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

Ulrich Bodenhofer; Sepp Hochreiter

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

Research output: Contribution to conference › Paper › peer-review

36 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.

Original language	English (American)
Publication status	Published - Dec 2017
Externally published	Yes
Event	NIPS Workshop on Machine Learning in Computational Biology - Long Beach, CA, United States Duration: 9 Dec 2017 → 9 Dec 2017

Workshop

Workshop	NIPS Workshop on Machine Learning in Computational Biology
Country/Territory	United States
Period	09.12.2017 → 09.12.2017

Access to Document

BodenhoferHochreiter17

Cite this

@conference{9a3c6d97b288475595bc051388d848aa,

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

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.",

author = "Ulrich Bodenhofer and Sepp Hochreiter",

year = "2017",

month = dec,

language = "Englisch (Amerika)",

note = "NIPS Workshop on Machine Learning in Computational Biology ; Conference date: 09-12-2017 Through 09-12-2017",

}

TY - CONF

T1 - Position kernels as a key to making sense of very rare and private single-nucleotide variants

AU - Bodenhofer, Ulrich

AU - Hochreiter, Sepp

PY - 2017/12

Y1 - 2017/12

N2 - 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.

AB - 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.

M3 - Papier

T2 - NIPS Workshop on Machine Learning in Computational Biology

Y2 - 9 December 2017 through 9 December 2017

ER -