Dr. Sebastian Schönherr

@Article{coassin,
  author    = {Coassin, Stefan and Erhart, Gertraud and Weissensteiner, Hansi and Guimaraes de Araujo, Mariana Eca and Lamina, Claudia and Sch\"onherr, Sebastian and Forer, Lukas and Haun, Margot and Lee Losso, Jamie and K\"ottgen, Anna and Uterman, Gerd and Peters, Annette and Gieger, Christian and Strauch, Konstantin and Finkenstedt, Armin and Bale, Reto and Zoller, Heinz and Paulweber, Bernhard and Eckardt, Kai-Uwe and H\"uttenhofer, Alexander and Huber, Lukas and Kronenberg, Florian},
  title     = {A novel but frequent variant in LPA KIV-2 is associated with a pronounced Lp(a) and cardiovascular risk reduction},
  journal   = {European Heart Journal - in press},
  year      = {2017},
  publisher = {Wiley Online Library},
}

@article{forer2016cloudflow,
  title={Cloudflow-enabling faster biomedical pipelines with MapReduce and Spark},
  author={Forer, Lukas and Afgan, Enis and Weissensteiner, Hansi and Davidovic, Davor and Specht, Guenther and Kronenberg, Florian and Schoenherr, Sebastian},
  journal={Scalable Computing: Practice and Experience},
  volume={17},
  number={2},
  pages={103--114},
  year={2016}
}

@article{doi:10.1093/nar/gkw233,
author = {Weissensteiner, Hansi and Pacher, Dominic and Kloss-Brandstätter, Anita and Forer, Lukas and Specht, Günther and Bandelt, Hans-Jürgen and Kronenberg, Florian and Salas, Antonio and Schönherr, Sebastian},
title = {HaploGrep 2: mitochondrial haplogroup classification in the era of high-throughput sequencing},
journal = {Nucleic Acids Research},
volume = {44},
number = {W1},
pages = {W58--W63},
year = {2016},
doi = {10.1093/nar/gkw233},
URL = { + http://dx.doi.org/10.1093/nar/gkw233},
eprint = {/oup/backfile/Content_public/Journal/nar/44/W1/10.1093_nar_gkw233/3/gkw233.pdf}
}

@article{doi:10.1093/nar/gkw247,
author = {Weissensteiner, Hansi and Forer, Lukas and Fuchsberger, Christian and Schöpf, Bernd and Kloss-Brandstätter, Anita and Specht, Günther and Kronenberg, Florian and Schönherr, Sebastian},
title = {mtDNA-Server: next-generation sequencing data analysis of human mitochondrial DNA in the cloud},
journal = {Nucleic Acids Research},
volume = {44},
number = {W1},
pages = {W64-W69},
year = {2016},
doi = {10.1093/nar/gkw247},
URL = { + http://dx.doi.org/10.1093/nar/gkw247},
eprint = {/oup/backfile/Content_public/Journal/nar/44/W1/10.1093_nar_gkw247/3/gkw247.pdf}
}

@INPROCEEDINGS{7160259,
author={L. Forer and E. Afgan and H. Weißensteiner and D. Davidović and G. Specht and F. Kronenberg and S. Schönherr},
booktitle={2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)},
title={Cloudflow - A framework for MapReduce pipeline development in Biomedical Research},
year={2015},
pages={172-177},
abstract={The data-driven parallelization framework Hadoop MapReduce allows analysing large data sets in a scalable way. Since the development of MapReduce programs can be a time-intensive and challenging task, the application and usage of Hadoop in Biomedical Research is still limited. Here we present Cloudflow, a high-level framework to hide the implementation details of Hadoop and to provide a set of building blocks to create biomedical pipelines in a more intuitive way. We demonstrate the benefit of Cloudflow on three different genetic use cases. It will be shown how the framework can be combined with the Hadoop workflow system Cloudgene and the cloud orchestration platform CloudMan to provide Hadoop pipelines as a service to everyone.},
keywords={cloud computing;data handling;medical computing;parallel processing;CloudMan;Cloudflow;Cloudgene;Hadoop MapReduce;biomedical research;cloud orchestration platform;data-driven parallelization framework;genetic use cases;high-level framework;pipeline development;workflow system;Bioinformatics;Genomics;Information filters;Pipeline processing;Pipelines},
doi={10.1109/MIPRO.2015.7160259},
month={May},}

@article{raschenberger2015telomeres,
  title={Do telomeres have a higher plasticity than thought? Results from the German Chronic Kidney Disease (GCKD) study as a high-risk population},
 author = {Raschenberger, Julia and Kollerits, Barbara and Titze, Stephanie and K{\"{o}}ttgen, Anna and B{\"{a}}rthlein, Barbara and Ekici, Arif B. and Forer, Lukas and Sch{\"{o}}nherr, Sebastian and Weissensteiner, Hansi and Haun, Margot and Wanner, Christoph and Eckardt, Kai-Uwe and Kronenberg, Florian},
  journal={Experimental gerontology},
  volume={72},
  pages={162--166},
  year={2015},
  publisher={Pergamon}
}

@article{kloss2015validation,
  title={Validation of next-generation sequencing of entire mitochondrial genomes and the diversity of mitochondrial DNA mutations in oral squamous cell carcinoma},
 author = {Kloss-Brandst{\"{a}}tter, Anita and Weissensteiner, Hansi and Erhart, Gertraud and Sch{\"{a}}fer, Georg and Forer, Lukas and Sch{\"{o}}nherr, Sebastian and Pacher, Dominic and Seifarth, Christof and St{\"{o}}ckl, Andrea and Fendt, Liane and Sottsas, Irma and Klocker, Helmut and Huck, Christian W. and Rasse, Michael and Kronenberg, Florian and Kloss, Frank R.},
  journal={PloS one},
  volume={10},
  number={8},
  pages={e0135643},
  year={2015},
  publisher={Public Library of Science}
}

@article{raschenberger2015association,
  title={Association of relative telomere length with cardiovascular disease in a large chronic kidney disease cohort: the GCKD study},
author = {Raschenberger, Julia and Kollerits, Barbara and Titze, Stephanie and {Koettgen}, Anna K and Baerthlein, Barbara B  and Ekici, Arif B and Forer, Lukas and Sch, Sebastian and Sch\"onherr, and Weissensteiner, Hansi and Haun, Margot and Wanner, Christoph and Eckardt, Kai-Uwe and Kronenberg, Florian},
  journal={Atherosclerosis},
  volume={242},
  number={2},
  pages={529--534},
  year={2015},
  publisher={Elsevier}
}

@PHDTHESIS {schoenherr2014-diss,
    author = {Sebastian Sch\"{o}nherr},
    title  = {{Processing of massive datasets in genomics}},
    school = {University of Innsbruck, Department of Computer Science},
    year   = {2014},
    month  = {may}
}

@inproceedings{forer2014delivering,
  title={Delivering bioinformatics mapreduce applications in the cloud},
  author={Forer, Lukas and Lipic, Tomislav and Schonherr, Sebastian and Weissensteiner, Hansi and Davidovic, Davor and Kronenberg, Florian and Afgan, Enis},
  booktitle={Information and Communication Technology, Electronics and Microelectronics (MIPRO), 2014 37th International Convention on},
  pages={373--377},
  year={2014},
  organization={IEEE}
}

@article{summerer2014large,
  title={Large-scale mitochondrial DNA analysis in Southeast Asia reveals evolutionary effects of cultural isolation in the multi-ethnic population of Myanmar},
 author = {Summerer, Monika and Horst, J{\"{u}}rgen and Erhart, Gertraud and Weissensteiner, Hansi and Sch{\"{o}}nherr, Sebastian and Pacher, Dominic and Forer, Lukas and Horst, David and Manhart, Angelika and Horst, Basil and Sanguansermsri, Torpong and Kloss-Brandst{\"{a}}tter, Anita},
  journal={BMC evolutionary biology},
  volume={14},
  number={1},
  pages={17},
  year={2014},
  publisher={BioMed Central}
}

@article{10.1371/journal.pone.0059508,
    author = {Weissensteiner, Hansi AND Haun, Margot AND Schönherr, Sebastian AND Neuner, Mathias AND Forer, Lukas AND Specht, Günther AND Kloss-Brandstätter, Anita AND Kronenberg, Florian AND Coassin, Stefan},
    journal = {PLOS ONE},
    publisher = {Public Library of Science},
    title = {SNPflow: A Lightweight Application for the Processing, Storing and Automatic Quality Checking of Genotyping Assays},
    year = {2013},
    month = {03},
    volume = {8},
    url = {http://dx.doi.org/10.1371%2Fjournal.pone.0059508},
    pages = {1-9},
    abstract = {Single nucleotide polymorphisms (SNPs) play a prominent role in modern genetics. Current genotyping technologies such as Sequenom iPLEX, ABI TaqMan and KBioscience KASPar made the genotyping of huge SNP sets in large populations straightforward and allow the generation of hundreds of thousands of genotypes even in medium sized labs. While data generation is straightforward, the subsequent data conversion, storage and quality control steps are time-consuming, error-prone and require extensive bioinformatic support. In order to ease this tedious process, we developed SNPflow. SNPflow is a lightweight, intuitive and easily deployable application, which processes genotype data from Sequenom MassARRAY (iPLEX) and ABI 7900HT (TaqMan, KASPar) systems and is extendible to other genotyping methods as well. SNPflow automatically converts the raw output files to ready-to-use genotype lists, calculates all standard quality control values such as call rate, expected and real amount of replicates, minor allele frequency, absolute number of discordant replicates, discordance rate and the p-value of the HWE test, checks the plausibility of the observed genotype frequencies by comparing them to HapMap/1000-Genomes, provides a module for the processing of SNPs, which allow sex determination for DNA quality control purposes and, finally, stores all data in a relational database. SNPflow runs on all common operating systems and comes as both stand-alone version and multi-user version for laboratory-wide use. The software, a user manual, screenshots and a screencast illustrating the main features are available at http://genepi-snpflow.i-med.ac.at.},
    number = {3},
    doi = {10.1371/journal.pone.0059508}
}

@incollection{forer2012cloud,
  title={Cloud Computing - Bringing computational power to medical genetics},
  author={Forer, Lukas and Sch{\"o}nherr, Sebastian and Weissensteiner, Hansi and Specht, G{\"u}nther and Kronenberg, Florian and Kloss-Brandst{\"a}tter, Anita},
  booktitle={Computational Medicine: Tools and Challenges},
  pages={27--36},
  year={2012},
  publisher={Springer},
}

@article{Lamina2012363,
title = "Evaluation of gene-obesity interaction effects on cholesterol levels: A genetic predisposition score on HDL-cholesterol is modified by obesity ",
journal = "Atherosclerosis ",
volume = "225",
number = "2",
pages = "363 - 369",
year = "2012",
note = "",
issn = "0021-9150",
doi = "http://dx.doi.org/10.1016/j.atherosclerosis.2012.09.016",
url = "http://www.sciencedirect.com/science/article/pii/S002191501200634X",
author = "Claudia Lamina and Lukas Forer and Sebastian Schönherr and Barbara Kollerits and Janina S. Ried and Christian Gieger and Annette Peters and H.-Erich Wichmann and Florian Kronenberg",
keywords = "Lipids",
keywords = "Genetic predisposition score",
keywords = "SNP",
keywords = "Interaction",
keywords = "Polymorphism",
keywords = "HDL cholesterol ",
abstract = "Objective Effect modification by obesity or obesity-related phenotypes (e.g. physical activity and diet) was observed in some candidate gene studies on lipids. We aimed to evaluate gene–obesity interaction effects on \{HDL\} (HDL-C), \{LDL\} (LDL-C) and total cholesterol (TC) levels using genetic predisposition scores. Methods We derived imputed genotypes for 104 \{SNPs\} in 84 lipid-associated loci in the population-based studies \{KORA\} \{F3\} (n = 1406) and \{KORA\} \{F4\} (n = 1515). We inferred specific unbiased weights for each \{SNP\} from linear regression estimates in \{KORA\} F4. Weighted genotypic predisposition SNP-scores were then calculated for each lipid trait in \{KORA\} F3. Interaction terms of SNP-scores with each of the obesity parameters (BMI, waist–hip-ratio, waist circumference) were included in age- and sex-adjusted linear regression models on HDL-C, LDL-C and TC. Results All three SNP-scores were shown to be highly associated with their respective lipid levels (p = 1.11 × 10−47 for HDL-C, p = 3.25 × 10−19 for LDL-C and 1.53 × 10−13 for TC). BMI, \{WHR\} and waist circumference modified the effect of the weighted HDL-C SNP-score on HDL-C significantly (all interaction p-values < 0.0062). No interaction term was significant for LDL-C or TC. Accounting for gene–obesity interaction substantially increased the proportion of HDL-C variance explained by 3–3.5%. Conclusion Our investigation revealed a significant interaction effect between obesity parameters and a SNP-score on HDL-C: the combined effect of HDL-C-increasing alleles on HDL-C is attenuated with increasing levels of obesity–relevant parameters. Future studies aiming to detect new genetic variants or to model genetic predictions of HDL-C levels should take obesity or obesity associated parameters into account. "
}

@Article{Schönherr2012,
author="Sch{\"o}nherr, Sebastian
and Forer, Lukas
and Wei{\ss}ensteiner, Hansi
and Kronenberg, Florian
and Specht, G{\"u}nther
and Kloss-Brandst{\"a}tter, Anita",
title="Cloudgene: A graphical execution platform for MapReduce programs on private and public clouds",
journal="BMC Bioinformatics",
year="2012",
volume="13",
number="1",
pages="200",
abstract="The MapReduce framework enables a scalable processing and analyzing of large datasets by distributing the computational load on connected computer nodes, referred to as a cluster. In Bioinformatics, MapReduce has already been adopted to various case scenarios such as mapping next generation sequencing data to a reference genome, finding SNPs from short read data or matching strings in genotype files. Nevertheless, tasks like installing and maintaining MapReduce on a cluster system, importing data into its distributed file system or executing MapReduce programs require advanced knowledge in computer science and could thus prevent scientists from usage of currently available and useful software solutions.",
issn="1471-2105",
doi="10.1186/1471-2105-13-200",
url="http://dx.doi.org/10.1186/1471-2105-13-200"
}

@inproceedings{schonherr2011feedback,
  title={A feedback guided interface for elastic computing.},
  author={Sch{\"o}nherr, Sebastian and Forer, Lukas and Wei{\ss}ensteiner, Hansi and Kronenberg, Florian and Specht, G{\"u}nther and Kloss-Brandst{\"a}tter, Anita},
  booktitle={Grundlagen von Datenbanken},
  pages={109--114},
  year={2011},
  organization={Citeseer}
}

@article {HUMU:HUMU21382,
author = {Kloss-Brandstätter, Anita and Pacher, Dominic and Schönherr, Sebastian and Weissensteiner, Hansi and Binna, Robert and Specht, Günther and Kronenberg, Florian},
title = {HaploGrep: a fast and reliable algorithm for automatic classification of mitochondrial DNA haplogroups},
journal = {Human Mutation},
volume = {32},
number = {1},
publisher = {Wiley Subscription Services, Inc., A Wiley Company},
issn = {1098-1004},
url = {http://dx.doi.org/10.1002/humu.21382},
doi = {10.1002/humu.21382},
pages = {25--32},
keywords = {mitochondrial DNA, haplogroup, Phylotree, quality assurance},
year = {2011},
}

Click to copy this citation from the text box above or download

@Article{Forer2010,
author="Forer, Lukas
and Sch{\"o}nherr, Sebastian
and Weissensteiner, Hansi
and Haider, Florian
and Kluckner, Thomas
and Gieger, Christian
and Wichmann, Heinz-Erich
and Specht, G{\"u}nther
and Kronenberg, Florian
and Kloss-Brandst{\"a}tter, Anita",
title="CONAN: copy number variation analysis software for genome-wide association studies",
journal="BMC Bioinformatics",
year="2010",
volume="11",
number="1",
pages="318",
abstract="Genome-wide association studies (GWAS) based on single nucleotide polymorphisms (SNPs) revolutionized our perception of the genetic regulation of complex traits and diseases. Copy number variations (CNVs) promise to shed additional light on the genetic basis of monogenic as well as complex diseases and phenotypes. Indeed, the number of detected associations between CNVs and certain phenotypes are constantly increasing. However, while several software packages support the determination of CNVs from SNP chip data, the downstream statistical inference of CNV-phenotype associations is still subject to complicated and inefficient in-house solutions, thus strongly limiting the performance of GWAS based on CNVs.",
issn="1471-2105",
doi="10.1186/1471-2105-11-318",
url="http://dx.doi.org/10.1186/1471-2105-11-318"
}

@Article{Weißensteiner2010,
author="Weißensteiner, Hansi
and Sch{\"o}nherr, Sebastian
and Specht, G{\"u}nther
and Kronenberg, Florian
and Brandst{\"a}tter, Anita",
title="eCOMPAGT integrates mtDNA: Import, Validation and Export of Mitochondrial DNA Profiles for Population Genetics, Tumour Dynamics and Genotype-Phenotype Association Studies",
journal="BMC Bioinformatics",
year="2010",
volume="11",
number="1",
pages="122",
abstract="Mitochondrial DNA (mtDNA) is widely being used for population genetics, forensic DNA fingerprinting and clinical disease association studies. The recent past has uncovered severe problems with mtDNA genotyping, not only due to the genotyping method itself, but mainly to the post-lab transcription, storage and report of mtDNA genotypes.",
issn="1471-2105",
doi="10.1186/1471-2105-11-122",
url="http://dx.doi.org/10.1186/1471-2105-11-122"
}

@Article{Schönherr2009,
author="Sch{\"o}nherr, Sebastian
and Wei{\ss}ensteiner, Hansi
and Coassin, Stefan
and Specht, G{\"u}nther
and Kronenberg, Florian
and Brandst{\"a}tter, Anita",
title="eCOMPAGT -- efficient Combination and Management of Phenotypes and Genotypes for Genetic Epidemiology",
journal="BMC Bioinformatics",
year="2009",
volume="10",
number="1",
pages="139",
abstract="High-throughput genotyping and phenotyping projects of large epidemiological study populations require sophisticated laboratory information management systems. Most epidemiological studies include subject-related personal information, which needs to be handled with care by following data privacy protection guidelines. In addition, genotyping core facilities handling cooperative projects require a straightforward solution to monitor the status and financial resources of the different projects.",
issn="1471-2105",
doi="10.1186/1471-2105-10-139",
url="http://dx.doi.org/10.1186/1471-2105-10-139"
}