Show simple item record

dc.contributor.authorTan, Jie
dc.contributor.authorDoing, Georgia
dc.contributor.authorLewis, Kimberley A.
dc.contributor.authorPrice, Courtney E.
dc.contributor.authorChen, Kathleen M.
dc.contributor.authorHogan, Deborah A.
dc.contributor.authorGreene, Casey S.
dc.contributor.authorCady, Kyle
dc.contributor.authorPerchuk, Barrett
dc.contributor.authorLaub, Michael T
dc.date.accessioned2018-07-03T13:31:59Z
dc.date.available2018-07-03T13:31:59Z
dc.date.issued2017-07
dc.date.submitted2017-04
dc.identifier.issn24054712
dc.identifier.urihttp://hdl.handle.net/1721.1/116746
dc.description.abstractCross-experiment comparisons in public data compendia are challenged by unmatched conditions and technical noise. The ADAGE method, which performs unsupervised integration with denoising autoencoder neural networks, can identify biological patterns, but because ADAGE models, like many neural networks, are over-parameterized, different ADAGE models perform equally well. To enhance model robustness and better build signatures consistent with biological pathways, we developed an ensemble ADAGE (eADAGE) that integrated stable signatures across models. We applied eADAGE to a compendium of Pseudomonas aeruginosa gene expression profiling experiments performed in 78 media. eADAGE revealed a phosphate starvation response controlled by PhoB in media with moderate phosphate and predicted that a second stimulus provided by the sensor kinase, KinB, is required for this PhoB activation. We validated this relationship using both targeted and unbiased genetic approaches. eADAGE, which captures stable biological patterns, enables cross-experiment comparisons that can highlight measured but undiscovered relationships.en_US
dc.description.sponsorshipGordon and Betty Moore Foundation (GBMF 4552)en_US
dc.description.sponsorshipNational Institutes of Health (U.S.) (grant R01-AI091702)en_US
dc.description.sponsorshipCystic Fibrosis Foundation (STANTO15R0)en_US
dc.publisherElsevier BVen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/J.CELS.2017.06.003en_US
dc.rightsCreative Commons Attribution 4.0 International Licenseen_US
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_US
dc.sourceElsevieren_US
dc.titleUnsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networksen_US
dc.typeArticleen_US
dc.identifier.citationTan, Jie, Georgia Doing, Kimberley A. Lewis, Courtney E. Price, Kathleen M. Chen, Kyle C. Cady, Barret Perchuk, Michael T. Laub, Deborah A. Hogan, and Casey S. Greene. “Unsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networks.” Cell Systems 5, no. 1 (July 2017): 63–71.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Biologyen_US
dc.contributor.mitauthorCady, Kyle
dc.contributor.mitauthorPerchuk, Barrett
dc.contributor.mitauthorLaub, Michael T
dc.relation.journalCell Systemsen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2018-06-28T18:07:41Z
dspace.orderedauthorsTan, Jie; Doing, Georgia; Lewis, Kimberley A.; Price, Courtney E.; Chen, Kathleen M.; Cady, Kyle C.; Perchuk, Barret; Laub, Michael T.; Hogan, Deborah A.; Greene, Casey S.en_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-8288-7607
mit.licensePUBLISHER_CCen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record