DNA methylation, histone modifications, and other epigenetic markers, making it a potent tool for researching epigenetics in plants. We explore the use of flow cytometry as a technique for examining epigenetic traits in this thorough discussion. The separation of cell nuclei and their subsequent labeling with fluorescent antibodies, offering information on the epigenetic mechanisms in plants when utilizing flow cytometry. We also go through the use of high-throughput data analysis methods to unravel the complex epigenetic processes occurring inside plant systems.

Single Infrared Spectrum Enables Simultaneous Identification of (Bio)Chemical Nature and Particle Size of Microorganisms and Synthetic Microplastic Beads

Populations of nearly identical chemical and biological microparticles include the synthetic microbeads used in cosmetic, biomedical, agri-food, and pharmaceutical industries as well as the class of living microorganisms such as yeast, pollen, and biological cells. Herein, we identify simultaneously the size and chemical nature of spherical microparticle populations with diameters larger than 1 μm. Our analysis relies on the extraction of both physical and chemical signatures from the same optical spectrum recorded using attenuated total reflection (ATR)-Fourier transform infrared (FTIR) spectroscopy. These signatures are the spectral resonances caused by the microparticles, which depend on their size and the absorption peaks revealing their chemical nature. We validate the method first on separated and mixed groups of spherical microplastic particles of two different diameters, where the method is used to calculate the diameter of the microspherical particles. Then, we apply the method to correctly identify and measure the diameter of Saccharomyces cerevisiae yeast cells. Theoretical simulations to help in understanding the effect of size distribution and dispersion support our results.

Deep learning-based high-throughput detection of in vitro germination to assess pollen viability from microscopic images

In vitro pollen germination is considered the most efficient method to assess pollen viability. The pollen germination frequency and pollen tube length, which are key indicators of pollen viability, should be accurately measured during in vitro culture. In this study, a Mask R-CNN model trained using microscopic images of tree peony (Paeonia suffruticosa) pollen has been proposed to rapidly detect the pollen germination rate and pollen tube length. To reduce the workload during image acquisition, images of synthesized crossed pollen tubes were added to the training dataset, significantly improving the model accuracy in recognizing crossed pollen tubes. At an Intersection over Union threshold of 50%, a mean average precision of 0.949 was achieved. The performance of the model was verified using 120 testing images. The R2 value of the linear regression model using detected pollen germination frequency against the ground truth was 0.909 and that using average pollen tube length was 0.958. Further, the model was successfully applied to two other plant species, indicating a good generalizability and potential to be applied widely.

Deductive automated pollen classification in environmental samples via exploratory deep learning and imaging flow cytometry

Pollen and tracheophyte spores are ubiquitous environmental indicators at local and global scales. Palynology is typically performed manually by microscopic analysis; a specialised and time-consuming task limited in taxonomical precision and sampling frequency, therefore restricting data quality used to inform climate change and pollen forecasting models. We build on the growing work using AI (artificial intelligence) for automated pollen classification to design a flexible network that can deal with the uncertainty of broad-scale environmental applications. We combined imaging flow cytometry with Guided Deep Learning to identify and accurately categorise pollen in environmental samples; here, pollen grains captured within c. 5500 Cal yr BP old lake sediments. Our network discriminates not only pollen included in training libraries to the species level but, depending on the sample, can classify previously unseen pollen to the likely phylogenetic order, family and even genus. Our approach offers valuable insights into the development of a widely transferable, rapid and accurate exploratory tool for pollen classification in 'real-world' environmental samples with improved accuracy over pure deep learning techniques. This work has the potential to revolutionise many aspects of palynology, allowing a more detailed spatial and temporal understanding of pollen in the environment with improved taxonomical resolution.

Is AI essential? Examining the need for deep learning in image-activated sorting of Saccharomyces cerevisiae

Artificial intelligence (AI) has become a focal point across a multitude of societal sectors, with science not being an exception. Particularly in the life sciences, imaging flow cytometry has increasingly integrated AI for automated management and categorization of extensive cell image data. However, the necessity of AI over traditional classification methods when extending imaging flow cytometry to include cell sorting remains uncertain, primarily due to the time constraints between image acquisition and sorting actuation. AI-enabled image-activated cell sorting (IACS) methods remain substantially limited, even as recent advancements in IACS have found success while largely relying on traditional feature gating strategies. Here we assess the necessity of AI for image classification in IACS by contrasting the performance of feature gating, classical machine learning (ML), and deep learning (DL) with convolutional neural networks (CNNs) in the differentiation of Saccharomyces cerevisiae mutant images. We show that classical ML could only yield a 2.8-fold enhancement in target enrichment capability, albeit at the cost of a 13.7-fold increase in processing time. Conversely, a CNN could offer an 11.0-fold improvement in enrichment capability at an 11.5-fold increase in processing time. We further executed IACS on mixed mutant populations and quantified target strain enrichment via downstream DNA sequencing to substantiate the applicability of DL for the proposed study. Our findings validate the feasibility and value of employing DL in IACS for morphology-based genetic screening of S. cerevisiae, encouraging its incorporation in future advancements of similar technologies.

Imaging flow cytometry: a primer

Imaging flow cytometry combines the high throughput nature of flow cytometry with the advantages of single cell image acquisition associated with microscopy. The measurement of large numbers of features from the resulting images provides rich datasets which have resulted in a wide range of novel biomedical applications. In this primer we discuss the typical imaging flow instrumentation, the form of data acquired and the typical analysis tools that can be applied to this data. Using examples from the literature we discuss the progression of the analysis methods that have been applied to imaging flow cytometry data. These methods start from the use of simple single image features and multiple channel gating strategies, followed by the design and use of custom features for phenotype classification, through to powerful machine and deep learning methods. For each of these methods, we outline the processes involved in analyzing typical datasets and provide details of example applications. Finally we discuss the current limitations of imaging flow cytometry and the innovations which are addressing these challenges.

Dimensionality reduction by UMAP for visualizing and aiding in classification of imaging flow cytometry data

Recent advances in imaging flow cytometry (IFC) have revolutionized high-throughput multiparameter analyses at single-cell resolution. Although enabling the discovery of population heterogeneities and the detection of rare events, IFC generates hyperdimensional datasets that demand innovative analytical approaches. Current methods work in a supervised manner, utilize only limited information content, or require large annotated reference datasets. Dimensionality reduction algorithms, including uniform manifold approximation and projection (UMAP), have been successfully applied to analyze the large number of parameters generated in various high-throughput techniques.

Here, we apply a workflow incorporating UMAP to analyze different IFC datasets. We demonstrate that it out-competes other popular dimensionality reduction methods in speed and accuracy. Moreover, it enables fast visualization, clustering, and tagging of unannotated objects in large-scale experiments. We anticipate that our workflow will be a robust method to address complex IFC datasets, either alone or as an upstream addition to the deep learning approaches.

•

UMAP dimensionality reduction provides fast and accurate method of IFC data analysis

•

UMAP yields improved object clustering and tagging of the multispectral IFC data

•

PCA decomposition allows multispectral signals merging for direct image embedding

Assessing the lysis of diverse pollen from bulk environmental samples for DNA metabarcoding

Pollen is ubiquitous year-round in bulk environmental samples and can provide useful information on previous and current plant communities. Characterization of pollen has traditionally been completed based on morphology, requiring significant time and expertise. DNA metabarcoding is a promising approach for characterizing pollen from bulk environmental samples, but accuracy hinges on successful lysis of pollen grains to free template DNA. In this study, we assessed the lysis of morphologically and taxonomically diverse pollen from one of the most common bulk environmental sample types for DNA metabarcoding, surface soil. To achieve this, a four species artificial pollen mixture was spiked into surface soils collected from Colorado, North Carolina, and Pennsylvania, and subsequently subjected to DNA extraction using both the PowerSoil and PowerSoil Pro Kits (Qiagen) with a heated incubation (either 65 °C or 90 °C). Amplification and Illumina sequencing of the internal transcribed spacer subunit 2 (ITS2) was completed in duplicate for each sample (total n, 76), and the resulting sequencing reads taxonomically identified using GenBank. The PowerSoil Pro Kit statistically outperformed the PowerSoil Kit for total DNA yield. When using either kit, incubation temperature (65 °C or 90 °C) used had no impact on the recovery of DNA, plant amplicon sequence variants (ASVs), or total plant ITS2 reads. This study highlighted that lysis of pollen in bulk environmental samples is feasible using commercially available kits, and downstream DNA metabarcoding can be used to accurately characterize pollen DNA from such sample types.

Imaging Flow Cytometry as a Quick and Effective Identification Technique of Pollen Grains from Betulaceae, Oleaceae, Urticaceae and Asteraceae

Despite the continuous and intensive development of laboratory techniques, a light microscope is still the most common tool used in pollen grains differentiation. However, microscopy is time-consuming and needs well-educated and experienced researchers. Other currently used techniques can be categorised as images and non-images analysis, but each has certain limitations. We propose a new approach to differentiate pollen grains using the Imaging Flow Cytometry (IFC) technique. It allows for high-throughput fluorescence data recording, which, in contrast to the standard FC, also enables real-time control of the results thanks to the possibility of digital image recording of cells flowing through the measuring capillary. The developed method allows us to determine the characteristics of the pollen grains population based on the obtained fluorescence data, using various combinations of parameters available in the IDEAS software, which can be analysed on different fluorescence channels. On this basis, we distinguished pollen grains both between and within different genera belonging to the Betulaceae, Oleaceae, Urticaceae and Asteraceae families. Thereby, we prove that the proposed methodology is sufficient for accurate, fast, and cost-effective identification and potentially can be used in the routine analysis of allergenic pollen grains.

DNA metabarcoding using nrITS2 provides highly qualitative and quantitative results for airborne pollen monitoring

Airborne pollen monitoring is of global socio-economic importance as it provides information on presence and prevalence of allergenic pollen in ambient air. Traditionally, this task has been performed by microscopic investigation, but novel techniques are being developed to automate this process. Among these, DNA metabarcoding has the highest potential of increasing the taxonomic resolution, but uncertainty exists about whether the results can be used to quantify pollen abundance. In this study, it is shown that DNA metabarcoding using trnL and nrITS2 provides highly improved taxonomic resolution for pollen from aerobiological samples from the Netherlands. A total of 168 species from 143 genera and 56 plant families were detected, while using a microscope only 23 genera and 22 plant families were identified. NrITS2 produced almost double the number of OTUs and a much higher percentage of identifications to species level (80.1%) than trnL (27.6%). Furthermore, regressing relative read abundances against the relative abundances of microscopically obtained pollen concentrations showed a better correlation for nrITS2 (R2 = 0.821) than for trnL (R2 = 0.620). Using three target taxa commonly encountered in early spring and fall in the Netherlands (Alnus sp., Cupressaceae/Taxaceae and Urticaceae) the nrITS2 results showed that all three taxa were dominated by one or two species (Alnus glutinosa/incana, Taxus baccata and Urtica dioica). Highly allergenic as well as artificial hybrid species were found using nrITS2 that could not be identified using trnL or microscopic investigation (Alnus × spaethii, Cupressus arizonica, Parietaria spp.). Furthermore, perMANOVA analysis indicated spatiotemporal patterns in airborne pollen trends that could be more clearly distinguished for all taxa using nrITS2 rather than trnL. All results indicate that nrITS2 should be the preferred marker of choice for molecular airborne pollen monitoring.

Imaging flow cytometry data analysis using convolutional neural network for quantitative investigation of phagocytosis

Macrophages play an important role in the adaptive immune system. Their ability to neutralize cellular targets through Fc receptor-mediated phagocytosis has relied upon immunotherapy that has become of particular interest for the treatment of cancer and autoimmune diseases. A detailed investigation of phagocytosis is the key to the improvement of the therapeutic efficiency of existing medications and the creation of new ones. A promising method for studying the process is imaging flow cytometry (IFC) that acquires thousands of cell images per second in up to 12 optical channels and allows multiparametric fluorescent and morphological analysis of samples in the flow. However, conventional IFC data analysis approaches are based on a highly subjective manual choice of masks and other processing parameters that can lead to the loss of valuable information embedded in the original image. Here, we show the application of a Faster region-based convolutional neural network (CNN) for accurate quantitative analysis of phagocytosis using imaging flow cytometry data. Phagocytosis of erythrocytes by peritoneal macrophages was chosen as a model system. CNN performed automatic high-throughput processing of datasets and demonstrated impressive results in the identification and classification of macrophages and erythrocytes, despite the variety of shapes, sizes, intensities, and textures of cells in images. The developed procedure allows determining the number of phagocytosed cells, disregarding cases with a low probability of correct classification. We believe that CNN-based approaches will enable powerful in-depth investigation of a wide range of biological processes and will reveal the intricate nature of heterogeneous objects in images, leading to completely new capabilities in diagnostics and therapy.

Preservation methods of honey bee-collected pollen are not a source of bias in ITS2 metabarcoding

Pollen metabarcoding is emerging as a powerful tool for ecological research and offers unprecedented scale in citizen science projects for environmental monitoring via honey bees. Biases in metabarcoding can be introduced at any stage of sample processing and preservation is at the forefront of the pipeline. While in metabarcoding studies pollen has been preserved at - 20 °C (FRZ), this is not the best method for citizen scientists. Herein, we compared this method with ethanol (EtOH), silica gel (SG) and room temperature (RT) for preservation of pollen collected from hives in Austria and Denmark. After ~ 4 months of storage, DNAs were extracted with a food kit, and their quality and concentration measured. Most DNA extracts exhibited 260/280 absorbance ratios close to the optimal 1.8, with RT samples from Austria performing slightly worse than FRZ and SG samples (P < 0.027). Statistical differences were also detected for DNA concentration, with EtOH samples producing lower yields than RT and FRZ samples in both countries and SG in Austria (P < 0.042). Yet, qualitative and quantitative assessments of floral composition obtained using high-throughput sequencing with the ITS2 barcode gave non-significant effects of preservation methods on richness, relative abundance and Shannon diversity, in both countries. While freezing and ethanol are commonly employed for archiving tissue for molecular applications, desiccation is cheaper and easier to use regarding both storage and transportation. Since SG is less dependent on ambient humidity and less prone to contamination than RT, we recommend SG for preserving pollen for metabarcoding. SG is straightforward for laymen to use and hence robust for widespread application in citizen science studies.

A deep learning approach to automate whole-genome prediction of diverse epigenomic modifications in plants

Epigenetic modifications function in gene transcription, RNA metabolism, and other biological processes. However, multiple factors currently limit the scientific utility of epigenomic datasets generated for plants. Here, using deep-learning approaches, we developed a Smart Model for Epigenetics in Plants (SMEP) to predict six types of epigenomic modifications: DNA 5-methylcytosine (5mC) and N6-methyladenosine (6mA) methylation, RNA N6-methyladenosine (m⁶ A) methylation, and three types of histone modification. Using the datasets from the japonica rice Nipponbare, SMEP achieved 95% prediction accuracy for 6mA, and also achieved around 80% for 5mC, m⁶ A, and the three types of histone modification based on the 10-fold cross-validation. Additionally, > 95% of the 6mA peaks detected after a heat-shock treatment were predicted. We also successfully applied the SMEP for examining epigenomic modifications in indica rice 93-11 and even the B73 maize line. Taken together, we show that the deep-learning-enabled SMEP can reliably mine epigenomic datasets from diverse plants to yield actionable insights about epigenomic sites. Thus, our work opens new avenues for the application of predictive tools to facilitate functional research, and will almost certainly increase the efficiency of genome engineering efforts.

Review: tomographic imaging flow cytometry

Within the last decades, conventional flow cytometry (FC) has evolved as a powerful measurement method in clinical diagnostics, biology, life sciences and healthcare. Imaging flow cytometry (IFC) extends the power of traditional FC by adding high resolution optical and spectroscopic information. However, the conventional IFC only provides a 2D projection of a 3D object. To overcome this limitation, tomographic imaging flow cytometry (tIFC) was developed to access 3D information about the target particles. The goal of tIFC is to visualize surfaces and internal structures in a holistic way. This review article gives an overview of the past and current developments in tIFC.

Machine Learning Enhances the Performance of Bioreceptor-Free Biosensors

Since their inception, biosensors have frequently employed simple regression models to calculate analyte composition based on the biosensor's signal magnitude. Traditionally, bioreceptors provide excellent sensitivity and specificity to the biosensor. Increasingly, however, bioreceptor-free biosensors have been developed for a wide range of applications. Without a bioreceptor, maintaining strong specificity and a low limit of detection have become the major challenge. Machine learning (ML) has been introduced to improve the performance of these biosensors, effectively replacing the bioreceptor with modeling to gain specificity. Here, we present how ML has been used to enhance the performance of these bioreceptor-free biosensors. Particularly, we discuss how ML has been used for imaging, Enose and Etongue, and surface-enhanced Raman spectroscopy (SERS) biosensors. Notably, principal component analysis (PCA) combined with support vector machine (SVM) and various artificial neural network (ANN) algorithms have shown outstanding performance in a variety of tasks. We anticipate that ML will continue to improve the performance of bioreceptor-free biosensors, especially with the prospects of sharing trained models and cloud computing for mobile computation. To facilitate this, the biosensing community would benefit from increased contributions to open-access data repositories for biosensor data.

Segmenting 20 Types of Pollen Grains for the Cretan Pollen Dataset v1 (CPD-1)

Pollen analysis and the classification of several pollen species is an important task in melissopalynology. The development of machine learning or deep learning based classification models depends on available datasets of pollen grains from various plant species from around the globe. In this paper, Cretan Pollen Dataset v1 (CPD-1) is presented, which is a novel dataset of grains from 20 pollen species from plants gathered in Crete, Greece. The pollen grains were prepared and stained with fuchsin, in order to be captured by a camera attached to a microscope under a ×400 magnification. In addition, a pollen grain segmentation method is presented, which segments and crops each unique pollen grain and achieved an overall detection accuracy of 92%. The final dataset comprises 4034 segmented pollen grains of 20 different pollen species, as well as the raw data and ground truth, as annotated by an expert. The developed dataset is publicly accessible, which we hope will accelerate research in melissopalynology.

Deep learning-based high-throughput phenotyping can drive future discoveries in plant reproductive biology

Advances in deep learning are providing a powerful set of image analysis tools that are readily accessible for high-throughput phenotyping applications in plant reproductive biology. High-throughput phenotyping systems are becoming critical for answering biological questions on a large scale. These systems have historically relied on traditional computer vision techniques. However, neural networks and specifically deep learning are rapidly becoming more powerful and easier to implement. Here, we examine how deep learning can drive phenotyping systems and be used to answer fundamental questions in reproductive biology. We describe previous applications of deep learning in the plant sciences, provide general recommendations for applying these methods to the study of plant reproduction, and present a case study in maize ear phenotyping. Finally, we highlight several examples where deep learning has enabled research that was previously out of reach and discuss the future outlook of these methods.

Deep Learning Methods for Improving Pollen Monitoring

The risk of pollen-induced allergies can be determined and predicted based on data derived from pollen monitoring. Hirst-type samplers are sensors that allow airborne pollen grains to be detected and their number to be determined. Airborne pollen grains are deposited on adhesive-coated tape, and slides are then prepared, which require further analysis by specialized personnel. Deep learning can be used to recognize pollen taxa based on microscopic images. This paper presents a method for recognizing a taxon based on microscopic images of pollen grains, allowing the pollen monitoring process to be automated. In this research, a deep CNN (convolutional neural network) model was built from scratch. Publicly available deep neural network models, pre-trained on image data (not including microscopic pictures), were also used. The results show that even a simple deep learning model produces quite good results when the classification of pollen grain taxa is performed directly from the images. The best deep learning model achieved 97.88% accuracy in the difficult task of recognizing three types of pollen grains (birch, alder, and hazel) with similar structures. The derived models can be used to build a system to support pollen monitoring experts in their work.