Show simple item record

dc.contributor.authorBryant, Drew H
dc.contributor.authorBashir, Ali
dc.contributor.authorSinai, Sam
dc.contributor.authorJain, Nina K
dc.contributor.authorOgden, Pierce J
dc.contributor.authorRiley, Patrick F
dc.contributor.authorChurch, George M
dc.contributor.authorColwell, Lucy J
dc.contributor.authorKelsic, Eric D
dc.date.accessioned2021-03-23T00:31:19Z
dc.date.available2021-03-23T00:31:19Z
dc.date.issued2021-06
dc.identifier.issn1087-0156
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/319086
dc.description.abstractModern experimental technologies can assay large numbers of biological sequences, but engineered protein libraries rarely exceed the sequence diversity of natural protein families. Machine learning (ML) models trained directly on experimental data without biophysical modeling provide one route to accessing the full potential diversity of engineered proteins. Here we apply deep learning to design highly diverse adeno-associated virus 2 (AAV2) capsid protein variants that remain viable for packaging of a DNA payload. Focusing on a 28-amino acid segment, we generated 201,426 variants of the AAV2 wild-type (WT) sequence yielding 110,689 viable engineered capsids, 57,348 of which surpass the average diversity of natural AAV serotype sequences, with 12-29 mutations across this region. Even when trained on limited data, deep neural network models accurately predict capsid viability across diverse variants. This approach unlocks vast areas of functional but previously unreachable sequence space, with many potential applications for the generation of improved viral vectors and protein therapeutics.
dc.format.mediumPrint-Electronic
dc.languageeng
dc.publisherSpringer Science and Business Media LLC
dc.rightsAll rights reserved
dc.subjectHela Cells
dc.subjectHumans
dc.subjectDependovirus
dc.subjectCapsid Proteins
dc.subjectGenetic Vectors
dc.subjectMachine Learning
dc.titleDeep diversification of an AAV capsid protein by machine learning.
dc.typeArticle
prism.endingPage696
prism.issueIdentifier6
prism.publicationDate2021
prism.publicationNameNat Biotechnol
prism.startingPage691
prism.volume39
dc.identifier.doi10.17863/CAM.66202
dcterms.dateAccepted2020-12-08
rioxxterms.versionofrecord10.1038/s41587-020-00793-4
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2021-06
dc.contributor.orcidBryant, Drew H [0000-0001-7781-7033]
dc.contributor.orcidRiley, Patrick F [0000-0003-0797-0272]
dc.contributor.orcidChurch, George M [0000-0003-3535-2076]
dc.contributor.orcidColwell, Lucy J [0000-0003-3148-0337]
dc.identifier.eissn1546-1696
rioxxterms.typeJournal Article/Review
cam.issuedOnline2021-02-11
cam.orpheus.successMon Mar 29 07:30:27 BST 2021 - Embargo updated
rioxxterms.freetoread.startdate2021-08-11


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record