@misc{FichteTruszczynskiWoltran2015, author = {Fichte, Johannes Klaus and Truszczynski, Miroslaw and Woltran, Stefan}, title = {Dual-normal logic programs}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {585}, issn = {1866-8372}, doi = {10.25932/publishup-41449}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-414490}, pages = {16}, year = {2015}, abstract = {Disjunctive Answer Set Programming is a powerful declarative programming paradigm with complexity beyond NP. Identifying classes of programs for which the consistency problem is in NP is of interest from the theoretical standpoint and can potentially lead to improvements in the design of answer set programming solvers. One of such classes consists of dual-normal programs, where the number of positive body atoms in proper rules is at most one. Unlike other classes of programs, dual-normal programs have received little attention so far. In this paper we study this class. We relate dual-normal programs to propositional theories and to normal programs by presenting several inter-translations. With the translation from dual-normal to normal programs at hand, we introduce the novel class of body-cycle free programs, which are in many respects dual to head-cycle free programs. We establish the expressive power of dual-normal programs in terms of SE- and UE-models, and compare them to normal programs. We also discuss the complexity of deciding whether dual-normal programs are strongly and uniformly equivalent.}, language = {en} } @misc{ArvidssonKwasniewskiRianoPachonetal.2008, author = {Arvidsson, Samuel Janne and Kwasniewski, Miroslaw and Ria{\~n}o- Pach{\´o}n, Diego Mauricio and Mueller-Roeber, Bernd}, title = {QuantPrime}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {943}, issn = {1866-8372}, doi = {10.25932/publishup-43153}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-431531}, pages = {17}, year = {2008}, abstract = {Background Medium- to large-scale expression profiling using quantitative polymerase chain reaction (qPCR) assays are becoming increasingly important in genomics research. A major bottleneck in experiment preparation is the design of specific primer pairs, where researchers have to make several informed choices, often outside their area of expertise. Using currently available primer design tools, several interactive decisions have to be made, resulting in lengthy design processes with varying qualities of the assays. Results Here we present QuantPrime, an intuitive and user-friendly, fully automated tool for primer pair design in small- to large-scale qPCR analyses. QuantPrime can be used online through the internet http://www.quantprime.de/ or on a local computer after download; it offers design and specificity checking with highly customizable parameters and is ready to use with many publicly available transcriptomes of important higher eukaryotic model organisms and plant crops (currently 295 species in total), while benefiting from exon-intron border and alternative splice variant information in available genome annotations. Experimental results with the model plant Arabidopsis thaliana, the crop Hordeum vulgare and the model green alga Chlamydomonas reinhardtii show success rates of designed primer pairs exceeding 96\%. Conclusion QuantPrime constitutes a flexible, fully automated web application for reliable primer design for use in larger qPCR experiments, as proven by experimental data. The flexible framework is also open for simple use in other quantification applications, such as hydrolyzation probe design for qPCR and oligonucleotide probe design for quantitative in situ hybridization. Future suggestions made by users can be easily implemented, thus allowing QuantPrime to be developed into a broad-range platform for the design of RNA expression assays.}, language = {en} } @unpublished{PrasseGrubenMachlikaetal.2016, author = {Prasse, Paul and Gruben, Gerrit and Machlika, Lukas and Pevny, Tomas and Sofka, Michal and Scheffer, Tobias}, title = {Malware Detection by HTTPS Traffic Analysis}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-100942}, pages = {10}, year = {2016}, abstract = {In order to evade detection by network-traffic analysis, a growing proportion of malware uses the encrypted HTTPS protocol. We explore the problem of detecting malware on client computers based on HTTPS traffic analysis. In this setting, malware has to be detected based on the host IP address, ports, timestamp, and data volume information of TCP/IP packets that are sent and received by all the applications on the client. We develop a scalable protocol that allows us to collect network flows of known malicious and benign applications as training data and derive a malware-detection method based on a neural networks and sequence classification. We study the method's ability to detect known and new, unknown malware in a large-scale empirical study.}, language = {en} } @phdthesis{Tinnefeld2014, author = {Tinnefeld, Christian}, title = {Building a columnar database on shared main memory-based storage}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063}, school = {Universit{\"a}t Potsdam}, pages = {175}, year = {2014}, abstract = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.}, language = {en} } @misc{MargariaKubczakSteffen2008, author = {Margaria, Tiziana and Kubczak, Christian and Steffen, Bernhard}, title = {Bio-jETI}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {822}, doi = {10.25932/publishup-42886}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-428868}, pages = {19}, year = {2008}, abstract = {Background: With Bio-jETI, we introduce a service platform for interdisciplinary work on biological application domains and illustrate its use in a concrete application concerning statistical data processing in R and xcms for an LC/MS analysis of FAAH gene knockout. Methods: Bio-jETI uses the jABC environment for service-oriented modeling and design as a graphical process modeling tool and the jETI service integration technology for remote tool execution. Conclusions: As a service definition and provisioning platform, Bio-jETI has the potential to become a core technology in interdisciplinary service orchestration and technology transfer. Domain experts, like biologists not trained in computer science, directly define complex service orchestrations as process models and use efficient and complex bioinformatics tools in a simple and intuitive way.}, language = {en} } @misc{DworschakGrellNikiforovaetal.2008, author = {Dworschak, Steve and Grell, Susanne and Nikiforova, Victoria J. and Schaub, Torsten H. and Selbig, Joachim}, title = {Modeling biological networks by action languages via answer set programming}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {843}, issn = {1866-8372}, doi = {10.25932/publishup-42984}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-429846}, pages = {47}, year = {2008}, abstract = {We describe an approach to modeling biological networks by action languages via answer set programming. To this end, we propose an action language for modeling biological networks, building on previous work by Baral et al. We introduce its syntax and semantics along with a translation into answer set programming, an efficient Boolean Constraint Programming Paradigm. Finally, we describe one of its applications, namely, the sulfur starvation response-pathway of the model plant Arabidopsis thaliana and sketch the functionality of our system and its usage.}, language = {en} } @misc{RepsilberKernTelaaretal.2010, author = {Repsilber, Dirk and Kern, Sabine and Telaar, Anna and Walzl, Gerhard and Black, Gillian F. and Selbig, Joachim and Parida, Shreemanta K. and Kaufmann, Stefan H. E. and Jacobsen, Marc}, title = {Biomarker discovery in heterogeneous tissue samples}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {854}, issn = {1866-8372}, doi = {10.25932/publishup-42934}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-429343}, pages = {17}, year = {2010}, abstract = {Background: For heterogeneous tissues, such as blood, measurements of gene expression are confounded by relative proportions of cell types involved. Conclusions have to rely on estimation of gene expression signals for homogeneous cell populations, e.g. by applying micro-dissection, fluorescence activated cell sorting, or in-silico deconfounding. We studied feasibility and validity of a non-negative matrix decomposition algorithm using experimental gene expression data for blood and sorted cells from the same donor samples. Our objective was to optimize the algorithm regarding detection of differentially expressed genes and to enable its use for classification in the difficult scenario of reversely regulated genes. This would be of importance for the identification of candidate biomarkers in heterogeneous tissues. Results: Experimental data and simulation studies involving noise parameters estimated from these data revealed that for valid detection of differential gene expression, quantile normalization and use of non-log data are optimal. We demonstrate the feasibility of predicting proportions of constituting cell types from gene expression data of single samples, as a prerequisite for a deconfounding-based classification approach. Classification cross-validation errors with and without using deconfounding results are reported as well as sample-size dependencies. Implementation of the algorithm, simulation and analysis scripts are available. Conclusions: The deconfounding algorithm without decorrelation using quantile normalization on non-log data is proposed for biomarkers that are difficult to detect, and for cases where confounding by varying proportions of cell types is the suspected reason. In this case, a deconfounding ranking approach can be used as a powerful alternative to, or complement of, other statistical learning approaches to define candidate biomarkers for molecular diagnosis and prediction in biomedicine, in realistically noisy conditions and with moderate sample sizes.}, language = {en} } @misc{MargariaSteffenKubczak2010, author = {Margaria, Tiziana and Steffen, Bernhard and Kubczak, Christian}, title = {Evolution support in heterogeneous service-oriented landscapes}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {918}, issn = {1866-8372}, doi = {10.25932/publishup-43240}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-432405}, pages = {15}, year = {2010}, abstract = {We present an approach that provides automatic or semi-automatic support for evolution and change management in heterogeneous legacy landscapes where (1) legacy heterogeneous, possibly distributed platforms are integrated in a service oriented fashion, (2) the coordination of functionality is provided at the service level, through orchestration, (3) compliance and correctness are provided through policies and business rules, (4) evolution and correctness-by-design are supported by the eXtreme Model Driven Development paradigm (XMDD) offered by the jABC (Margaria and Steffen in Annu. Rev. Commun. 57, 2004)—the model-driven service oriented development platform we use here for integration, design, evolution, and governance. The artifacts are here semantically enriched, so that automatic synthesis plugins can field the vision of Enterprise Physics: knowledge driven business process development for the end user. We demonstrate this vision along a concrete case study that became over the past three years a benchmark for Semantic Web Service discovery and mediation. We enhance the Mediation Scenario of the Semantic Web Service Challenge along the 2 central evolution paradigms that occur in practice: (a) Platform migration: platform substitution of a legacy system by an ERP system and (b) Backend extension: extension of the legacy Customer Relationship Management (CRM) and Order Management System (OMS) backends via an additional ERP layer.}, language = {en} } @misc{LarhlimiDavidSelbigetal.2012, author = {Larhlimi, Abdelhalim and David, Laszlo and Selbig, Joachim and Bockmayr, Alexander}, title = {F2C2}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {921}, issn = {1866-8372}, doi = {10.25932/publishup-43243}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-432431}, pages = {11}, year = {2012}, abstract = {Background: Flux coupling analysis (FCA) has become a useful tool in the constraint-based analysis of genome-scale metabolic networks. FCA allows detecting dependencies between reaction fluxes of metabolic networks at steady-state. On the one hand, this can help in the curation of reconstructed metabolic networks by verifying whether the coupling between reactions is in agreement with the experimental findings. On the other hand, FCA can aid in defining intervention strategies to knock out target reactions. Results: We present a new method F2C2 for FCA, which is orders of magnitude faster than previous approaches. As a consequence, FCA of genome-scale metabolic networks can now be performed in a routine manner. Conclusions: We propose F2C2 as a fast tool for the computation of flux coupling in genome-scale metabolic networks. F2C2 is freely available for non-commercial use at https://sourceforge.net/projects/f2c2/files/.}, language = {en} } @misc{Wallenta2014, author = {Wallenta, Daniel}, title = {A Lefschetz fixed point formula for elliptic quasicomplexes}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe}, number = {885}, issn = {1866-8372}, doi = {10.25932/publishup-43547}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-435471}, pages = {577 -- 587}, year = {2014}, abstract = {In a recent paper, the Lefschetz number for endomorphisms (modulo trace class operators) of sequences of trace class curvature was introduced. We show that this is a well defined, canonical extension of the classical Lefschetz number and establish the homotopy invariance of this number. Moreover, we apply the results to show that the Lefschetz fixed point formula holds for geometric quasiendomorphisms of elliptic quasicomplexes.}, language = {en} }