DeepPVP: phenotype-based prioritization of causative variants using deep learning.

Boudellioua, Imane and Kulmanov, Maxat and Schofield, Paul N and Gkoutos, Georgios V and Hoehndorf, Robert (2019) DeepPVP: phenotype-based prioritization of causative variants using deep learning. BMC bioinformatics, 20 (1). p. 65. ISSN 1471-2105.

[img]
Preview
Text (PDF Fil Format)
DeepPVP- phenotype-based prioritization of causative variants using deep learning..pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (746kB) | Preview
Official URL: https://bmcbioinformatics.biomedcentral.com/articl...

Abstract

BACKGROUND

Prioritization of variants in personal genomic data is a major challenge. Recently, computational methods that rely on comparing phenotype similarity have shown to be useful to identify causative variants. In these methods, pathogenicity prediction is combined with a semantic similarity measure to prioritize not only variants that are likely to be dysfunctional but those that are likely involved in the pathogenesis of a patient's phenotype.

RESULTS

We have developed DeepPVP, a variant prioritization method that combined automated inference with deep neural networks to identify the likely causative variants in whole exome or whole genome sequence data. We demonstrate that DeepPVP performs significantly better than existing methods, including phenotype-based methods that use similar features. DeepPVP is freely available at https://github.com/bio-ontology-research-group/phenomenet-vp .

CONCLUSIONS

DeepPVP further improves on existing variant prioritization methods both in terms of speed as well as accuracy.

Item Type: Article
Subjects: QC-QM General sciences
QU Biochemistry
Divisions: Planned IP Care > Oncology and Clinical Haematology
Related URLs:
Depositing User: Jennifer Manders
Date Deposited: 12 Mar 2019 14:02
Last Modified: 12 Mar 2019 14:02
URI: http://www.repository.heartofengland.nhs.uk/id/eprint/1908

Actions (login required)

View Item View Item