DeepTetrad: high-throughput image analysis of meiotic tetrads by deep learning in Arabidopsis thaliana

The histone variant H2A.W restricts heterochromatic crossovers in Arabidopsis

Meiotic crossovers rearrange allele combinations and create offspring diversity. Crossovers occur nonrandomly along chromosomes, predominantly in distal euchromatin and less in pericentromeric heterochromatin marked with histone H3 lysine 9 dimethylation (H3K9me2) and the H2A variant H2A.W in Arabidopsis thaliana. Loss of H3K9me2 increases heterochromatic crossovers, but how H2A.W affects crossover formation in pericentromeric regions is unknown. Here, we report that H2A.W is required to restrict heterochromatic crossovers in Arabidopsis. Using meiosis-specific microRNA-induced gene silencing (meiMIGS) and fluorescence-tagged recombination reporters, we show that meiotic knockdown of H2A.W.6, H2A.W.7, and H2A.W.12 (meiMIGS-H2A.W.6/7/12) increases pericentromeric crossovers. High-resolution genomic maps of crossovers show that meiMIGS-H2A.W.6/7/12 enhances heterochromatic crossovers, similar to meiMIGS plants silencing the H3K9me2 pathway. Consistently, genome-wide crossover maps show that the mutants h2a.w.6, h2a.w.7, h2a.w.6 h2a.w.7, and h2a.w.6 h2a.w.7 h2a.w.12, but not h2a.w.12, exhibit a similar increase in heterochromatic crossovers to meiMIGS-H2A.W.6/7/12, demonstrating that H2A.W.6 and H2A.W.7 limit heterochromatic crossovers. Profiling of genome-wide nucleosome density using micrococcal nuclease sequencing reveals that h2a.w mutants with increased heterochromatic crossovers have increased heterochromatin accessibility, with lower H3K9me2 levels during meiosis. Our findings shed light on the role of H2A.W variants as heterochromatin compaction factors that suppress meiotic crossovers within the pericentromeric regions.

High-throughput classification of S. cerevisiae tetrads using deep learning

Meiotic crossovers play a vital role in proper chromosome segregation and evolution of most sexually reproducing organisms. Meiotic recombination can be visually observed in Saccharomyces cerevisiae tetrads using linked spore-autonomous fluorescent markers placed at defined intervals within the genome, which allows for analysis of meiotic segregation without the need for tetrad dissection. To automate the analysis, we developed a deep learning-based image recognition and classification pipeline for high-throughput tetrad detection and meiotic crossover classification. As a proof of concept, we analyzed a large image data set from wild-type and selected gene knock-out mutants to quantify crossover frequency, interference, chromosome missegregation, and gene conversion events. The deep learning-based method has the potential to accelerate the discovery of new genes involved in meiotic recombination in S. cerevisiae such as the underlying factors controlling crossover frequency and interference.

From Organelle Morphology to Whole-Plant Phenotyping: A Phenotypic Detection Method Based on Deep Learning

The analysis of plant phenotype parameters is closely related to breeding, so plant phenotype research has strong practical significance. This paper used deep learning to classify Arabidopsis thaliana from the macro (plant) to the micro level (organelle). First, the multi-output model identifies Arabidopsis accession lines and regression to predict Arabidopsis's 22-day growth status. The experimental results showed that the model had excellent performance in identifying Arabidopsis lines, and the model's classification accuracy was 99.92%. The model also had good performance in predicting plant growth status, and the regression prediction of the model root mean square error (RMSE) was 1.536. Next, a new dataset was obtained by increasing the time interval of Arabidopsis images, and the model's performance was verified at different time intervals. Finally, the model was applied to classify Arabidopsis organelles to verify the model's generalizability. Research suggested that deep learning will broaden plant phenotype detection methods. Furthermore, this method will facilitate the design and development of a high-throughput information collection platform for plant phenotypes.

Control of meiotic crossover interference by a proteolytic chaperone network

Meiosis is a specialized eukaryotic division that produces genetically diverse gametes for sexual reproduction. During meiosis, homologous chromosomes pair and undergo reciprocal exchanges, called crossovers, which recombine genetic variation. Meiotic crossovers are stringently controlled with at least one obligate exchange forming per chromosome pair, while closely spaced crossovers are inhibited by interference. In Arabidopsis, crossover positions can be explained by a diffusion-mediated coarsening model, in which large, approximately evenly spaced foci of the pro-crossover E3 ligase HEI10 grow at the expense of smaller, closely spaced clusters. However, the mechanisms that control HEI10 dynamics during meiosis remain unclear. Here, through a forward genetic screen in Arabidopsis, we identified high crossover rate3 (hcr3), a dominant-negative mutant that reduces crossover interference and increases crossovers genome-wide. HCR3 encodes J3, a co-chaperone related to HSP40, which acts to target protein aggregates and biomolecular condensates to the disassembly chaperone HSP70, thereby promoting proteasomal degradation. Consistently, we show that a network of HCR3 and HSP70 chaperones facilitates proteolysis of HEI10, thereby regulating interference and the recombination landscape. These results reveal a new role for the HSP40/J3-HSP70 chaperones in regulating chromosome-wide dynamics of recombination via control of HEI10 proteolysis.

Epigenetic regulation during meiosis and crossover

Meiosis is a distinctive type of cell division that reorganizes genetic material between generations. The initial stages of meiosis consist of several crucial steps which include double strand break, homologous chromosome pairing, break repair and crossover. Crossover frequency varies depending on the position on the chromosome, higher at euchromatin region and rare at heterochromatin, centromeres, telomeres and ribosomal DNA. Crossover positioning is dependent on various factors, especially epigenetic modifications. DNA methylation, histone post-translational modifications, histone variants and non-coding RNAs are most probably playing an important role in positioning of crossovers on a chromosomal level as well as hotspot level. DNA methylation negatively regulates crossover frequency and its effect is visible in centromeres, pericentromeres and heterochromatin regions. Pericentromeric chromatin and heterochromatin mark studies have been a centre of attraction in meiosis. Crossover hotspots are associated with euchromatin regions having specific chromatin modifications such as H3K4me3, H2A.Z. and H3 acetylation. This review will provide the current understanding of the epigenetic role in plants during meiotic recombination, chromosome synapsis, double strand break and hotspots with special attention to euchromatin and heterochromatin marks. Further, the role of epigenetic modifications in regulating meiosis and crossover in other organisms is also discussed.

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.

A review of open-source image analysis tools for mammalian cell culture: algorithms, features and implementations

Cell culture is undeniably important for multiple scientific applications, including pharmaceuticals, transplants, and cosmetics. However, cell culture involves multiple manual steps, such as regularly analyzing cell images for their health and morphology. Computer scientists have developed algorithms to automate cell imaging analysis, but they are not widely adopted by biologists, especially those lacking an interactive platform. To address the issue, we compile and review existing open-source cell image processing tools that provide interactive interfaces for management and prediction tasks. We highlight the prediction tools that can detect, segment, and track different mammalian cell morphologies across various image modalities and present a comparison of algorithms and unique features of these tools, whether they work locally or in the cloud. This would guide non-experts to determine which is best suited for their purposes and, developers to acknowledge what is worth further expansion. In addition, we provide a general discussion on potential implementations of the tools for a more extensive scope, which guides the reader to not restrict them to prediction tasks only. Finally, we conclude the article by stating new considerations for the development of interactive cell imaging tools and suggesting new directions for future research.

Arabidopsis HEAT SHOCK FACTOR BINDING PROTEIN is required to limit meiotic crossovers and HEI10 transcription

The number of meiotic crossovers is tightly controlled and most depend on pro-crossover ZMM proteins, such as the E3 ligase HEI10. Despite the importance of HEI10 dosage for crossover formation, how HEI10 transcription is controlled remains unexplored. In a forward genetic screen using a fluorescent crossover reporter in Arabidopsis thaliana, we identify heat shock factor binding protein (HSBP) as a repressor of HEI10 transcription and crossover numbers. Using genome-wide crossover mapping and cytogenetics, we show that hsbp mutations or meiotic HSBP knockdowns increase ZMM-dependent crossovers toward the telomeres, mirroring the effects of HEI10 overexpression. Through RNA sequencing, DNA methylome, and chromatin immunoprecipitation analysis, we reveal that HSBP is required to repress HEI10 transcription by binding with heat shock factors (HSFs) at the HEI10 promoter and maintaining DNA methylation over the HEI10 5' untranslated region. Our findings provide insights into how the temperature response regulator HSBP restricts meiotic HEI10 transcription and crossover number by attenuating HSF activity.

Knock-down of gene expression throughout meiosis and pollen formation by virus-induced gene silencing in Arabidopsis thaliana

Through the inactivation of genes that act during meiosis it is possible to direct the genetic make-up of plants in subsequent generations and optimize breeding schemes. Offspring may show higher recombination of parental alleles resulting from elevated crossover (CO) incidence, or by omission of meiotic divisions, offspring may become polyploid. However, stable mutations in genes essential for recombination, or for either one of the two meiotic divisions, can have pleiotropic effects on plant morphology and line stability, for instance by causing lower fertility. Therefore, it is often favorable to temporarily change gene expression during meiosis rather than relying on stable null mutants. It was previously shown that virus-induced gene silencing (VIGS) can be used to transiently reduce CO frequencies. We asked if VIGS could also be used to modify other processes throughout meiosis and during pollen formation in Arabidopsis thaliana. Here, we show that VIGS-mediated knock-down of FIGL1, RECQ4A/B, OSD1 and QRT2 can induce (i) an increase in chiasma numbers, (ii) unreduced gametes and (iii) pollen tetrads. We further show that VIGS can target both sexes and different genetic backgrounds and can simultaneously silence different gene copies. The successful knock-down of these genes in A. thaliana suggests that VIGS can be exploited to manipulate any process during or shortly after meiosis. Hence, the transient induction of changes in inheritance patterns can be used as a powerful tool for applied research and biotechnological applications.

Fast and Precise: How to Measure Meiotic Crossovers in Arabidopsis

During meiosis, homologous chromosomes (homologs) pair and undergo genetic recombination via assembly and disassembly of the synaptonemal complex. Meiotic recombination is initiated by excess formation of DNA double-strand breaks (DSBs), among which a subset are repaired by reciprocal genetic exchange, called crossovers (COs). COs generate genetic variations across generations, profoundly affecting genetic diversity and breeding. At least one CO between homologs is essential for the first meiotic chromosome segregation, but generally only one and fewer than three inter-homolog COs occur in plants. CO frequency and distribution are biased along chromosomes, suppressed in centromeres, and controlled by pro-CO, anti-CO, and epigenetic factors. Accurate and high-throughput detection of COs is important for our understanding of CO formation and chromosome behavior. Here, we review advanced approaches that enable precise measurement of the location, frequency, and genomic landscapes of COs in plants, with a focus on Arabidopsis thaliana.

YeastMate: Neural network-assisted segmentation of mating and budding events in S. cerevisiae

SUMMARY

Here, we introduce YeastMate, a user-friendly deep learning-based application for automated detection and segmentation of Saccharomyces cerevisiae cells and their mating and budding events in microscopy images. We build upon Mask R-CNN with a custom segmentation head for the subclassification of mother and daughter cells during lifecycle transitions. YeastMate can be used directly as a Python library or through a stand-alone GUI application and a Fiji plugin as easy to use frontends.

AVAILABILITY AND IMPLEMENTATION

The source code for YeastMate is freely available at https://github.com/hoerlteam/YeastMate under the MIT license. We offer installers for our software stack for Windows, macOS and Linux. A detailed user guide is available at https://yeastmate.readthedocs.io.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Domestication shapes recombination patterns in tomato

Meiotic recombination is a biological process of key importance in breeding, to generate genetic diversity and develop novel or agronomically relevant haplotypes. In crop tomato, recombination is curtailed as manifested by linkage disequilibrium decay over a longer distance and reduced diversity compared with wild relatives. Here, we compared domesticated and wild populations of tomato and found an overall conserved recombination landscape, with local changes in effective recombination rate in specific genomic regions. We also studied the dynamics of recombination hotspots resulting from domestication and found that loss of such hotspots is associated with selective sweeps, most notably in the pericentromeric heterochromatin. We detected footprints of genetic changes and structural variants, among them associated with transposable elements, linked with hotspot divergence during domestication, likely causing fine-scale alterations to recombination patterns and resulting in linkage drag.

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.

Understanding and exploiting uniparental genome elimination in plants: insights from Arabidopsis thaliana

Uniparental genome elimination (UGE) refers to the preferential exclusion of one set of the parental chromosome complement during embryogenesis following successful fertilization, giving rise to uniparental haploid progeny. This artificially induced phenomenon was documented as one of the consequences of distant (wide) hybridization in plants. Ten decades since its discovery, attempts to unravel the molecular mechanism behind this process remained elusive due to a lack of genetic tools and genomic resources in the species exhibiting UGE. Hence, its successful adoption in agronomic crops for in planta (in vivo) haploid production remains implausible. Recently, Arabidopsis thaliana has emerged as a model system to unravel the molecular basis of UGE. It is now possible to simulate the genetic consequences of distant crosses in an A. thaliana intraspecific cross by a simple modification of centromeres, via the manipulation of the centromere-specific histone H3 variant gene, CENH3. Thus, the experimental advantages conferred by A. thaliana have been used to elucidate and exploit the benefits of UGE in crop breeding. In this review, we discuss developments and prospects of CENH3 gene-mediated UGE and other in planta haploid induction strategies to illustrate its potential in expediting plant breeding and genetics in A. thaliana and other model plants.

HIGH CROSSOVER RATE1 encodes PROTEIN PHOSPHATASE X1 and restricts meiotic crossovers in Arabidopsis

Meiotic crossovers are tightly restricted in most eukaryotes, despite an excess of initiating DNA double-strand breaks. The majority of plant crossovers are dependent on class I interfering repair, with a minority formed via the class II pathway. Class II repair is limited by anti-recombination pathways; however, similar pathways repressing class I crossovers have not been identified. Here, we performed a forward genetic screen in Arabidopsis using fluorescent crossover reporters to identify mutants with increased or decreased recombination frequency. We identified HIGH CROSSOVER RATE1 (HCR1) as repressing crossovers and encoding PROTEIN PHOSPHATASE X1. Genome-wide analysis showed that hcr1 crossovers are increased in the distal chromosome arms. MLH1 foci significantly increase in hcr1 and crossover interference decreases, demonstrating an effect on class I repair. Consistently, yeast two-hybrid and in planta assays show interaction between HCR1 and class I proteins, including HEI10, PTD, MSH5 and MLH1. We propose that HCR1 plays a major role in opposition to pro-recombination kinases to restrict crossovers in Arabidopsis.

Direct evidence for crossover and chromatid interference in meiosis of two plant hybrids (Lolium multiflorum×Festuca pratensis and Allium cepa×A. roylei)

Crossing over, in addition to its strictly genetic role, also performs a critical mechanical function, by bonding homologues in meiosis. Hence, it is responsible for an orderly reduction of the chromosome number. As such, it is strictly controlled in frequency and distribution. The well-known crossover control is positive crossover interference which reduces the probability of a crossover in the vicinity of an already formed crossover. A poorly studied aspect of the control is chromatid interference. Such analyses are possible in very few organisms as they require observation of all four products of a single meiosis. Here, we provide direct evidence of chromatid interference. Using in situ probing in two interspecific plant hybrids (Lolium multiflorum×Festuca pratensis and Allium cepa×A. roylei) during anaphase I, we demonstrate that the involvement of four chromatids in double crossovers is significantly more frequent than expected (64% versus 25%). We also provide a physical measure of the crossover interference distance, covering ~30-40% of the relative chromosome arm length, and show that the centromere acts as a barrier for crossover interference. The two arms of a chromosome appear to act as independent units in the process of crossing over. Chromatid interference has to be seriously addressed in genetic mapping approaches and further studies.

A Deep Learning-Based System (Microscan) for the Identification of Pollen Development Stages and Its Application to Obtaining Doubled Haploid Lines in Eggplant

The development of double haploids (DHs) is a straightforward path for obtaining pure lines but has multiple bottlenecks. Among them is the determination of the optimal stage of pollen induction for androgenesis. In this work, we developed Microscan, a deep learning-based system for the detection and recognition of the stages of pollen development. In a first experiment, the algorithm was developed adapting the RetinaNet predictive model using microspores of different eggplant accessions as samples. A mean average precision of 86.30% was obtained. In a second experiment, the anther range to be cultivated in vitro was determined in three eggplant genotypes by applying the Microscan system. Subsequently, they were cultivated following two different androgenesis protocols (Cb and E6). The response was only observed in the anther size range predicted by Microscan, obtaining the best results with the E6 protocol. The plants obtained were characterized by flow cytometry and with the Single Primer Enrichment Technology high-throughput genotyping platform, obtaining a high rate of confirmed haploid and double haploid plants. Microscan has been revealed as a tool for the high-throughput efficient analysis of microspore samples, as it has been exemplified in eggplant by providing an increase in the yield of DHs production.