DeepCNV: A deep learning approach for authenticating copy number variations

Joseph T. Glessner, Xiurui Hou, Cheng Zhong, Jie Zhang, Munir Khan, Fabian Brand, Peter Krawitz, Patrick M.A. Sleiman, Hakon Hakonarson, Zhi Wei

Research output: Contribution to journalReview articlepeer-review

Abstract

Copy number variations (CNVs) are an important class of variations contributing to the pathogenesis of many disease phenotypes. Detecting CNVs from genomic data remains difficult, and the most currently applied methods suffer from an unacceptably high false positive rate. A common practice is to have human experts manually review original CNV calls for filtering false positives before further downstream analysis or experimental validation. Here, we propose DeepCNV, a deep learning-based tool, intended to replace human experts when validating CNV calls, focusing on the calls made by one of the most accurate CNV callers, PennCNV. The sophistication of the deep neural network algorithm is enriched with over 10 000 expert-scored samples that are split into training and testing sets. Variant confidence, especially for CNVs, is a main roadblock impeding the progress of linking CNVs with the disease. We show that DeepCNV adds to the confidence of the CNV calls with an optimal area under the receiver operating characteristic curve of 0.909, exceeding other machine learning methods. The superiority of DeepCNV was also benchmarked and confirmed using an experimental wet-lab validation dataset. We conclude that the improvement obtained by DeepCNV results in significantly fewer false positive results and failures to replicate the CNV association results.

Original languageEnglish (US)
Article numberbbaa381
JournalBriefings in Bioinformatics
Volume22
Issue number5
DOIs
StatePublished - Sep 1 2021

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Molecular Biology

Keywords

  • copy number variation
  • deep learning

Fingerprint

Dive into the research topics of 'DeepCNV: A deep learning approach for authenticating copy number variations'. Together they form a unique fingerprint.

Cite this