Structural Variant Machine (SV-M)

Main content

Dominik Grimm, Jörg Hagmann, Daniel Koenig, Detlef Weigel and Karsten Borgwardt

Accurate indel prediction using paired-end short reads

Summary

To accurately predict deletions and insertions we developed a tool called Structural Variant Machine (SV-M). This tool is using a Support Vector Machine (SVM) to then predict potential indel candidates as true or false ones. Further we are working on a single pipeline to simplfy the whole process of predicting indels.

Code

The code is written in C/C++. The source can be downloaded here (ZIP, 96 KB).

Supplementary data

The supplementary data contains the Sanger validated training data and all annotated indels and potential gene losses. The data can be downloaded here (ZIP, 5 MB).

Reference

Keyboard navigation between tabs via Alt arrow keys as well as Home and End.

Dominik Grimm, Jörg Hagmann, Daniel Koenig, Detlef Weigel and Karsten Borgwardt
Accurate indel prediction using paired-end short reads,
BMC Genomics 2013, 14:132-141. (Online)

@Article{Grimm_Accurate_2013,
author="Grimm, Dominik
and Hagmann, J{\"o}rg
and Koenig, Daniel
and Weigel, Detlef
and Borgwardt, Karsten",
title="Accurate indel prediction using paired-end short reads",
journal="BMC Genomics",
year="2013",
volume="14",
number="1",
pages="1--10",
issn="1471-2164",
doi="10.1186/1471-2164-14-132",
url="http://dx.doi.org/10.1186/1471-2164-14-132"
}

Contact for questions.

 
 
Page URL: https://www.bsse.ethz.ch/mlcb/research/bioinformatics-and-computational-biology/structural-variant-machine--sv-m-.html
Thu Mar 23 17:16:53 CET 2017
© 2017 Eidgenössische Technische Hochschule Zürich