@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab134},
  pages     = {17},
  year      = {2021},
  abstract  = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.},
  language  = {en}
}
@article{KaitouaRablMarkl2020,
  author    = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker},
  title     = {A distributed data exchange engine for polystores},
  series = {Information technology : methods and applications of informatics and information technology},
  volume    = {62},
  journal   = {Information technology : methods and applications of informatics and information technology},
  number    = {3-4},
  publisher = {De Gruyter},
  address   = {Berlin},
  issn      = {1611-2776},
  doi       = {10.1515/itit-2019-0037},
  pages     = {145 -- 156},
  year      = {2020},
  abstract  = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.},
  language  = {en}
}
@misc{SukmanaTorkuraChengetal.2018,
  author    = {Sukmana, Muhammad Ihsan Haikal and Torkura, Kennedy A. and Cheng, Feng and Meinel, Christoph and Graupner, Hendrik},
  title     = {Unified logging system for monitoring multiple cloud storage providers in cloud storage broker},
  series = {32ND International Conference on Information Networking (ICOIN)},
  journal   = {32ND International Conference on Information Networking (ICOIN)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-2290-2},
  doi       = {10.1109/ICOIN.2018.8343081},
  pages     = {44 -- 49},
  year      = {2018},
  abstract  = {With the increasing demand for personal and enterprise data storage service, Cloud Storage Broker (CSB) provides cloud storage service using multiple Cloud Service Providers (CSPs) with guaranteed Quality of Service (QoS), such as data availability and security. However monitoring cloud storage usage in multiple CSPs has become a challenge for CSB due to lack of standardized logging format for cloud services that causes each CSP to implement its own format. In this paper we propose a unified logging system that can be used by CSB to monitor cloud storage usage across multiple CSPs. We gather cloud storage log files from three different CSPs and normalise these into our proposed log format that can be used for further analysis process. We show that our work enables a coherent view suitable for data navigation, monitoring, and analytics.},
  language  = {en}
}
@article{PaascheEberle2011,
  author    = {Paasche, Hendrik and Eberle, Detlef},
  title     = {Automated compilation of pseudo-lithology maps from geophysical data sets a comparison of Gustafson-Kessel and fuzzy c-means cluster algorithms},
  series = {Exploration geophysics : the bulletin of the Australian Society of Exploration Geophysicists},
  volume    = {42},
  journal   = {Exploration geophysics : the bulletin of the Australian Society of Exploration Geophysicists},
  number    = {4},
  publisher = {CSIRO},
  address   = {Collingwood},
  issn      = {0812-3985},
  doi       = {10.1071/EG11014},
  pages     = {275 -- 285},
  year      = {2011},
  abstract  = {The fuzzy partitioning Gustafson-Kessel cluster algorithm is employed for rapid and objective integration of multi-parameter Earth-science related databases. We begin by evaluating the Gustafson-Kessel algorithm using the example of a synthetic study and compare the results to those obtained from the more widely employed fuzzy c-means algorithm. Since the Gustafson-Kessel algorithm goes beyond the potential of the fuzzy c-means algorithm by adapting the shape of the clusters to be detected and enabling a manual control of the cluster volume, we believe the results obtained from Gustafson-Kessel algorithm to be superior. Accordingly, a field database comprising airborne and ground-based geophysical data sets is analysed, which has previously been classified by means of the fuzzy c-means algorithm. This database is integrated using the Gustafson-Kessel algorithm thus minimising the amount of empirical data processing required before and after fuzzy c-means clustering. The resultant zonal geophysical map is more evenly clustered matching regional geology information available from the survey area. Even additional information about linear structures, e. g. as typically caused by the presence of dolerite dykes or faults, is visible in the zonal map obtained from Gustafson-Kessel cluster analysis.},
  language  = {en}
}