Show simple item record

2017-01-04Zeitschriftenartikel DOI: 10.1038/srep39194
PaPrBaG: A machine learning approach for the detection of novel pathogens from NGS data
dc.contributor.authorDeneke, Carlus
dc.contributor.authorRentzsch, Robert
dc.contributor.authorRenard, Bernhard Y.
dc.date.accessioned2018-05-07T19:38:55Z
dc.date.available2018-05-07T19:38:55Z
dc.date.created2017-01-16
dc.date.issued2017-01-04none
dc.identifier.otherhttp://edoc.rki.de/oa/articles/re6U6mYBUDWQ/PDF/25fDpe5t1iHbE.pdf
dc.identifier.urihttp://edoc.rki.de/176904/2519
dc.description.abstractThe reliable detection of novel bacterial pathogens from next-generation sequencing data is a key challenge for microbial diagnostics. Current computational tools usually rely on sequence similarity and often fail to detect novel species when closely related genomes are unavailable or missing from the reference database. Here we present the machine learning based approach PaPrBaG (Pathogenicity Prediction for Bacterial Genomes). PaPrBaG overcomes genetic divergence by training on a wide range of species with known pathogenicity phenotype. To that end we compiled a comprehensive list of pathogenic and non-pathogenic bacteria with human host, using various genome metadata in conjunction with a rule-based protocol. A detailed comparative study reveals that PaPrBaG has several advantages over sequence similarity approaches. Most importantly, it always provides a prediction whereas other approaches discard a large number of sequencing reads with low similarity to currently known reference genomes. Furthermore, PaPrBaG remains reliable even at very low genomic coverages. CombiningPaPrBaG with existing approaches further improves prediction results.eng
dc.language.isoeng
dc.publisherRobert Koch-Institut
dc.subject.ddc610 Medizin
dc.titlePaPrBaG: A machine learning approach for the detection of novel pathogens from NGS data
dc.typeperiodicalPart
dc.identifier.urnurn:nbn:de:0257-10050656
dc.identifier.doi10.1038/srep39194
dc.identifier.doihttp://dx.doi.org/10.25646/2444
local.edoc.container-titleScientific Reports
local.edoc.fp-subtypeArtikel
local.edoc.type-nameZeitschriftenartikel
local.edoc.container-typeperiodical
local.edoc.container-type-nameZeitschrift
local.edoc.container-urlhttp://www.nature.com/articles/srep39194
local.edoc.container-publisher-nameNature Publishing Group
local.edoc.container-volume7
local.edoc.container-year2017

Show simple item record