@phdthesis{Yu2019,
  author    = {Yu, Sung-Huan},
  title     = {Development and application of computational tools for RNA-Seq based transcriptome annotations},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-176468},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {In order to understand the regulation of gene expression in organisms, precise genome annotation is essential. In recent years, RNA-Seq has become a potent method for generating and improving genome annotations. However, this Approach is time consuming and often inconsistently performed when done manually. In particular, the discovery of non-coding RNAs benefits strongly from the application of RNA-Seq data but requires significant amounts of expert knowledge and is labor-intensive. As a part of my doctoral study, I developed a modular tool called ANNOgesic that can detect numerous transcribed genomic features, including non-coding RNAs, based on RNA-Seq data in a precise and automatic fashion with a focus on bacterial and achaeal species. The software performs numerous analyses and generates several visualizations. It can generate annotations of high-Resolution that are hard to produce using traditional annotation tools that are based only on genome sequences. ANNOgesic can detect numerous novel genomic Features like UTR-derived small non-coding RNAs for which no other tool has been developed before. ANNOgesic is available under an open source license (ISCL) at https://github.com/Sung-Huan/ANNOgesic. My doctoral work not only includes the development of ANNOgesic but also its application to annotate the transcriptome of Staphylococcus aureus HG003 - a strain which has been a insightful model in infection biology. Despite its potential as a model, a complete genome sequence and annotations have been lacking for HG003. In order to fill this gap, the annotations of this strain, including sRNAs and their functions, were generated using ANNOgesic by analyzing differential RNA-Seq data from 14 different samples (two media conditions with seven time points), as well as RNA-Seq data generated after transcript fragmentation. ANNOgesic was also applied to annotate several bacterial and archaeal genomes, and as part of this its high performance was demonstrated. In summary, ANNOgesic is a powerful computational tool for RNA-Seq based annotations and has been successfully applied to several species.},
  subject      = {Genom},
  language  = {en}
}
@phdthesis{PradaSalcedo2018,
  author    = {Prada Salcedo, Juan Pablo},
  title     = {Image Processing and other bioinformatic tools for Neurobiology},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-157721},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2018},
  abstract  = {Neurobiology is widely supported by bioinformatics. Due to the big amount of data generated from the biological side a computational approach is required. This thesis presents four different cases of bioinformatic tools applied to the service of Neurobiology. The first two tools presented belong to the field of image processing. In the first case, we make use of an algorithm based on the wavelet transformation to assess calcium activity events in cultured neurons. We designed an open source tool to assist neurobiology researchers in the analysis of calcium imaging videos. Such analysis is usually done manually which is time consuming and highly subjective. Our tool speeds up the work and offers the possibility of an unbiased detection of the calcium events. Even more important is that our algorithm not only detects the neuron spiking activity but also local spontaneous activity which is normally discarded because it is considered irrelevant. We showed that this activity is determinant in the calcium dynamics in neurons and it is involved in important functions like signal modulation and memory and learning. The second project is a segmentation task. In our case we are interested in segmenting the neuron nuclei in electron microscopy images of c.elegans. Marking these structures is necessary in order to reconstruct the connectome of the organism. C.elegans is a great study case due to the simplicity of its nervous system (only 502 neurons). This worm, despite its simplicity has taught us a lot about neuronal mechanisms. There is still a lot of information we can extract from the c.elegans, therein lies the importance of reconstructing its connectome. There is a current version of the c.elegans connectome but it was done by hand and on a single subject which leaves a big room for errors. By automatizing the segmentation of the electron microscopy images we guarantee an unbiased approach and we will be able to verify the connectome on several subjects. For the third project we moved from image processing applications to biological modeling. Because of the high complexity of even small biological systems it is necessary to analyze them with the help of computational tools. The term in silico was coined to refer to such computational models of biological systems. We designed an in silico model of the TNF (Tumor necrosis factor) ligand and its two principal receptors. This biological system is of high relevance because it is involved in the inflammation process. Inflammation is of most importance as protection mechanism but it can also lead to complicated diseases (e.g. cancer). Chronic inflammation processes can be particularly dangerous in the brain. In order to better understand the dynamics that govern the TNF system we created a model using the BioNetGen language. This is a rule based language that allows one to simulate systems where multiple agents are governed by a single rule. Using our model we characterized the TNF system and hypothesized about the relation of the ligand with each of the two receptors. Our hypotheses can be later used to define drug targets in the system or possible treatments for chronic inflammation or lack of the inflammatory response. The final project deals with the protein folding problem. In our organism proteins are folded all the time, because only in their folded conformation are proteins capable of doing their job (with some very few exceptions). This folding process presents a great challenge for science because it has been shown to be an NP problem. NP means non deterministic Polynomial time problem. This basically means that this kind of problems cannot be efficiently solved. Nevertheless, somehow the body is capable of folding a protein in just milliseconds. This phenomenon puzzles not only biologists but also mathematicians. In mathematics NP problems have been studied for a long time and it is known that given the solution to one NP problem we could solve many of them (i.e. NP-complete problems). If we manage to understand how nature solves the protein folding problem then we might be able to apply this solution to many other problems. Our research intends to contribute to this discussion. Unfortunately, not to explain how nature solves the protein folding problem, but to explain that it does not solve the problem at all. This seems contradictory since I just mentioned that the body folds proteins all the time, but our hypothesis is that the organisms have learned to solve a simplified version of the NP problem. Nature does not solve the protein folding problem in its full complexity. It simply solves a small instance of the problem. An instance which is as simple as a convex optimization problem. We formulate the protein folding problem as an optimization problem to illustrate our claim and present some toy examples to illustrate the formulation. If our hypothesis is true, it means that protein folding is a simple problem. So we just need to understand and model the conditions of the vicinity inside the cell at the moment the folding process occurs. Once we understand this starting conformation and its influence in the folding process we will be able to design treatments for amyloid diseases such as Alzheimer's and Parkinson's. In summary this thesis project contributes to the neurobiology research field from four different fronts. Two are practical contributions with immediate benefits, such as the calcium imaging video analysis tool and the TNF in silico model. The neuron nuclei segmentation is a contribution for the near future. A step towards the full annotation of the c.elegans connectome and later for the reconstruction of the connectome of other species. And finally, the protein folding project is a first impulse to change the way we conceive the protein folding process in nature. We try to point future research in a novel direction, where the amino code is not the most relevant characteristic of the process but the conditions within the cell.},
  subject      = {Bildverarbeitung},
  language  = {en}
}
@phdthesis{Beisser2011,
  author    = {Beisser, Daniela},
  title     = {Integrated functional analysis of biological networks},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-70150},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2011},
  abstract  = {In recent years high-throughput experiments provided a vast amount of data from all areas of molecular biology, including genomics, transcriptomics, proteomics and metabolomics. Its analysis using bioinformatics methods has developed accordingly, towards a systematic approach to understand how genes and their resulting proteins give rise to biological form and function. They interact with each other and with other molecules in highly complex structures, which are explored in network biology. The in-depth knowledge of genes and proteins obtained from high-throughput experiments can be complemented by the architecture of molecular networks to gain a deeper understanding of biological processes. This thesis provides methods and statistical analyses for the integration of molecular data into biological networks and the identification of functional modules, as well as its application to distinct biological data. The integrated network approach is implemented as a software package, termed BioNet, for the statistical language R. The package includes the statistics for the integration of transcriptomic and functional data with biological networks, the scoring of nodes and edges of these networks as well as methods for subnetwork search and visualisation. The exact algorithm is extensively tested in a simulation study and outperforms existing heuristic methods for the calculation of this NP-hard problem in accuracy and robustness. The variability of the resulting solutions is assessed on perturbed data, mimicking random or biased factors that obscure the biological signal, generated for the integrated data and the network. An optimal, robust module can be calculated using a consensus approach, based on a resampling method. It summarizes optimally an ensemble of solutions in a robust consensus module with the estimated variability indicated by confidence values for the nodes and edges. The approach is subsequently applied to two gene expression data sets. The first application analyses gene expression data for acute lymphoblastic leukaemia (ALL) and differences between the subgroups with and without an oncogenic BCR/ABL gene fusion. In a second application gene expression and survival data from diffuse large B-cell lymphomas are examined. The identified modules include and extend already existing gene lists and signatures by further significant genes and their interactions. The most important novelty is that these genes are determined and visualised in the context of their interactions as a functional module and not as a list of independent and unrelated transcripts. In a third application the integrative network approach is used to trace changes in tardigrade metabolism to identify pathways responsible for their extreme resistance to environmental changes and endurance in an inactive tun state. For the first time a metabolic network approach is proposed to detect shifts in metabolic pathways, integrating transcriptome and metabolite data. Concluding, the presented integrated network approach is an adequate technique to unite high-throughput experimental data for single molecules and their intermolecular dependencies. It is flexible to apply on diverse data, ranging from gene expression changes over metabolite abundances to protein modifications in a combination with a suitable molecular network. The exact algorithm is accurate and robust in comparison to heuristic approaches and delivers an optimal, robust solution in form of a consensus module with confidence values. By the integration of diverse sources of information and a simultaneous inspection of a molecular event from different points of view, new and exhaustive insights into biological processes can be acquired.},
  subject      = {Bioinformatik},
  language  = {en}
}