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

Handle URI:
http://hdl.handle.net/10754/627821
Title:
DeepPVP: phenotype-based prioritization of causative variants using deep learning
Authors:
Boudellioua, Imene; Kulmanov, Maxat ( 0000-0003-1710-1820 ) ; Schofield, Paul N; Gkoutos, Georgios V; Hoehndorf, Robert ( 0000-0001-8149-5890 )
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.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Computational Bioscience Research Center (CBRC)
Citation:
Boudellioua I, Kulmanov M, Schofield PN, Gkoutos GV, Hoehndorf R (2018) DeepPVP: phenotype-based prioritization of causative variants using deep learning. Available: http://dx.doi.org/10.1101/311621.
Publisher:
Cold Spring Harbor Laboratory
KAUST Grant Number:
URF/1/3454-01-01; FCC/1/1976-08-01
Issue Date:
2-May-2018
DOI:
10.1101/311621
Type:
Working Paper
Sponsors:
This work was supported by funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3454-01-01 and FCC/1/1976-08-01. GVG acknowledges support from H2020-EINFRA (731075) and the National Science Foundation (IOS:1340112) as well as support from the NIHR Birmingham ECMC, NIHR Birmingham SRMRC and the NIHR Birmingham Biomedical Research Centre and the MRC HDR UK. The views expressed in this publication are those of the authors and not necessarily those of the NHS, the National Institute for Health Research, the Medical Research Council or the Department of Health.
Additional Links:
https://www.biorxiv.org/content/early/2018/05/02/311621
Appears in Collections:
Other/General Submission; Computer Science Program; Computational Bioscience Research Center (CBRC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorBoudellioua, Imeneen
dc.contributor.authorKulmanov, Maxaten
dc.contributor.authorSchofield, Paul Nen
dc.contributor.authorGkoutos, Georgios Ven
dc.contributor.authorHoehndorf, Roberten
dc.date.accessioned2018-05-10T08:56:42Z-
dc.date.available2018-05-10T08:56:42Z-
dc.date.issued2018-05-02en
dc.identifier.citationBoudellioua I, Kulmanov M, Schofield PN, Gkoutos GV, Hoehndorf R (2018) DeepPVP: phenotype-based prioritization of causative variants using deep learning. Available: http://dx.doi.org/10.1101/311621.en
dc.identifier.doi10.1101/311621en
dc.identifier.urihttp://hdl.handle.net/10754/627821-
dc.description.abstractBackground: 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.en
dc.description.sponsorshipThis work was supported by funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3454-01-01 and FCC/1/1976-08-01. GVG acknowledges support from H2020-EINFRA (731075) and the National Science Foundation (IOS:1340112) as well as support from the NIHR Birmingham ECMC, NIHR Birmingham SRMRC and the NIHR Birmingham Biomedical Research Centre and the MRC HDR UK. The views expressed in this publication are those of the authors and not necessarily those of the NHS, the National Institute for Health Research, the Medical Research Council or the Department of Health.en
dc.publisherCold Spring Harbor Laboratoryen
dc.relation.urlhttps://www.biorxiv.org/content/early/2018/05/02/311621en
dc.rightsThe copyright holder for this preprint is the author/funder. It is made available under a CC-BY-NC 4.0 International license.en
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/en
dc.titleDeepPVP: phenotype-based prioritization of causative variants using deep learningen
dc.typeWorking Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentComputational Bioscience Research Center (CBRC)en
dc.eprint.versionPre-printen
dc.contributor.institutionDepartment of Physiology, Development & Neuroscience, University of Cambridge, Downing Street, CB2 3EG Cambridge, United Kingdomen
dc.contributor.institutionMRC Health Data Research UK, B15 2TT Birmingham, United Kingdomen
dc.contributor.institutionNIHR Biomedical Research Centre, B15 2TT Birmingham, United Kingdomen
dc.contributor.institutionNIHR Surgical Reconstruction and Microbiology, B15 2TT Birmingham, United Kingdomen
dc.contributor.institutionNIHR Experimental Cancer Medicine Centre, B15 2TT Birmingham, United Kingdomen
dc.contributor.institutionInstitute of Translational Medicine, University Hospitals Birmingham, NHS Foundation Trust, B15 2TT Birmingham, United Kingdomen
dc.contributor.institutionCollege of Medical and Dental Sciences, Institute of Cancer and Genomic Sciences, Centre for Computational Biology, University of Birmingham, B15 2TT Birmingham, United Kingdomen
kaust.authorBoudellioua, Imeneen
kaust.authorKulmanov, Maxaten
kaust.authorHoehndorf, Roberten
kaust.grant.numberURF/1/3454-01-01en
kaust.grant.numberFCC/1/1976-08-01en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.