Matching Items (5)
Filtering by
- All Subjects: Antibodies
- All Subjects: Machine Learning
- Status: Published
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This project aims to address the current protocol regarding the diagnosis and treatment of traumatic brain injury (TBI) in medical industries around the world. Although there are various methods used to qualitatively determine if TBI has occurred to a patient, this study attempts to aid in the creation of a system for quantitative measurement of TBI and its relative magnitude. Through a method of artificial evolution/selection called phage display, an antibody that binds highly specifically to a post-TBI upregulated brain chondroitin sulfate proteoglycan called neurocan has been identified. As TG1 Escheria Coli bacteria were infected with KM13 helper phage and M13 filamentous phage in conjunction, monovalent display of antibody fragments (ScFv) was performed. The ScFv bind directly to the neurocan and from screening, phage that produced ScFv's with higher affinity and specificity to neurocan were separated and purified. Future research aims to improve the ScFv characteristics through increased screening toward neurocan. The identification of a highly specific antibody could lead to improved targeting of neurocan post-TBI in-vivo, aiding researchers in quantitatively defining TBI by visualizing its magnitude.
ContributorsSeelig, Timothy Scott (Author) / Stabenfeldt, Sarah (Thesis director) / Ankeny, Casey (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor)
Created2015-05
Description
A chimeric, humanized monoclonal antibody that recognizes a highly conserved fusion loop found on flaviviruses was constructed with a geminiviral replicon and transiently expressed in Nicotiana benthamiana plants through Agrobacterium tumefaciens infiltration. Characterization and expression studies were then conducted to confirm correct assembly of the antibody. Once the antibody was purified, an ELISA was conducted to validate that the antibody was able to bind to the flavivirus fusion loop.
ContributorsPardhe, Mary (Author) / Mason, Hugh (Thesis director) / Chen, Qiang (Committee member) / Mor, Tsafrir (Committee member) / School of Life Sciences (Contributor) / Department of Information Systems (Contributor) / W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Monoclonal antibody therapy focuses on engineering immune cells to target specific peptide sequences indicative of disease. An impediment in the continued advancement of this market is the lack of an efficient, inexpensive means of characterization that can be broadly applied to any antibody while still providing high-density data. Many characterization methods address an antibody's affinity for its cognate sequence but overlook other important aspects of binding behavior such as off-target binding interactions. The purpose of this study is to demonstrate how the binding intensity between an antibody and a library of random-sequence peptides, otherwise known as an immunosignature, can be evaluated to determine antibody specificity and polyreactivity. A total of 24 commercially available monoclonal antibodies were assayed on 125K and 330K peptide microarrays and analyzed using a motif clustering program to predict candidate epitopes within each antigen sequence. The results support the further development of immunosignaturing as an antibody characterization tool that is relevant to both therapeutic and non-therapeutic antibodies.
ContributorsDai, Jennifer T. (Author) / Stafford, Phillip (Thesis director) / Diehnelt, Chris (Committee member) / School of Life Sciences (Contributor) / W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Abstract: The Ultimate Fighting Championship or UFC as it is commonly known, was founded in 1993 and has quickly built itself into the world's foremost authority on all things MMA (mixed martial arts) related. With pay-per-view and cable television deals in hand, the UFC has become a huge competitor in the sports market, rivaling the popularity of boxing for almost a decade. As with most other sports, the UFC has seen an influx of various analytics and data science over the past five to seven years. We see this revolution in football with the broadcast first down markers, basketball with tracking player movement, and baseball with locating pitches for strikes and balls, and now the UFC has partnered with statistics company Fightmetric, to provide in-depth statistical analysis of its fights. ESPN has their win probability metrics, and statistical predictive modeling has begun to spread throughout sports. All these stats were made to showcase the information about a fighter that one wouldn't typically know, giving insight into how the fight might go. But, can these fights be predicted? Based off of the research of prior individuals and combining the thought processes of relevant research into other sports leagues, I sought to use the arsenal of statistical analyses done by Fightmetric, along with the official UFC fighter database to answer the question of whether UFC fights could be predicted. Specifically, by using only data that would be known about a fighter prior to stepping into the cage, could I predict with any degree of certainty who was going to win the fight?
ContributorsMoorman, Taylor D. (Author) / Simon, Alan (Thesis director) / Simon, Phil (Committee member) / W.P. Carey School of Business (Contributor) / Department of Information Systems (Contributor) / Department of Management and Entrepreneurship (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05