@phdthesis{GonzalezDuran2023,
  author    = {Gonzalez Duran, Enrique},
  title     = {Genetic control of intracellular gene transfer by DNA repair in N. tabacum},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XII, 127, XLI},
  year      = {2023},
  abstract  = {Mitochondria and plastids are organelles with an endosymbiotic origin. During evolution, many genes are lost from the organellar genomes and get integrated in the nuclear genome, in what is known as intracellular/endosymbiotic gene transfer (IGT/EGT). IGT has been reproduced experimentally in Nicotiana tabacum at a gene transfer rate (GTR) of 1 event in 5 million cells, but, despite its centrality to eukaryotic evolution, there are no genetic factors known to influence the frequency of IGT in higher eukaryotes. The focus of this work was to determine the role of different DNA repair pathways of double strand break repair (DSBR) in the integration step of organellar DNA in the nuclear genome during IGT. Here, a CRISPR/Cas9 mutagenesis strategy was implemented in N. tabacum, with the aim of generating mutants in nuclear genes without expected visible phenotypes. This strategy led to the generation of a collection of independent mutants in the LIG4 (necessary for non-homologous end joining, NHEJ) and POLQ genes (necessary for microhomology mediated end joining, MMEJ). Targeting of other DSBR genes (KU70, KU80, RPA1C) generated mutants with unexpectedly strong developmental phenotypes.. These factors have telomeric roles, hinting towards a possible relationship between telomere length, and strength of developmental disruption upon loss of telomere structure in plants. The mutants were made in a genetic background encoding a plastid-encoded IGT reporter, that confers kanamycin resistance upon transfer to the nucleus. Through large scale independent experiments, increased IGT from the chloroplast to the nucleus was observed in lig4 mutants, as well as lines encoding a POLQ gene with a defective polymerase domain (polqΔPol). This shows that NHEJ or MMEJ have a double-sided relationship with IGT: while transferred genes may integrate using either pathway, the presence of both pathways suppresses IGT in wild-type somatic cells, thus demonstrating for the first time the extent on which nuclear genes control IGT frequency in plants. The IGT frequency increases in the mutants are likely mediated by increased availability of double strand breaks for integration. Additionally, kinetic analysis reveals that gene transfer (GT) events accumulate linearly as a function of time spent under antibiotic selection in the experiment, demonstrating that, contrary to what was previously thought, there is no such thing as a single GTR in somatic IGT experiments. Furthermore, IGT in tissue culture experiments appears to be the result of a "race against the clock" for integration in the nuclear genome, that starts when the organellar DNA arrives to the nucleus granting transient antibiotic resistance. GT events and escapes of kanamycin selection may be two possible outcomes from this race: those instances where the organellar DNA gets to integrate are recovered as GT events, and in those cases where timely integration fails, antibiotic resistance cannot be sustained, and end up considered as escapes. In the mutants, increased opportunities for integration in the nuclear genome change the overall ratio between IGT and escape events. The resources generated here are promising starting points for future research: (1) the mutant collection, for the further study of processes that depend on DNA repair in plants (2) the collection of GT lines obtained from these experiments, for the study of the effect of DSBR pathways over integration patterns and stability of transferred genes and (3) the developed CRISPR/Cas9 workflow for mutant generation, to make N. tabacum meet its potential as an attractive model for answering complex biological questions.},
  language  = {en}
}
@phdthesis{Thiele2011,
  author    = {Thiele, Sven},
  title     = {Modeling biological systems with Answer Set Programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-59383},
  school      = {Universit{\"a}t Potsdam},
  year      = {2011},
  abstract  = {Biology has made great progress in identifying and measuring the building blocks of life. The availability of high-throughput methods in molecular biology has dramatically accelerated the growth of biological knowledge for various organisms. The advancements in genomic, proteomic and metabolomic technologies allow for constructing complex models of biological systems. An increasing number of biological repositories is available on the web, incorporating thousands of biochemical reactions and genetic regulations. Systems Biology is a recent research trend in life science, which fosters a systemic view on biology. In Systems Biology one is interested in integrating the knowledge from all these different sources into models that capture the interaction of these entities. By studying these models one wants to understand the emerging properties of the whole system, such as robustness. However, both measurements as well as biological networks are prone to considerable incompleteness, heterogeneity and mutual inconsistency, which makes it highly non-trivial to draw biologically meaningful conclusions in an automated way. Therefore, we want to promote Answer Set Programming (ASP) as a tool for discrete modeling in Systems Biology. ASP is a declarative problem solving paradigm, in which a problem is encoded as a logic program such that its answer sets represent solutions to the problem. ASP has intrinsic features to cope with incompleteness, offers a rich modeling language and highly efficient solving technology. We present ASP solutions, for the analysis of genetic regulatory networks, determining consistency with observed measurements and identifying minimal causes for inconsistency. We extend this approach for computing minimal repairs on model and data that restore consistency. This method allows for predicting unobserved data even in case of inconsistency. Further, we present an ASP approach to metabolic network expansion. This approach exploits the easy characterization of reachability in ASP and its various reasoning methods, to explore the biosynthetic capabilities of metabolic reaction networks and generate hypotheses for extending the network. Finally, we present the BioASP library, a Python library which encapsulates our ASP solutions into the imperative programming paradigm. The library allows for an easy integration of ASP solution into system rich environments, as they exist in Systems Biology.},
  language  = {en}
}