Comparison of embryonic expression within multigene families using the FlyExpress discovery platform reveals more spatial than temporal divergence

MIGGRI: A multi-instance graph neural network model for inferring gene regulatory networks for Drosophila from spatial expression images

Recent breakthrough in spatial transcriptomics has brought great opportunities for exploring gene regulatory networks (GRNs) from a brand-new perspective. Especially, the local expression patterns and spatio-temporal regulation mechanisms captured by spatial expression images allow more delicate delineation of the interplay between transcript factors and their target genes. However, the complexity and size of spatial image collections pose significant challenges to GRN inference using image-based methods. Extracting regulatory information from expression images is difficult due to the lack of supervision and the multi-instance nature of the problem, where a gene often corresponds to multiple images captured from different views. While graph models, particularly graph neural networks, have emerged as a promising method for leveraging underlying structure information from known GRNs, incorporating expression images into graphs is not straightforward. To address these challenges, we propose a two-stage approach, MIGGRI, for capturing comprehensive regulatory patterns from image collections for each gene and known interactions. Our approach involves a multi-instance graph neural network (GNN) model for GRN inference, which first extracts gene regulatory features from spatial expression images via contrastive learning, and then feeds them to a multi-instance GNN for semi-supervised learning. We apply our approach to a large set of Drosophila embryonic spatial gene expression images. MIGGRI achieves outstanding performance in the inference of GRNs for early eye development and mesoderm development of Drosophila, and shows robustness in the scenarios of missing image information. Additionally, we perform interpretable analysis on image reconstruction and functional subgraphs that may reveal potential pathways or coordinate regulations. By leveraging the power of graph neural networks and the information contained in spatial expression images, our approach has the potential to advance our understanding of gene regulation in complex biological systems.

Deep Low-Shot Learning for Biological Image Classification and Visualization From Limited Training Samples

Predictive modeling is useful but very challenging in biological image analysis due to the high cost of obtaining and labeling training data. For example, in the study of gene interaction and regulation in Drosophila embryogenesis, the analysis is most biologically meaningful when in situ hybridization (ISH) gene expression pattern images from the same developmental stage are compared. However, labeling training data with precise stages is very time-consuming even for developmental biologists. Thus, a critical challenge is how to build accurate computational models for precise developmental stage classification from limited training samples. In addition, identification and visualization of developmental landmarks are required to enable biologists to interpret prediction results and calibrate models. To address these challenges, we propose a deep two-step low-shot learning framework to accurately classify ISH images using limited training images. Specifically, to enable accurate model training on limited training samples, we formulate the task as a deep low-shot learning problem and develop a novel two-step learning approach, including data-level learning and feature-level learning. We use a deep residual network as our base model and achieve improved performance in the precise stage prediction task of ISH images. Furthermore, the deep model can be interpreted by computing saliency maps, which consists of pixel-wise contributions of an image to its prediction result. In our task, saliency maps are used to assist the identification and visualization of developmental landmarks. Our experimental results show that the proposed model can not only make accurate predictions but also yield biologically meaningful interpretations. We anticipate our methods to be easily generalizable to other biological image classification tasks with small training datasets. Our open-source code is available at https://github.com/divelab/lsl-fly.

Accurate inference of gene regulatory interactions from spatial gene expression with deep contrastive learning

MOTIVATION

Reverse engineering of gene regulatory networks (GRNs) has long been an attractive research topic in system biology. Computational prediction of gene regulatory interactions has remained a challenging problem due to the complexity of gene expression and scarce information resources. The high-throughput spatial gene expression data, like in situ hybridization images that exhibit temporal and spatial expression patterns, has provided abundant and reliable information for the inference of GRNs. However, computational tools for analyzing the spatial gene expression data are highly underdeveloped.

RESULTS

In this study, we develop a new method for identifying gene regulatory interactions from gene expression images, called ConGRI. The method is featured by a contrastive learning scheme and deep Siamese convolutional neural network architecture, which automatically learns high-level feature embeddings for the expression images and then feeds the embeddings to an artificial neural network to determine whether or not the interaction exists. We apply the method to a Drosophila embryogenesis dataset and identify GRNs of eye development and mesoderm development. Experimental results show that ConGRI outperforms previous traditional and deep learning methods by a large margin, which achieves accuracies of 76.7% and 68.7% for the GRNs of early eye development and mesoderm development, respectively. It also reveals some master regulators for Drosophila eye development.

AVAILABILITYAND IMPLEMENTATION

https://github.com/lugimzheng/ConGRI.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

The F-box protein Bard (CG14317) targets the Smaug RNA-binding protein for destruction during the Drosophila maternal-to-zygotic transition

During the maternal-to-zygotic transition (MZT), which encompasses the earliest stages of animal embryogenesis, a subset of maternally supplied gene products is cleared, thus permitting activation of zygotic gene expression. In the Drosophila melanogaster embryo, the RNA-binding protein Smaug (SMG) plays an essential role in progression through the MZT by translationally repressing and destabilizing a large number of maternal mRNAs. The SMG protein itself is rapidly cleared at the end of the MZT by a Skp/Cullin/F-box (SCF) E3-ligase complex. Clearance of SMG requires zygotic transcription and is required for an orderly MZT. Here, we show that an F-box protein, which we name Bard (encoded by CG14317), is required for degradation of SMG. Bard is expressed zygotically and physically interacts with SMG at the end of the MZT, coincident with binding of the maternal SCF proteins, SkpA and Cullin1, and with degradation of SMG. shRNA-mediated knock-down of Bard or deletion of the bard gene in the early embryo results in stabilization of SMG protein, a phenotype that is rescued by transgenes expressing Bard. Bard thus times the clearance of SMG at the end of the MZT.

The Roles of the LIM Domain Proteins in Drosophila Cardiac and Hematopoietic Morphogenesis

Drosophila melanogaster has been used as a model organism for study on development and pathophysiology of the heart. LIM domain proteins act as adaptors or scaffolds to promote the assembly of multimeric protein complexes. We found a total of 75 proteins encoded by 36 genes have LIM domain in Drosophila melanogaster by the tools of SMART, FLY-FISH, and FlyExpress, and around 41.7% proteins with LIM domain locate in lymph glands, muscles system, and circulatory system. Furthermore, we summarized functions of different LIM domain proteins in the development and physiology of fly heart and hematopoietic systems. It would be attractive to determine whether it exists a probable "LIM code" for the cycle of different cell fates in cardiac and hematopoietic tissues. Next, we aspired to propose a new research direction that the LIM domain proteins may play an important role in fly cardiac and hematopoietic morphogenesis.

Quantitative analyses of EGFR localization and trafficking dynamics in the follicular epithelium

To bridge the gap between qualitative and quantitative analyses of the epidermal growth factor receptor (EGFR) in tissues, we generated an sfGFP-tagged EGF receptor (EGFR-sfGFP) in Drosophila The homozygous fly appears similar to wild type with EGFR expression and activation patterns that are consistent with previous reports in the ovary, early embryo, and imaginal discs. Using ELISA, we quantified an average of 1100, 6200 and 2500 receptors per follicle cell (FC) at stages 8/9, 10 and ≥11 of oogenesis, respectively. Interestingly, the spatial localization of the EGFR to the apical side of the FCs at early stages depended on the TGFα-like ligand Gurken. At later stages, EGFR localized to basolateral positions of the FCs. Finally, we followed the endosomal localization of EGFR in the FCs. The EGFR colocalized with the late endosome, but no significant colocalization of the receptor was found with the early endosome. The EGFR-sfGFP fly is an exciting new resource for studying cellular localization and regulation of EGFR in tissues.

Predicting gene regulatory interactions based on spatial gene expression data and deep learning

Reverse engineering of gene regulatory networks (GRNs) is a central task in systems biology. Most of the existing methods for GRN inference rely on gene co-expression analysis or TF-target binding information, where the determination of co-expression is often unreliable merely based on gene expression levels, and the TF-target binding data from high-throughput experiments may be noisy, leading to a high ratio of false links and missed links, especially for large-scale networks. In recent years, the microscopy images recording spatial gene expression have become a new resource in GRN reconstruction, as the spatial and temporal expression patterns contain much abundant gene interaction information. Till now, the spatial expression resources have been largely underexploited, and only a few traditional image processing methods have been employed in the image-based GRN reconstruction. Moreover, co-expression analysis using conventional measurements based on image similarity may be inaccurate, because it is the local-pattern consistency rather than global-image-similarity that determines gene-gene interactions. Here we present GripDL (Gene regulatory interaction prediction via Deep Learning), which incorporates high-confidence TF-gene regulation knowledge from previous studies, and constructs GRNs for Drosophila eye development based on Drosophila embryonic gene expression images. Benefitting from the powerful representation ability of deep neural networks and the supervision information of known interactions, the new method outperforms traditional methods with a large margin and reveals new intriguing knowledge about Drosophila eye development.

In locus analysis of patterning evolution of the BMP type II receptor Wishful thinking

Proper tissue patterning is an essential step during organ formation. During this process, genes are expressed in distinct patterns, defining boundaries for future functional domains. The bone morphogenetic protein (BMP) signaling pathway sets the anterior domain during eggshell patterning. Previously, the Drosophila melanogaster homolog of BMPR2, Wishful thinking (WIT), was shown to be required for BMP signaling and patterning during eggshell formation. Expressed in a conserved anterior pattern, the width of wit patterning in the follicular epithelium is evolutionarily divergent between Drosophila species. We used genome editing to demonstrate how the gene pattern divergence is controlled in cis within the wit locus of D. virilis Furthermore, unlike direct targets of BMP signaling, we demonstrate how one transcription factor binding site shapes the pattern of WIT in D. melanogaster by negative regulation. However, changes in this site are not sufficient to explain the evolution of wit patterning, suggesting that a positive regulatory element that controls pattern divergence remains to be discovered.

Simple Expression Domains Are Regulated by Discrete CRMs During Drosophila Oogenesis

Eggshell patterning has been extensively studied in Drosophila melanogaster. However, the cis-regulatory modules (CRMs), which control spatiotemporal expression of these patterns, are vastly unexplored. The FlyLight collection contains >7000 intergenic and intronic DNA fragments that, if containing CRMs, can drive the transcription factor GAL4. We cross-listed the 84 genes known to be expressed during D. melanogaster oogenesis with the ∼1200 listed genes of the FlyLight collection, and found 22 common genes that are represented by 281 FlyLight fly lines. Of these lines, 54 show expression patterns during oogenesis when crossed to an UAS-GFP reporter. Of the 54 lines, 16 recapitulate the full or partial pattern of the associated gene pattern. Interestingly, while the average DNA fragment size is ∼3 kb in length, the vast majority of fragments show one type of spatiotemporal pattern in oogenesis. Mapping the distribution of all 54 lines, we found a significant enrichment of CRMs in the first intron of the associated genes’ model. In addition, we demonstrate the use of different anteriorly active FlyLight lines as tools to disrupt eggshell patterning in a targeted manner. Our screen provides further evidence that complex gene patterns are assembled combinatorially by different CRMs controlling the expression of genes in simple domains.

FlyExpress 7: An Integrated Discovery Platform To Study Coexpressed Genes Using in Situ Hybridization Images in Drosophila

Gene expression patterns assayed across development can offer key clues about a gene's function and regulatory role. Drosophila melanogaster is ideal for such investigations as multiple individual and high-throughput efforts have captured the spatiotemporal patterns of thousands of embryonic expressed genes in the form of in situ images. FlyExpress (www.flyexpress.net), a knowledgebase based on a massive and unique digital library of standardized images and a simple search engine to find coexpressed genes, was created to facilitate the analytical and visual mining of these patterns. Here, we introduce the next generation of FlyExpress resources to facilitate the integrative analysis of sequence data and spatiotemporal patterns of expression from images. FlyExpress 7 now includes over 100,000 standardized in situ images and implements a more efficient, user-defined search algorithm to identify coexpressed genes via Genomewide Expression Maps (GEMs). Shared motifs found in the upstream 5' regions of any pair of coexpressed genes can be visualized in an interactive dotplot. Additional webtools and link-outs to assist in the downstream validation of candidate motifs are also provided. Together, FlyExpress 7 represents our largest effort yet to accelerate discovery via the development and dispersal of new webtools that allow researchers to perform data-driven analyses of coexpression (image) and genomic (sequence) data.

Representation of anatomy in online atlases and databases: a survey and collection of patterns for interface design

BACKGROUND

A large number of online atlases and databases have been developed to mange the rapidly growing amount of data describing embryogenesis. As these community resources continue to evolve, it is important to understand how representations of anatomy can facilitate the sharing and integration of data. In addition, attention to the design of the interfaces is critical to make online resources useful and usable.

RESULTS

I first present a survey of online atlases and gene expression resources for model organisms, with a focus on methods of semantic and spatial representation of anatomy. A total of 14 anatomical atlases and 21 gene expression resources are included. This survey demonstrates how choices in semantic representation, in the form of ontologies, can enhance interface search functions and provide links between relevant information. This survey also reviews methods for spatially representing anatomy in online resources. I then provide a collection of patterns for interface design based on the atlases and databases surveyed. These patterns include methods for displaying graphics, integrating semantic and spatial representations, organizing information, and querying databases to find genes expressed in anatomical structures.

CONCLUSIONS

This collection of patterns for interface design will assist biologists and software developers in planning the interfaces of new atlases and databases or enhancing existing ones. They also show the benefits of standardizing semantic and spatial representations of anatomy by demonstrating how interfaces can use standardization to provide enhanced functionality.

myFX: a turn-key software for laboratory desktops to analyze spatial patterns of gene expression in Drosophila embryos

Spatial patterns of gene expression are of key importance in understanding developmental networks. Using in situ hybridization, many laboratories are generating images to describe these spatial patterns and to test biological hypotheses. To facilitate such analyses, we have developed biologist-centric software (myFX) that contains computational methods to automatically process and analyze images depicting embryonic gene expression in the fruit fly Drosophila melanogaster. It facilitates creating digital descriptions of spatial patterns in images and enables measurements of pattern similarity and visualization of expression across genes and developmental stages. myFX interacts directly with the online FlyExpress database, which allows users to search thousands of existing patterns to find co-expressed genes by image comparison.

Bioimage Informatics in the context of Drosophila research

Modern biological research relies heavily on microscopic imaging. The advanced genetic toolkit of Drosophila makes it possible to label molecular and cellular components with unprecedented level of specificity necessitating the application of the most sophisticated imaging technologies. Imaging in Drosophila spans all scales from single molecules to the entire populations of adult organisms, from electron microscopy to live imaging of developmental processes. As the imaging approaches become more complex and ambitious, there is an increasing need for quantitative, computer-mediated image processing and analysis to make sense of the imagery. Bioimage Informatics is an emerging research field that covers all aspects of biological image analysis from data handling, through processing, to quantitative measurements, analysis and data presentation. Some of the most advanced, large scale projects, combining cutting edge imaging with complex bioimage informatics pipelines, are realized in the Drosophila research community. In this review, we discuss the current research in biological image analysis specifically relevant to the type of systems level image datasets that are uniquely available for the Drosophila model system. We focus on how state-of-the-art computer vision algorithms are impacting the ability of Drosophila researchers to analyze biological systems in space and time. We pay particular attention to how these algorithmic advances from computer science are made usable to practicing biologists through open source platforms and how biologists can themselves participate in their further development.

Automated annotation of developmental stages of Drosophila embryos in images containing spatial patterns of expression

MOTIVATION

Drosophila melanogaster is a major model organism for investigating the function and interconnection of animal genes in the earliest stages of embryogenesis. Today, images capturing Drosophila gene expression patterns are being produced at a higher throughput than ever before. The analysis of spatial patterns of gene expression is most biologically meaningful when images from a similar time point during development are compared. Thus, the critical first step is to determine the developmental stage of an embryo. This information is also needed to observe and analyze expression changes over developmental time. Currently, developmental stages (time) of embryos in images capturing spatial expression pattern are annotated manually, which is time- and labor-intensive. Embryos are often designated into stage ranges, making the information on developmental time course. This makes downstream analyses inefficient and biological interpretations of similarities and differences in spatial expression patterns challenging, particularly when using automated tools for analyzing expression patterns of large number of images.

RESULTS

Here, we present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In an analysis of 3724 images, the new approach shows high accuracy in predicting the developmental stage correctly (79%). In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores for all images containing expression patterns of the same gene enable a direct way to view expression changes over developmental time for any gene. We show that the genomewide-expression-maps generated using images from embryos in refined stages illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.

AVAILABILITY AND IMPLEMENTATION

The software package is availablefor download at: http://www.public.asu.edu/*jye02/Software/Fly-Project/.

Chorion patterning: a window into gene regulation and Drosophila species' relatedness

Changes in gene regulation are associated with the evolution of morphologies. However, the specific sequence information controlling gene expression is largely unknown and discovery is time and labor consuming. We use the intricate patterning of follicle cells to probe species' relatedness in the absence of sequence information. We focus on one of the major families of genes that pattern the Drosophila eggshell, the Chorion protein (Cp). Systematically screening for the spatiotemporal patterning of all nine Cp genes in three species (Drosophila melanogaster, D. nebulosa, and D. willistoni), we found that most genes are expressed dynamically during mid and late stages of oogenesis. Applying an annotation code, we transformed the data into binary matrices that capture the complexity of gene expression. Gene patterning is sufficient to predict species' relatedness, consistent with their phylogeny. Surprisingly, we found that expression domains of most genes are different among species, suggesting that Cp regulation is rapidly evolving. In addition, we found a morphological novelty along the dorsalmost side of the eggshell, the dorsal ridge. Our matrix analysis placed the dorsal ridge domain in a cluster of epidermal growth factor receptor associated domains, which was validated through genetic and chemical perturbations. Expression domains are regulated cooperatively or independently by signaling pathways, supporting that complex patterns are combinatorially assembled from simple domains.

Functional genetic characterization of salivary gland development in Aedes aegypti

BACKGROUND

Despite the devastating global impact of mosquito-borne illnesses on human health, very little is known about mosquito developmental biology. In this investigation, functional genetic analysis of embryonic salivary gland development was performed in Aedes aegypti, the dengue and yellow fever vector and an emerging model for vector mosquito development. Although embryonic salivary gland development has been well studied in Drosophila melanogaster, little is known about this process in mosquitoes or other arthropods.

RESULTS

Mosquitoes possess orthologs of many genes that regulate Drosophila melanogaster embryonic salivary gland development. The expression patterns of a large subset of these genes were assessed during Ae. aegypti development. These studies identified a set of molecular genetic markers for the developing mosquito salivary gland. Analysis of marker expression allowed for tracking of the progression of Ae. aegypti salivary gland development in embryos. In Drosophila, the salivary glands develop from placodes located in the ventral neuroectoderm. However, in Ae. aegypti, salivary marker genes are not expressed in placode-like patterns in the ventral neuroectoderm. Instead, marker gene expression is detected in salivary gland rudiments adjacent to the proventriculus. These observations highlighted the need for functional genetic characterization of mosquito salivary gland development. An siRNA- mediated knockdown strategy was therefore employed to investigate the role of one of the marker genes, cyclic-AMP response element binding protein A (Aae crebA), during Ae. aegypti salivary gland development. These experiments revealed that Aae crebA encodes a key transcriptional regulator of the secretory pathway in the developing Ae. aegypti salivary gland.

CONCLUSIONS

The results of this investigation indicated that the initiation of salivary gland development in Ae. aegypti significantly differs from that of D. melanogaster. Despite these differences, some elements of salivary gland development, including the ability of CrebA to regulate secretory gene expression, are conserved between the two species. These studies underscore the need for further analysis of mosquito developmental genetics and may foster comparative studies of salivary gland development in additional insect species.

Exploring spatial patterns of gene expression from fruit fly embryogenesis on the iPhone

Mobile technologies provide unique opportunities for ubiquitous distribution of scientific information through user-friendly interfaces. Therefore, we have developed a new FlyExpress mobile application that makes available a growing collection (>100 000) of standardized in situ hybridization images containing spatial patterns of gene expression from Drosophila melanogaster (fruit fly) embryogenesis. Using this application, scientists can visualize and compare expression patterns of >4000 developmentally relevant genes. The FlyExpress app displays the expression patterns of the selected gene for different visual projections (e.g. lateral) and displays them according to their developmental stages, which shows a gene's progression of spatial expression over developmental time. Ultimately, we envision the use of FlyExpress app in the laboratory where scientists may wish to immediately conduct a visual comparison of a known expression pattern with the one observed on the bench top or to display expression patterns of interest during scientific discussions at large.

AVAILABILITY

Search "FlyExpress" on the Apple iTunes store.

FlyExpress: visual mining of spatiotemporal patterns for genes and publications in Drosophila embryogenesis

SUMMARY

Images containing spatial expression patterns illuminate the roles of different genes during embryogenesis. In order to generate initial clues to regulatory interactions, biologists frequently need to know the set of genes expressed at the same time at specific locations in a developing embryo, as well as related research publications. However, text-based mining of image annotations and research articles cannot produce all relevant results, because the primary data are images that exist as graphical objects. We have developed a unique knowledge base (FlyExpress) to facilitate visual mining of images from Drosophila melanogaster embryogenesis. By clicking on specific locations in pictures of fly embryos from different stages of development and different visual projections, users can produce a list of genes and publications instantly. In FlyExpress, each queryable embryo picture is a heat-map that captures the expression patterns of more than 4500 genes and more than 2600 published articles. In addition, one can view spatial patterns for particular genes over time as well as find other genes with similar expression patterns at a given developmental stage. Therefore, FlyExpress is a unique tool for mining spatiotemporal expression patterns in a format readily accessible to the scientific community.

AVAILABILITY

http://www.flyexpress.net

CONTACT

s.kumar@asu.edu.