@phdthesis{Childs2010,
  author    = {Childs, Liam H.},
  title     = {Bioinformatics approaches to analysing RNA mediated regulation of gene expression},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41284},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {The genome can be considered the blueprint for an organism. Composed of DNA, it harbours all organism-specific instructions for the synthesis of all structural components and their associated functions. The role of carriers of actual molecular structure and functions was believed to be exclusively assumed by proteins encoded in particular segments of the genome, the genes. In the process of converting the information stored genes into functional proteins, RNA - a third major molecule class - was discovered early on to act a messenger by copying the genomic information and relaying it to the protein-synthesizing machinery. Furthermore, RNA molecules were identified to assist in the assembly of amino acids into native proteins. For a long time, these - rather passive - roles were thought to be the sole purpose of RNA. However, in recent years, new discoveries have led to a radical revision of this view. First, RNA molecules with catalytic functions - thought to be the exclusive domain of proteins - were discovered. Then, scientists realized that much more of the genomic sequence is transcribed into RNA molecules than there are proteins in cells begging the question what the function of all these molecules are. Furthermore, very short and altogether new types of RNA molecules seemingly playing a critical role in orchestrating cellular processes were discovered. Thus, RNA has become a central research topic in molecular biology, even to the extent that some researcher dub cells as "RNA machines". This thesis aims to contribute towards our understanding of RNA-related phenomena by applying Bioinformatics means. First, we performed a genome-wide screen to identify sites at which the chemical composition of DNA (the genotype) critically influences phenotypic traits (the phenotype) of the model plant Arabidopsis thaliana. Whole genome hybridisation arrays were used and an informatics strategy developed, to identify polymorphic sites from hybridisation to genomic DNA. Following this approach, not only were genotype-phenotype associations discovered across the entire Arabidopsis genome, but also regions not currently known to encode proteins, thus representing candidate sites for novel RNA functional molecules. By statistically associating them with phenotypic traits, clues as to their particular functions were obtained. Furthermore, these candidate regions were subjected to a novel RNA-function classification prediction method developed as part of this thesis. While determining the chemical structure (the sequence) of candidate RNA molecules is relatively straightforward, the elucidation of its structure-function relationship is much more challenging. Towards this end, we devised and implemented a novel algorithmic approach to predict the structural and, thereby, functional class of RNA molecules. In this algorithm, the concept of treating RNA molecule structures as graphs was introduced. We demonstrate that this abstraction of the actual structure leads to meaningful results that may greatly assist in the characterization of novel RNA molecules. Furthermore, by using graph-theoretic properties as descriptors of structure, we indentified particular structural features of RNA molecules that may determine their function, thus providing new insights into the structure-function relationships of RNA. The method (termed Grapple) has been made available to the scientific community as a web-based service. RNA has taken centre stage in molecular biology research and novel discoveries can be expected to further solidify the central role of RNA in the origin and support of life on earth. As illustrated by this thesis, Bioinformatics methods will continue to play an essential role in these discoveries.},
  language  = {en}
}
@misc{RazaghiMoghadamNikoloski2020,
  author    = {Razaghi-Moghadam, Zahra and Nikoloski, Zoran},
  title     = {Supervised learning of gene regulatory networks},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-51656},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-516561},
  pages     = {9},
  year      = {2020},
  abstract  = {Identifying the entirety of gene regulatory interactions in a biological system offers the possibility to determine the key molecular factors that affect important traits on the level of cells, tissues, and whole organisms. Despite the development of experimental approaches and technologies for identification of direct binding of transcription factors (TFs) to promoter regions of downstream target genes, computational approaches that utilize large compendia of transcriptomics data are still the predominant methods used to predict direct downstream targets of TFs, and thus reconstruct genome-wide gene-regulatory networks (GRNs). These approaches can broadly be categorized into unsupervised and supervised, based on whether data about known, experimentally verified gene-regulatory interactions are used in the process of reconstructing the underlying GRN. Here, we first describe the generic steps of supervised approaches for GRN reconstruction, since they have been recently shown to result in improved accuracy of the resulting networks? We also illustrate how they can be used with data from model organisms to obtain more accurate prediction of gene regulatory interactions.},
  language  = {en}
}
@misc{SeleemAyzelCostaTomazdeSouzaetal.2022,
  author    = {Seleem, Omar and Ayzel, Georgy and Costa Tomaz de Souza, Arthur and Bronstert, Axel and Heistermann, Maik},
  title     = {Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1297},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-57680},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-576806},
  pages     = {1640 -- 1662},
  year      = {2022},
  abstract  = {Identifying urban pluvial flood-prone areas is necessary but the application of two-dimensional hydrodynamic models is limited to small areas. Data-driven models have been showing their ability to map flood susceptibility but their application in urban pluvial flooding is still rare. A flood inventory (4333 flooded locations) and 11 factors which potentially indicate an increased hazard for pluvial flooding were used to implement convolutional neural network (CNN), artificial neural network (ANN), random forest (RF) and support vector machine (SVM) to: (1) Map flood susceptibility in Berlin at 30, 10, 5, and 2 m spatial resolutions. (2) Evaluate the trained models' transferability in space. (3) Estimate the most useful factors for flood susceptibility mapping. The models' performance was validated using the Kappa, and the area under the receiver operating characteristic curve (AUC). The results indicated that all models perform very well (minimum AUC = 0.87 for the testing dataset). The RF models outperformed all other models at all spatial resolutions and the RF model at 2 m spatial resolution was superior for the present flood inventory and predictor variables. The majority of the models had a moderate performance for predictions outside the training area based on Kappa evaluation (minimum AUC = 0.8). Aspect and altitude were the most influencing factors on the image-based and point-based models respectively. Data-driven models can be a reliable tool for urban pluvial flood susceptibility mapping wherever a reliable flood inventory is available.},
  language  = {en}
}