Show simple item record

dc.contributor.authorAngenent-Mari, Nicolaas M
dc.contributor.authorGarruss, Alexander S
dc.contributor.authorSoenksen, Luis R
dc.contributor.authorChurch, George
dc.contributor.authorCollins, James J
dc.date.accessioned2021-10-27T20:31:08Z
dc.date.available2021-10-27T20:31:08Z
dc.date.issued2020
dc.identifier.urihttps://hdl.handle.net/1721.1/136157
dc.description.abstractEngineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these synthetic biology components remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Here, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesize and characterize in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperform (R = 0.43–0.70) previous state-of-the-art thermodynamic and kinetic models (R = 0.04–0.15) and allow for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This work shows that deep learning approaches can be used for functionality predictions and insight generation in RNA synthetic biology. 2 2en_US
dc.language.isoen
dc.publisherSpringer Science and Business Media LLCen_US
dc.relation.isversionof10.1038/S41467-020-18677-1en_US
dc.rightsCreative Commons Attribution 4.0 International licenseen_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.sourceNatureen_US
dc.titleA deep learning approach to programmable RNA switchesen_US
dc.typeArticleen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Biological Engineering
dc.contributor.departmentMassachusetts Institute of Technology. Institute for Medical Engineering & Science
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineering
dc.contributor.departmentHarvard University--MIT Division of Health Sciences and Technology
dc.relation.journalNature Communicationsen_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.updated2021-08-25T18:06:33Z
dspace.orderedauthorsAngenent-Mari, NM; Garruss, AS; Soenksen, LR; Church, G; Collins, JJen_US
dspace.date.submission2021-08-25T18:06:36Z
mit.journal.volume11en_US
mit.journal.issue1en_US
mit.licensePUBLISHER_CC
mit.metadata.statusAuthority Work and Publication Information Needed


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record