@phdthesis{Wolf2017,
  author    = {Wolf, Beat},
  title     = {Reducing the complexity of OMICS data analysis},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-153687},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2017},
  abstract  = {The field of genetics faces a lot of challenges and opportunities in both research and diagnostics due to the rise of next generation sequencing (NGS), a technology that allows to sequence DNA increasingly fast and cheap. NGS is not only used to analyze DNA, but also RNA, which is a very similar molecule also present in the cell, in both cases producing large amounts of data. The big amount of data raises both infrastructure and usability problems, as powerful computing infrastructures are required and there are many manual steps in the data analysis which are complicated to execute. Both of those problems limit the use of NGS in the clinic and research, by producing a bottleneck both computationally and in terms of manpower, as for many analyses geneticists lack the required computing skills. Over the course of this thesis we investigated how computer science can help to improve this situation to reduce the complexity of this type of analysis. We looked at how to make the analysis more accessible to increase the number of people that can perform OMICS data analysis (OMICS groups various genomics data-sources). To approach this problem, we developed a graphical NGS data analysis pipeline aimed at a diagnostics environment while still being useful in research in close collaboration with the Human Genetics Department at the University of W{\"u}rzburg. The pipeline has been used in various research papers on covering subjects, including works with direct author participation in genomics, transcriptomics as well as epigenomics. To further validate the graphical pipeline, a user survey was carried out which confirmed that it lowers the complexity of OMICS data analysis. We also studied how the data analysis can be improved in terms of computing infrastructure by improving the performance of certain analysis steps. We did this both in terms of speed improvements on a single computer (with notably variant calling being faster by up to 18 times), as well as with distributed computing to better use an existing infrastructure. The improvements were integrated into the previously described graphical pipeline, which itself also was focused on low resource usage. As a major contribution and to help with future development of parallel and distributed applications, for the usage in genetics or otherwise, we also looked at how to make it easier to develop such applications. Based on the parallel object programming model (POP), we created a Java language extension called POP-Java, which allows for easy and transparent distribution of objects. Through this development, we brought the POP model to the cloud, Hadoop clusters and present a new collaborative distributed computing model called FriendComputing. The advances made in the different domains of this thesis have been published in various works specified in this document.},
  subject      = {Bioinformatik},
  language  = {en}
}