Mapping the gene expression universe

Perspectives and applications of machine learning for evolutionary developmental biology

Evolutionary Developmental Biology (Evo-Devo) is an ever-expanding field that aims to understand how development was modulated by the evolutionary process. In this sense, "omic" studies emerged as a powerful ally to unravel the molecular mechanisms underlying development. In this scenario, bioinformatics tools become necessary to analyze the growing amount of information. Among computational approaches, machine learning stands out as a promising field to generate knowledge and trace new research perspectives for bioinformatics. In this review, we aim to expose the current advances of machine learning applied to evolution and development. We draw clear perspectives and argue how evolution impacted machine learning techniques.

A mesh generation and machine learning framework for Drosophila gene expression pattern image analysis

BACKGROUND

Multicellular organisms consist of cells of many different types that are established during development. Each type of cell is characterized by the unique combination of expressed gene products as a result of spatiotemporal gene regulation. Currently, a fundamental challenge in regulatory biology is to elucidate the gene expression controls that generate the complex body plans during development. Recent advances in high-throughput biotechnologies have generated spatiotemporal expression patterns for thousands of genes in the model organism fruit fly Drosophila melanogaster. Existing qualitative methods enhanced by a quantitative analysis based on computational tools we present in this paper would provide promising ways for addressing key scientific questions.

RESULTS

We develop a set of computational methods and open source tools for identifying co-expressed embryonic domains and the associated genes simultaneously. To map the expression patterns of many genes into the same coordinate space and account for the embryonic shape variations, we develop a mesh generation method to deform a meshed generic ellipse to each individual embryo. We then develop a co-clustering formulation to cluster the genes and the mesh elements, thereby identifying co-expressed embryonic domains and the associated genes simultaneously. Experimental results indicate that the gene and mesh co-clusters can be correlated to key developmental events during the stages of embryogenesis we study. The open source software tool has been made available at http://compbio.cs.odu.edu/fly/.

CONCLUSIONS

Our mesh generation and machine learning methods and tools improve upon the flexibility, ease-of-use and accuracy of existing methods.

Whole mount RNA fluorescent in situ hybridization of Drosophila embryos

Assessing the expression pattern of a gene, as well as the subcellular localization properties of its transcribed RNA, are key features for understanding its biological function during development. RNA in situ hybridization (RNA-ISH) is a powerful method used for visualizing RNA distribution properties, be it at the organismal, cellular or subcellular levels. RNA-ISH is based on the hybridization of a labeled nucleic acid probe (e.g. antisense RNA, oligonucleotides) complementary to the sequence of an mRNA or a non-coding RNA target of interest. As the procedure requires primary sequence information alone to generate sequence-specific probes, it can be universally applied to a broad range of organisms and tissue specimens. Indeed, a number of large-scale ISH studies have been implemented to document gene expression and RNA localization dynamics in various model organisms, which has led to the establishment of important community resources. While a variety of probe labeling and detection strategies have been developed over the years, the combined usage of fluorescently-labeled detection reagents and enzymatic signal amplification steps offer significant enhancements in the sensitivity and resolution of the procedure. Here, we describe an optimized fluorescent in situ hybridization method (FISH) employing tyramide signal amplification (TSA) to visualize RNA expression and localization dynamics in staged Drosophila embryos. The procedure is carried out in 96-well PCR plate format, which greatly facilitates the simultaneous processing of large numbers of samples.

A microfluidic device and computational platform for high-throughput live imaging of gene expression

To fully describe gene expression dynamics requires the ability to quantitatively capture expression in individual cells over time. Automated systems for acquiring and analyzing real-time images are needed to obtain unbiased data across many samples and conditions. We developed a microfluidics device, the RootArray, in which 64 Arabidopsis thaliana seedlings can be grown and their roots imaged by confocal microscopy over several days without manual intervention. To achieve high throughput, we decoupled acquisition from analysis. In the acquisition phase, we obtain images at low resolution and segment to identify regions of interest. Coordinates are communicated to the microscope to record the regions of interest at high resolution. In the analysis phase, we reconstruct three-dimensional objects from stitched high-resolution images and extract quantitative measurements from a virtual medial section of the root. We tracked hundreds of roots to capture detailed expression patterns of 12 transgenic reporter lines under different conditions.

Learning sparse representations for fruit-fly gene expression pattern image annotation and retrieval

Background

Fruit fly embryogenesis is one of the best understood animal development systems, and the spatiotemporal gene expression dynamics in this process are captured by digital images. Analysis of these high-throughput images will provide novel insights into the functions, interactions, and networks of animal genes governing development. To facilitate comparative analysis, web-based interfaces have been developed to conduct image retrieval based on body part keywords and images. Currently, the keyword annotation of spatiotemporal gene expression patterns is conducted manually. However, this manual practice does not scale with the continuously expanding collection of images. In addition, existing image retrieval systems based on the expression patterns may be made more accurate using keywords.

Results

In this article, we adapt advanced data mining and computer vision techniques to address the key challenges in annotating and retrieving fruit fly gene expression pattern images. To boost the performance of image annotation and retrieval, we propose representations integrating spatial information and sparse features, overcoming the limitations of prior schemes.

Conclusions

We perform systematic experimental studies to evaluate the proposed schemes in comparison with current methods. Experimental results indicate that the integration of spatial information and sparse features lead to consistent performance improvement in image annotation, while for the task of retrieval, sparse features alone yields better results.

High resolution fluorescent in situ hybridization in Drosophila

Tissue-specific gene expression is a major determinant in the elaboration of cells with distinctive phenotypes and functions, which is crucial for the development and homeostasis of multicellular organisms. Fluorescent in situ hybridization (FISH) is a powerful method for assessing the expression and localization properties of RNA at subcellular resolution in whole mount organism and tissue specimens. This chapter describes a high-resolution FISH protocol for the detection of RNA expression and localization dynamics in embryos and tissues of the fruit fly, Drosophila melanogaster. The approach utilizes tyramide signal amplification (TSA) for enhanced sensitivity and resolution in the detection of coding and noncoding RNAs, for the codetection of different RNA species or of RNA and a protein marker of interest. Furthermore, the protocol outlines details for conducting FISH in microtiter plates, which greatly enhances the throughput, practicality, and economy of the procedure.

Visualization of image data from cells to organisms

Advances in imaging techniques and high-throughput technologies are providing scientists with unprecedented possibilities to visualize internal structures of cells, organs and organisms and to collect systematic image data characterizing genes and proteins on a large scale. To make the best use of these increasingly complex and large image data resources, the scientific community must be provided with methods to query, analyze and crosslink these resources to give an intuitive visual representation of the data. This review gives an overview of existing methods and tools for this purpose and highlights some of their limitations and challenges.

Analysis of cell fate from single-cell gene expression profiles in C. elegans

The C. elegans cell lineage provides a unique opportunity to look at how cell lineage affects patterns of gene expression. We developed an automatic cell lineage analyzer that converts high-resolution images of worms into a data table showing fluorescence expression with single-cell resolution. We generated expression profiles of 93 genes in 363 specific cells from L1 stage larvae and found that cells with identical fates can be formed by different gene regulatory pathways. Molecular signatures identified repeating cell fate modules within the cell lineage and enabled the generation of a molecular differentiation map that reveals points in the cell lineage when developmental fates of daughter cells begin to diverge. These results demonstrate insights that become possible using computational approaches to analyze quantitative expression from many genes in parallel using a digital gene expression atlas.

Global implications of mRNA localization pathways in cellular organization

Genome expression profiling has led to the important realization that RNA molecules are more numerous and diverse than previously expected. One aspect of RNA biology that is just beginning to be fully appreciated is the extent to which mRNAs are transported to specific subcellular destinations before being translated, an exquisite mechanism for targeting proteins where they are required in the cell. While several excellent reviews have discussed the subject of mRNA localization, it is only in recent years that high-throughput technologies have been applied to address issues such as the extent and diversity of RNA localization events and mechanisms. This review focuses on these recent functional genomic approaches, their implications, and the new tools and methods that will be needed to further elucidate mRNA localization pathways.