@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} } @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} } @book{HerschelNaumann2008, author = {Herschel, Melanie and Naumann, Felix}, title = {Space and time scalability of duplicate detection in graph data}, isbn = {978-3-940793-46-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32851}, publisher = {Universit{\"a}t Potsdam}, year = {2008}, abstract = {Duplicate detection consists in determining different representations of real-world objects in a database. Recent research has considered the use of relationships among object representations to improve duplicate detection. In the general case where relationships form a graph, research has mainly focused on duplicate detection quality/effectiveness. Scalability has been neglected so far, even though it is crucial for large real-world duplicate detection tasks. In this paper we scale up duplicate detection in graph data (DDG) to large amounts of data and pairwise comparisons, using the support of a relational database system. To this end, we first generalize the process of DDG. We then present how to scale algorithms for DDG in space (amount of data processed with limited main memory) and in time. Finally, we explore how complex similarity computation can be performed efficiently. Experiments on data an order of magnitude larger than data considered so far in DDG clearly show that our methods scale to large amounts of data not residing in main memory.}, language = {en} } @book{PolyvyanyySmirnovWeske2008, author = {Polyvyanyy, Artem and Smirnov, Sergey and Weske, Mathias}, title = {The triconnected abstraction of process models}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-940793-65-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32847}, publisher = {Universit{\"a}t Potsdam}, pages = {17}, year = {2008}, abstract = {Contents: Artem Polyvanny, Sergey Smirnow, and Mathias Weske The Triconnected Abstraction of Process Models 1 Introduction 2 Business Process Model Abstraction 3 Preliminaries 4 Triconnected Decomposition 4.1 Basic Approach for Process Component Discovery 4.2 SPQR-Tree Decomposition 4.3 SPQR-Tree Fragments in the Context of Process Models 5 Triconnected Abstraction 5.1 Abstraction Rules 5.2 Abstraction Algorithm 6 Related Work and Conclusions}, language = {en} } @phdthesis{Bickel2008, author = {Bickel, Steffen}, title = {Learning under differing training and test distributions}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33331}, school = {Universit{\"a}t Potsdam}, year = {2008}, abstract = {One of the main problems in machine learning is to train a predictive model from training data and to make predictions on test data. Most predictive models are constructed under the assumption that the training data is governed by the exact same distribution which the model will later be exposed to. In practice, control over the data collection process is often imperfect. A typical scenario is when labels are collected by questionnaires and one does not have access to the test population. For example, parts of the test population are underrepresented in the survey, out of reach, or do not return the questionnaire. In many applications training data from the test distribution are scarce because they are difficult to obtain or very expensive. Data from auxiliary sources drawn from similar distributions are often cheaply available. This thesis centers around learning under differing training and test distributions and covers several problem settings with different assumptions on the relationship between training and test distributions-including multi-task learning and learning under covariate shift and sample selection bias. Several new models are derived that directly characterize the divergence between training and test distributions, without the intermediate step of estimating training and test distributions separately. The integral part of these models are rescaling weights that match the rescaled or resampled training distribution to the test distribution. Integrated models are studied where only one optimization problem needs to be solved for learning under differing distributions. With a two-step approximation to the integrated models almost any supervised learning algorithm can be adopted to biased training data. In case studies on spam filtering, HIV therapy screening, targeted advertising, and other applications the performance of the new models is compared to state-of-the-art reference methods.}, language = {en} } @misc{AndorfGaertnerSteinfathetal.2008, author = {Andorf, Sandra and G{\"a}rtner, Tanja and Steinfath, Matthias and Witucka-Wall, Hanna and Altmann, Thomas and Repsilber, Dirk}, title = {Towards systems biology of heterosis}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {949}, issn = {1866-8372}, doi = {10.25932/publishup-43627}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-436274}, pages = {14}, year = {2008}, abstract = {We propose a network structure-based model for heterosis, and investigate it relying on metabolite profiles from Arabidopsis. A simple feed-forward two-layer network model (the Steinbuch matrix) is used in our conceptual approach. It allows for directly relating structural network properties with biological function. Interpreting heterosis as increased adaptability, our model predicts that the biological networks involved show increasing connectivity of regulatory interactions. A detailed analysis of metabolite profile data reveals that the increasing-connectivity prediction is true for graphical Gaussian models in our data from early development. This mirrors properties of observed heterotic Arabidopsis phenotypes. Furthermore, the model predicts a limit for increasing hybrid vigor with increasing heterozygosity—a known phenomenon in the literature.}, language = {en} } @book{OPUS4-3213, title = {Proceedings of the 2nd International Workshop on e-learning and Virtual and Remote Laboratories}, editor = {Rabe, Bernhard and Rasche, Andreas}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-940793-17-1}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-34315}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 98}, year = {2008}, abstract = {Content Session 1: Architecture of Virtual \& Remote Laboratory Infrastructures (I) An Internet-Based Laboratory Course in Chemical Reaction Engineering and Unit Operations Internet Based Laboratory for Experimentation with Multilevel Medium-Power Converters Session 2: Architecture of Virtual \& Remote Laboratory Infrastructures (II) Content management and architectural issues of a remote learning laboratory Distributed Software Architecture and Applications for Remote Laboratories Tele-Lab IT-Security: an architecture for an online virtual IT security lab Session 3: New e-learning Techniques for Virtual \& Remote Laboratories NeOS: Neuchˆatel Online System A Flexible Instructional Electronics Laboratory with Local and Remote LabWorkbenches in a Grid Simulation of an Intelligent Network - Basic Call State Model Remote Laboratory Session 4: Service-Orientation in Virtual \& Remote Laboratories SOA Meets Robots - A Service-Based Software Infrastructure For Remote Laboratories Service Orientation in Education - Intelligent Networks for eLearning / mLearning}, language = {de} } @book{PolyvyanyySmirnovWeske2008, author = {Polyvyanyy, Artem and Smirnov, Sergey and Weske, Mathias}, title = {Reducing the complexity of large EPCs}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-32959}, publisher = {Universit{\"a}t Potsdam}, year = {2008}, abstract = {Inhalt: 1 Introduction 2 Motivation and Goal 3 Fundamentals 4 Elementary Abstractions 5 Real World Example 6 Conclusions}, language = {en} } @misc{LamprechtMargariaSteffenetal.2008, author = {Lamprecht, Anna-Lena and Margaria, Tiziana and Steffen, Bernhard and Sczyrba, Alexander and Hartmeier, Sven and Giegerich, Robert}, title = {GeneFisher-P}, series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, number = {868}, issn = {1866-8372}, doi = {10.25932/publishup-43424}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-434241}, pages = {17}, year = {2008}, abstract = {Background: PCR primer design is an everyday, but not trivial task requiring state-of-the-art software. We describe the popular tool GeneFisher and explain its recent restructuring using workflow techniques. We apply a service-oriented approach to model and implement GeneFisher-P, a process-based version of the GeneFisher web application, as a part of the Bio-jETI platform for service modeling and execution. We show how to introduce a flexible process layer to meet the growing demand for improved user-friendliness and flexibility. Results: Within Bio-jETI, we model the process using the jABC framework, a mature model-driven, service-oriented process definition platform. We encapsulate remote legacy tools and integrate web services using jETI, an extension of the jABC for seamless integration of remote resources as basic services, ready to be used in the process. Some of the basic services used by GeneFisher are in fact already provided as individual web services at BiBiServ and can be directly accessed. Others are legacy programs, and are made available to Bio-jETI via the jETI technology. The full power of service-based process orientation is required when more bioinformatics tools, available as web services or via jETI, lead to easy extensions or variations of the basic process. This concerns for instance variations of data retrieval or alignment tools as provided by the European Bioinformatics Institute (EBI). Conclusions: The resulting service-and process-oriented GeneFisher-P demonstrates how basic services from heterogeneous sources can be easily orchestrated in the Bio-jETI platform and lead to a flexible family of specialized processes tailored to specific tasks.}, language = {en} }