2 Search Results for "Hartmann, Sven"

Document
DOI: 10.4230/LIPIcs.WABI.2018.13
Spalter: A Meta Machine Learning Approach to Distinguish True DNA Variants from Sequencing Artefacts

Authors: Till Hartmann and Sven Rahmann

Published in: LIPIcs, Volume 113, 18th International Workshop on Algorithms in Bioinformatics (WABI 2018)

Abstract
Being able to distinguish between true DNA variants and technical sequencing artefacts is a fundamental task in whole genome, exome or targeted gene analysis. Variant calling tools provide diagnostic parameters, such as strand bias or an aggregated overall quality for each called variant, to help users make an informed choice about which variants to accept or discard. Having several such quality indicators poses a problem for the users of variant callers because they need to set or adjust thresholds for each such indicator. Alternatively, machine learning methods can be used to train a classifier based on these indicators. This approach needs large sets of labeled training data, which is not easily available. The new approach presented here relies on the idea that a true DNA variant exists independently of technical features of the read in which it appears (e.g. base quality, strand, position in the read). Therefore the nucleotide separability classification problem - predicting the nucleotide state of each read in a given pileup based on technical features only - should be near impossible to solve for true variants. Nucleotide separability, i.e. achievable classification accuracy, can either be used to distinguish between true variants and technical artefacts directly, using a thresholding approach, or it can be used as a meta-feature to train a separability-based classifier. This article explores both possibilities with promising results, showing accuracies around 90%.
Cite as

Till Hartmann and Sven Rahmann. Spalter: A Meta Machine Learning Approach to Distinguish True DNA Variants from Sequencing Artefacts. In 18th International Workshop on Algorithms in Bioinformatics (WABI 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 113, pp. 13:1-13:8, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)

Copy BibTex To Clipboard

@InProceedings{hartmann_et_al:LIPIcs.WABI.2018.13,
  author =	{Hartmann, Till and Rahmann, Sven},
  title =	{{Spalter: A Meta Machine Learning Approach to Distinguish True DNA Variants from Sequencing Artefacts}},
  booktitle =	{18th International Workshop on Algorithms in Bioinformatics (WABI 2018)},
  pages =	{13:1--13:8},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-082-8},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{113},
  editor =	{Parida, Laxmi and Ukkonen, Esko},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.WABI.2018.13},
  URN =		{urn:nbn:de:0030-drops-93158},
  doi =		{10.4230/LIPIcs.WABI.2018.13},
  annote =	{Keywords: variant calling, sequencing error, technical artefact, meta machine learning, classification}
}
Document
DOI: 10.4230/DagRep.3.5.43
Automated Reasoning on Conceptual Schemas (Dagstuhl Seminar 13211)

Authors: Diego Calvanese, Sven Hartmann, and Ernest Teniente

Published in: Dagstuhl Reports, Volume 3, Issue 5 (2013)

Abstract
This report documents the outcomes of the Dagstuhl Seminar 13211 "Automated Reasoning on Conceptual Schemas". The quality of an information system is largely determined early in the development cycle, i.e., during requirements specification and conceptual modeling since errors introduced at these stages are usually much more expensive to correct than errors made during design or implementation. Thus, it is desirable to prevent, detect, and correct errors as early as possible in the development process by assessing the correctness of the conceptual schemas built. The high expressivity of conceptual schemas requires to adopt automated reasoning techniques to support the designer in this important task. Research in this area can be classified according to two different dimensions. On the one hand, according to the language used to specify the conceptual schema. On the other hand, according to whether reasoning is performed on the structural schema alone, or also on its dynamic aspects. We find interesting and promising results from all these communities which have usually worked isolatedly. Therefore, the aim of this seminar was to allow them to communicate with each other to avoid duplicate effort and to exploit synergies. The research questions that were pursued in the seminar included, among others: (i) Does it make sense to renounce to decidability to be able to handle the full expressive power of the language used with and without textual integrity constraints? (ii) Which is the current state of the achievements as far as reasoning on the behavioral part is concerned? (iii) Are the existing techniques and tools ready to be used in an industrial environment? (iv) Which are the new challenges for automated reasoning on conceptual schemas?
Cite as

Diego Calvanese, Sven Hartmann, and Ernest Teniente. Automated Reasoning on Conceptual Schemas (Dagstuhl Seminar 13211). In Dagstuhl Reports, Volume 3, Issue 5, pp. 43-77, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2013)

Copy BibTex To Clipboard

@Article{calvanese_et_al:DagRep.3.5.43,
  author =	{Calvanese, Diego and Hartmann, Sven and Teniente, Ernest},
  title =	{{Automated Reasoning on Conceptual Schemas (Dagstuhl Seminar 13211)}},
  pages =	{43--77},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2013},
  volume =	{3},
  number =	{5},
  editor =	{Calvanese, Diego and Hartmann, Sven and Teniente, Ernest},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.3.5.43},
  URN =		{urn:nbn:de:0030-drops-41807},
  doi =		{10.4230/DagRep.3.5.43},
  annote =	{Keywords: Automated Reasoning, Conceptual Schema of an Information System, Validation, Verification}
}
  • Refine by Author
  • 1 Calvanese, Diego
  • 1 Hartmann, Sven
  • 1 Hartmann, Till
  • 1 Rahmann, Sven
  • 1 Teniente, Ernest

  • Refine by Classification
  • 1 Applied computing → Sequencing and genotyping technologies
  • 1 Computing methodologies → Supervised learning by classification
  • 1 Computing methodologies → Unsupervised learning

  • Refine by Keyword
  • 1 Automated Reasoning
  • 1 Conceptual Schema of an Information System
  • 1 Validation
  • 1 Verification
  • 1 classification
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 1 2013
  • 1 2018

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact