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.
Learning Sparse Representations for Fruit-Fly Gene Expression Pattern Image Annotation and Retrieval
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.
Drosophila melanogaster has been established as a model organism for investigating the developmental gene interactions. The spatio-temporal gene expression patterns of Drosophila melanogaster can be visualized by in situ hybridization and documented as digital images. Automated and efficient tools for analyzing these expression images will provide biological insights into the gene functions, interactions, and networks. To facilitate pattern recognition and comparison, many web-based resources have been created to conduct comparative analysis based on the body part keywords and the associated images. With the fast accumulation of images from high-throughput techniques, manual inspection of images will impose a serious impediment on the pace of biological discovery. It is thus imperative to design an automated system for efficient image annotation and comparison.
Results
We present a computational framework to perform anatomical keywords annotation for Drosophila gene expression images. The spatial sparse coding approach is used to represent local patches of images in comparison with the well-known bag-of-words (BoW) method. Three pooling functions including max pooling, average pooling and Sqrt (square root of mean squared statistics) pooling are employed to transform the sparse codes to image features. Based on the constructed features, we develop both an image-level scheme and a group-level scheme to tackle the key challenges in annotating Drosophila gene expression pattern images automatically. To deal with the imbalanced data distribution inherent in image annotation tasks, the undersampling method is applied together with majority vote. Results on Drosophila embryonic expression pattern images verify the efficacy of our approach.
Conclusion
In our experiment, the three pooling functions perform comparably well in feature dimension reduction. The undersampling with majority vote is shown to be effective in tackling the problem of imbalanced data. Moreover, combining sparse coding and image-level scheme leads to consistent performance improvement in keywords annotation.
Exchange transfusion is the replacement of blood from newborn infants with elevated bilirubin level in their blood stream with donor blood containing normal bilirubin levels. Newborn infants that experience jaundice, the yellowing of the skin and eyes, have a buildup of bilirubin, a chemical that occurs during red blood cell breakdown, or hemolysis. Exchange transfusion is a therapy developed throughout the 1940s by Louis Diamond and a group of surgeons at the Children’s Medical Center in Boston, Massachusetts. During exchange transfusion, a physician inserts a plastic tube called a catheter through the umbilical vein of the infant to slowly remove infant blood and sequentially replace it with donor blood. Exchange transfusion was the first definitive treatment for hyperbilirubinemia in the US and it helped reduce the incidence of kernicterus, a type of brain damage caused by elevated bilirubin levels.
Neonatal jaundice is the yellow discoloration of the skin and eyes due to elevated bilirubin levels in the bloodstream of a newborn. Bilirubin is a byproduct of the breakdown of red blood cells. Jaundiced infants are unable to process bilirubin at a normal rate or they have an abnormally high amount of bilirubin in their bloodstream, resulting in a buildup of the yellow colored bilirubin. That build up is called hyperbilirubinemia and is the cause of jaundice. Jaundice can lead to kernicterus, a rare neurological disorder that results in hearing loss, permanent brain damage, and sometimes death. Research into the causes of jaundice and kernicterus began in the late eighteenth century in Paris, France. By the middle of the twentieth century, scientists developed treatments for jaundice that successfully treated infants afflicted with the condition, phototherapy and blood exchange transfusion, due to these treatments, the risk for an infant in developing kernicterus is very low.
In 1968, pediatric researchers Jerold Lucey, Mario Ferreiro, and Jean Hewitt conducted an experimental trial that determined that exposure to light effectively treated jaundice in premature infants. The three researchers published their results in 'Prevention of Hyperbilirubinemia of Prematurity by Phototherapy' that same year in Pediatrics. Jaundice is the yellowing of the skin and eyes due to the failure of the liver to break down excess bilirubin in the blood, a condition called hyperbilirubinemia. Bilirubin is a product that results from the degradation of red blood cells, which the immature liver of premature infants often has difficulty breaking down. Lucey's group's study demonstrated both the efficacy of phototherapy, which uses light to breakdown the bilirubin in the blood, as treatment for hyperbilirubinemia. As a result of Lucey's research team's study, physicians adopted phototherapy as the standard of care for treating premature infants born with jaundice.
Light therapy, also called phototherapy, exposes infants with jaundice, a yellowing of the skin and eyes, to artificial or natural light to break down the buildup of bilirubin pigment in the blood. Bilirubin is an orange to red pigment produced when red blood cells break down, which causes infants to turn into a yellowish color. Small amounts of bilirubin in the blood are normal, but when there is an accumulation of excess bilirubin pigment, the body deposits the excess bilirubin in the layer of fat beneath the skin. That accumulation of bilirubin causes the skin and the white areas of the eye to appear yellowed, a common symptom of jaundice. Buildup of bilirubin typically occurs when the immature liver of a newborn infant is unable to efficiently breakdown the bilirubin molecule into products that the body can excrete. High levels of bilirubin, a phenomenon called hyperbilirubinemia can be toxic and can lead to a brain dysfunction called kernicterus, which may result in permanent brain damage. The relative simplicity of phototherapy treatment has made effective neonatal jaundice treatment nearly universal, almost completely eliminating the risk of infant brain damage from hyperbilirubinemia.
Jerold Lucey studied newborn infants in the United States in the twentieth century. In the 1960s and 1970s, Lucey studied phototherapy as a treatment for jaundice, a condition in infants whose livers cannot excrete broken down red blood cells, called bilirubin, into the bloodstream at a fast enough rate. In addition to his work in jaundice, Lucey was the editor in chief for the journal Pediatrics of the American Academy of Pediatrics. Lucey helped establish standards of care for several neonatal conditions, including neonatal jaundice and infant respiratory distress disorder (also called hyaline membrane disorder).