Matching Items (3)
Filtering by
- Genre: Masters Thesis
- Status: Published
Description
Continuous advancements in biomedical research have resulted in the production of vast amounts of scientific data and literature discussing them. The ultimate goal of computational biology is to translate these large amounts of data into actual knowledge of the complex biological processes and accurate life science models. The ability to rapidly and effectively survey the literature is necessary for the creation of large scale models of the relationships among biomedical entities as well as hypothesis generation to guide biomedical research. To reduce the effort and time spent in performing these activities, an intelligent search system is required. Even though many systems aid in navigating through this wide collection of documents, the vastness and depth of this information overload can be overwhelming. An automated extraction system coupled with a cognitive search and navigation service over these document collections would not only save time and effort, but also facilitate discovery of the unknown information implicitly conveyed in the texts. This thesis presents the different approaches used for large scale biomedical named entity recognition, and the challenges faced in each. It also proposes BioEve: an integrative framework to fuse a faceted search with information extraction to provide a search service that addresses the user's desire for "completeness" of the query results, not just the top-ranked ones. This information extraction system enables discovery of important semantic relationships between entities such as genes, diseases, drugs, and cell lines and events from biomedical text on MEDLINE, which is the largest publicly available database of the world's biomedical journal literature. It is an innovative search and discovery service that makes it easier to search
avigate and discover knowledge hidden in life sciences literature. To demonstrate the utility of this system, this thesis also details a prototype enterprise quality search and discovery service that helps researchers with a guided step-by-step query refinement, by suggesting concepts enriched in intermediate results, and thereby facilitating the "discover more as you search" paradigm.
avigate and discover knowledge hidden in life sciences literature. To demonstrate the utility of this system, this thesis also details a prototype enterprise quality search and discovery service that helps researchers with a guided step-by-step query refinement, by suggesting concepts enriched in intermediate results, and thereby facilitating the "discover more as you search" paradigm.
ContributorsKanwar, Pradeep (Author) / Davulcu, Hasan (Thesis advisor) / Dinu, Valentin (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2010
Description
Traditional Reinforcement Learning (RL) assumes to learn policies with respect to reward available from the environment but sometimes learning in a complex domain requires wisdom which comes from a wide range of experience. In behavior based robotics, it is observed that a complex behavior can be described by a combination of simpler behaviors. It is tempting to apply similar idea such that simpler behaviors can be combined in a meaningful way to tailor the complex combination. Such an approach would enable faster learning and modular design of behaviors. Complex behaviors can be combined with other behaviors to create even more advanced behaviors resulting in a rich set of possibilities. Similar to RL, combined behavior can keep evolving by interacting with the environment. The requirement of this method is to specify a reasonable set of simple behaviors. In this research, I present an algorithm that aims at combining behavior such that the resulting behavior has characteristics of each individual behavior. This approach has been inspired by behavior based robotics, such as the subsumption architecture and motor schema-based design. The combination algorithm outputs n weights to combine behaviors linearly. The weights are state dependent and change dynamically at every step in an episode. This idea is tested on discrete and continuous environments like OpenAI’s “Lunar Lander” and “Biped Walker”. Results are compared with related domains like Multi-objective RL, Hierarchical RL, Transfer learning, and basic RL. It is observed that the combination of behaviors is a novel way of learning which helps the agent achieve required characteristics. A combination is learned for a given state and so the agent is able to learn faster in an efficient manner compared to other similar approaches. Agent beautifully demonstrates characteristics of multiple behaviors which helps the agent to learn and adapt to the environment. Future directions are also suggested as possible extensions to this research.
ContributorsVora, Kevin Jatin (Author) / Zhang, Yu (Thesis advisor) / Yang, Yezhou (Committee member) / Praharaj, Sarbeswar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Vitamin D is a nutrient that is obtained through the diet and vitamin D supplementation and created from exposure to Ultraviolet B (UVB) radiation. While there are many factors that determine how much serum 25-hydroxyvitamin D (25(OH)D) concentration is in the body, little is known about how genetic variation in vitamin D-related genes influences serum 25(OH)D concentrations resulting from daily vitamin D intake and exposure to direct sunlight. Previous studies show that common genetic variants rs10741657 (CYP2R1), rs4588 (GC), rs228678 (GC), and rs4516035 (VDR) act as moderators and alter the effect of outdoor time and vitamin D intake on serum 25(OH)D concentrations. The objective of this study is to analyze the associations between serum 25(OH)D concentrations resulting from outdoor time and vitamin D intake, and genetic risk scores (GRS) established from previous studies involving single nucleotide polymorphisms (SNP) located on or near genes involving vitamin D synthesis, transport, activation, and degradation in 102 Hispanic and Non-Hispanic adults in the San Diego County, California. This study is a secondary analysis of data from the Community of Mine study. Global Positioning System (GPS) data collected by the Qstarz GPS device worn by each participant was used to measure outdoor time, a proxy measurement for sun exposure time. Vitamin D intake was assessed using two 24-hour dietary recalls. Blood samples were measured for serum 25(OH)D concentrations. DNA was provided to assess each participant for the various genetic variants. Adjusted analyses of the GRS and serum 25(OH)D concentrations showed that individuals with high GRS (3-4) had lower serum 25(OH)D concentrations than individuals with low GRS (0-2) for both Nissen GRS and Rivera-Paredez GRS.
ContributorsAnderson, Heather Ray (Author) / Sears, Dorothy (Thesis advisor) / Alexon, Christy (Committee member) / Dinu, Valentin (Committee member) / Jankowska, Marta (Committee member) / Arizona State University (Publisher)
Created2022