Position kernels as a key to making sense of very rare and private single-nucleotide variants

Ulrich Bodenhofer, Sepp Hochreiter

Publikation: KonferenzbeitragPapierBegutachtung

2 Downloads (Pure)

Abstract

We present an approach for convolving single-nucleotide variants (SNVs) with a position kernel in order to augment SNVs with information about close-by SNVs. By means of the Position-Dependent Kernel Association Test (PODKAT), we demonstrate the potential of this approach to leverage the analysis of rare and private SNVs. Finally, we also provide some ideas how machine-learning based predictions from genomic data can benefit from this augmentation.
OriginalspracheEnglisch (Amerika)
PublikationsstatusVeröffentlicht - Dez 2017
Extern publiziertJa
VeranstaltungNIPS Workshop on Machine Learning in Computational Biology - Long Beach, CA, USA/Vereinigte Staaten
Dauer: 9 Dez 20179 Dez 2017

Workshop

WorkshopNIPS Workshop on Machine Learning in Computational Biology
Land/GebietUSA/Vereinigte Staaten
Zeitraum09.12.201709.12.2017

Zitieren