Structural Variant Machine (SV-M)

Accurate indel prediction using paired-end short reads

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.

This tool uses various features derived from alignment statistics to then predict potential indel candidates into true or false indels.

C/C++ code can be found at my GitHub repository: C/C++ Code


Background One of the major open challenges in next generation sequencing (NGS) is the accurate identification of structural variants such as insertions and deletions (indels). Current methods for indel calling assign scores to different types of evidence or counter-evidence for the presence of an indel, such as the number of split read alignments spanning the boundaries of a deletion candidate or reads that map within a putative deletion. Candidates with a score above a manually defined threshold are then predicted to be true indels. As a consequence, structural variants detected in this manner contain many false positives.

Results Here, we present a machine learning based method which is able to discover and distinguish true from false indel candidates in order to reduce the false positive rate. Our method identifies indel candidates using a discriminative classifier based on features of split read alignment profiles and trained on true and false indel candidates that were validated by Sanger sequencing. We demonstrate the usefulness of our method with paired-end Illumina reads from 80 genomes of the first phase of the 1001 Genomes Project ( in Arabidopsis thaliana.

Conclusion In this work we show that indel classification is a necessary step to reduce the number of false positive candidates. We demonstrate that missing classification may lead to spurious biological interpretations. 

  • Accurate indel prediction using paired-end short reads. 
    D Grimm*, J Hagmann*, D Koenig, D Weigel and K Borgwardt
    BMC Genomics 2013, 14:132