NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data
Bioinformatics · 04.03.2024 · 40 (3)
DOI: 10.1093/bioinformatics/btae129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 05.03.2024. Verfasst von Michael D Linderman und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NHLBI NIH HHS, National Institute of General Medical Sciences of the National Institutes of Health.
Abstract (Originalsprache)
Motivation Structural variants (SVs) play a causal role in numerous diseases but can be difficult to detect and accurately genotype (determine zygosity) with short-read genome sequencing data (SRS). Improving SV genotyping accuracy in SRS data, particularly for the many SVs first detected with long-read sequencing, will improve our understanding of genetic variation. Results NPSV-deep is a deep learning-based approach for genotyping previously reported insertion and deletion SVs that recasts this task as an image similarity problem. NPSV-deep predicts the SV genotype based on the similarity between pileup images generated from the actual SRS data and matching SRS simulations. We show that NPSV-deep consistently matches or improves upon the state-of-the-art for SV genotyping accuracy across different SV call sets, samples and variant types, including a 25% reduction in genotyping errors for the Genome-in-a-Bottle (GIAB) high-confidence SVs. NPSV-deep is not limited to the SVs as described; it improves deletion genotyping concordance a further 1.5 percentage points for GIAB SVs (92%) by automatically correcting imprecise/incorrectly described SVs. Availability and implementation Python/C++ source code and pre-trained models freely available at https://github.com/mlinderm/npsv2.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
- Google, Mountain View, CA 94043, United States.
- Mindich Child Health and Development Institute and the Departments of Pediatrics and Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY 10029, United States.
ORCID-Profile: Michael D Linderman, Jacob Wallace, Eliza Wieman, Zahra Shamsi, Jeremiah Liu, Bruce D Gelb, Ali Bashir
Förderung
- NIGMS NIH HHS
- NHLBI NIH HHS
- National Institute of General Medical Sciences of the National Institutes of Health
- National Heart, Lung, and Blood Institute of the National Institutes of Health
Zitieren
APA
Linderman, M. D., Wallace, J., van der Heyde, A., Wieman, E., Brey, D., Shi, Y., Hansen, P., Shamsi, Z., Liu, J., Gelb, B. D., & Bashir, A. (2024). NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data. Bioinformatics, 40(3). https://doi.org/10.1093/bioinformatics/btae129
Vancouver
Linderman MD, Wallace J, van der Heyde A, Wieman E, Brey D, Shi Y, et al. NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data. Bioinformatics. 2024;40(3). doi:10.1093/bioinformatics/btae129
BibTeX
@article{Linderman2024,
author = {Linderman, Michael D and Wallace, Jacob and van der Heyde, Alderik and Wieman, Eliza and Brey, Daniel and Shi, Yiran and Hansen, Peter and Shamsi, Zahra and Liu, Jeremiah and Gelb, Bruce D and Bashir, Ali},
title = {NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {3},
doi = {10.1093/bioinformatics/btae129}
}
EUVIMED