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.
Every year, nearly 1.5 shelter animals are euthanized.(1) By the end of 2020, California was reported to be responsible for the second most dog euthanasia’s in the United States, behind Texas by nearly 15,000 dogs. Sadly, these numbers do not include the euthanizing of cats which is generally a fraction larger. Additionally, a majority of numbers tallied by euthanasia centers do not include animals that younger than 1 month old and under 2 pounds. These animals are referred to as “neonate,” which is essentially unsavable newborns. In fact, the New York Times writes, “Many of the shelters do not track outcomes uniformly or make historical data readily available online. Until recently, there has not been a concerted national effort to standardize and compile shelter records.”(2) If these numbers were to be included, we would see a large spike for shelter euthanasia’s in every state. <br/>Traveling Paws is a 501(c)3 Nonprofit Organization that was created to help reduce the number of shelter and stray animals euthanized in California. Our mission is to rehome animals from dangerous environments and kill shelters into their “forever homes,” or shelter facilities where they then can further be adopted and live out the rest of their lives happily. In addition to animal relocation, our team has begun programs such as sheltering, fostering, and put an emphasis on a trap, neuter, and return program to help increase the health and safety, while reducing reproduction rates of stray cats in the Southern California region. While we have been able to substantially help animals located in areas of Southern California, our work is nowhere near complete. <br/>Through this write up, I will tell you the story of my journey, creating and managing our nonprofit organization, along with our successes, problems faced, business plans to help guide us toward our future goals and success, and what I have learned throughout the process.
Every year, nearly 1.5 shelter animals are euthanized.(1) By the end of 2020, California was reported to be responsible for the second most dog euthanasia’s in the United States, behind Texas by nearly 15,000 dogs. Sadly, these numbers do not include the euthanizing of cats which is generally a fraction larger. Additionally, a majority of numbers tallied by euthanasia centers do not include animals that younger than 1 month old and under 2 pounds. These animals are referred to as “neonate,” which is essentially unsavable newborns. In fact, the New York Times writes, “Many of the shelters do not track outcomes uniformly or make historical data readily available online. Until recently, there has not been a concerted national effort to standardize and compile shelter records.”(2) If these numbers were to be included, we would see a large spike for shelter euthanasia’s in every state. <br/>Traveling Paws is a 501(c)3 Nonprofit Organization that was created to help reduce the number of shelter and stray animals euthanized in California. Our mission is to rehome animals from dangerous environments and kill shelters into their “forever homes,” or shelter facilities where they then can further be adopted and live out the rest of their lives happily. In addition to animal relocation, our team has begun programs such as sheltering, fostering, and put an emphasis on a trap, neuter, and return program to help increase the health and safety, while reducing reproduction rates of stray cats in the Southern California region. While we have been able to substantially help animals located in areas of Southern California, our work is nowhere near complete. <br/>Through this write up, I will tell you the story of my journey, creating and managing our nonprofit organization, along with our successes, problems faced, business plans to help guide us toward our future goals and success, and what I have learned throughout the process.
In the early years of the National Football League, scouting and roster development resembled the wild west. Drafts were held in hotel ballrooms the day after the last game of regular season college football was played. There was no combine, limited scouting, and no salary cap. Over time, these aspects have changed dramatically, in part due to key figures from Pete Rozelle to Gil Brandt to Bill Belichick. The development and learning from this time period have laid the foundational infrastructure that modern roster construction is based upon. In this modern day, managing a team and putting together a roster involves numerous people, intense scouting, layers of technology, and, critically, the management of the salary cap. Since it was first put into place in 1994, managing the cap has become an essential element of building and sustaining a successful team. The New England Patriots’ mastery of the cap is a large part of what enabled their dynastic run over the past twenty years. While their model has undoubtedly proven to be successful, an opposing model has become increasingly popular and yielded results of its own. Both models center around different distributions of the salary cap, starting with the portion paid to the starting quarterback. The Patriots dynasty was, in part, made possible due to their use of both models over the course of their dominance. Drafting, organizational culture, and coaching are all among the numerous critical factors in determining a team’s success and it becomes difficult to pinpoint the true source of success for any given team. Ultimately, however, effective management of the cap proves to be a force multiplier; it does not guarantee that a team will be successful, but it helps teams that handle the other variables well sustain their success.
The retail department store industry has been in decline for years. Online shopping has become increasingly popular, and this was happening even before the pandemic. Department stores made the mistake years ago of focusing on expansion instead of improving their presence online. In this paper, I make recommendations to help retail department stores make more sales online, as well as get more shoppers back in their brick-and-mortar locations. There needs to be a new target customer that is much younger than the previous. Department stores need put money and time into building their social media platforms. These stores should be looking for several e-commerce brands to incorporate into their stores online, but more importantly in their brick-and-mortar locations. To grow bigger faster, department stores should start to consider using trusted third-party sellers like their biggest competitor Amazon does. Many younger people choose to shop from sustainable and socially responsible brands. Department stores should put in their best efforts to make sure they are caring about these things, not only to help make a change but to also increase their popularity among consumers. It is critical that large retail department stores use several influencers to promote their store and products among all forms of social media. This has become one of the most inexpensive and effective ways to increase sales. Finally, department stores should consider trying livestream shopping as a way to connect with their customers and sell more product. I have covered several ways that department stores can start to expand their business and begin to grow again. I believe these recommendations can transform the retail department store into possible something even more successful than it was before.