Structural Variant Machine (SV-M)

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 from our GitHub repository external pagehere.

Supplementary data

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

Publication

Accurate indel prediction using paired-end short reads

Dominik G. Grimm, Jörg Hagmann, Daniel Koenig, Detlef Weigel and Karsten Borgwardt
BMC Genomics 2013, 14(1): 132-141
external pageOnline | external pageETH Research Collection | Project page | external pageGitHub

Contact for questions.

Structural Variant Machine (SV-M)

Accurate indel prediction using paired-end short reads

Summary

Code

Supplementary data

Publication

Accurate indel prediction using paired-end short reads

Open Positions