Repository logo
 

Prospectively Validated Proteochemometric Models for the Prediction of Small-Molecule Binding to Bromodomain Proteins.

cam.issuedOnline2018-09-07
dc.contributor.authorGiblin, Kathryn A
dc.contributor.authorHughes, Samantha J
dc.contributor.authorBoyd, Helen
dc.contributor.authorHansson, Pia
dc.contributor.authorBender, Andreas
dc.contributor.orcidGiblin, Kathryn A [0000-0003-2446-6326]
dc.contributor.orcidBender, Andreas [0000-0002-6683-7546]
dc.date.accessioned2018-11-14T00:31:25Z
dc.date.available2018-11-14T00:31:25Z
dc.date.issued2018-09-24
dc.description.abstractThe bromodomain-containing proteins are a ligandable family of epigenetic readers, which play important roles in oncological, cardiovascular, and inflammatory diseases. Achieving selective inhibition of specific bromodomains is challenging, due to the limited understanding of compound and target selectivity features. In this study we build and benchmark proteochemometric (PCM) classification models on bioactivity data for 15,350 data points across 31 bromodomains, using both compound fingerprints and binding site protein descriptors as input variables, achieving a maximum performance as measured by the Matthew's Correlation Coefficient (MCC) of 0.83 on the external test set. We also find that histone peptide binding data can be used as a target descriptor to build a high performing PCM model (MCC 0.80), showing the transferability of peptide interaction information to modeling small-molecule bioactivity. 1,139 compounds were selected for prospective experimental testing by performing a virtual screen using model predictions and implementing conformal prediction, which resulted in 319 correctly predicted compound-target pair actives and the correct prediction for certain selectivity profile combinations of the four bromodomains tested against. We identify that conformal prediction can be used to fine-tune the balance between hit retrieval and hit structural diversity in a virtual screening setting. PCM can be applied to future virtual screening and compound design, including off-target prediction for bromodomains.
dc.format.mediumPrint-Electronic
dc.identifier.doi10.17863/CAM.32420
dc.identifier.eissn1549-960X
dc.identifier.issn1549-9596
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/285050
dc.languageeng
dc.language.isoeng
dc.publisherAmerican Chemical Society (ACS)
dc.publisher.urlhttp://dx.doi.org/10.1021/acs.jcim.8b00400
dc.subjectBinding Sites
dc.subjectComputer Simulation
dc.subjectDrug Discovery
dc.subjectHumans
dc.subjectModels, Chemical
dc.subjectModels, Molecular
dc.subjectNuclear Proteins
dc.subjectProtein Binding
dc.subjectProtein Conformation
dc.subjectQuantitative Structure-Activity Relationship
dc.subjectReproducibility of Results
dc.titleProspectively Validated Proteochemometric Models for the Prediction of Small-Molecule Binding to Bromodomain Proteins.
dc.typeArticle
dcterms.dateAccepted2018-08-20
prism.endingPage1888
prism.issueIdentifier9
prism.publicationDate2018
prism.publicationNameJ Chem Inf Model
prism.startingPage1870
prism.volume58
pubs.funder-project-idEuropean Research Council (336159)
rioxxterms.licenseref.startdate2018-09-07
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.typeJournal Article/Review
rioxxterms.versionAM
rioxxterms.versionofrecord10.1021/acs.jcim.8b00400

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
Manuscript_JCIM_final_revisions.docx
Size:
1.91 MB
Format:
Microsoft Word XML
Description:
Accepted version
Licence
http://www.rioxx.net/licenses/all-rights-reserved
No Thumbnail Available
Name:
Supplementary_information_JCIM_revised.docx
Size:
2.23 MB
Format:
Microsoft Word XML
Description:
Supporting information
Licence
http://www.rioxx.net/licenses/all-rights-reserved
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
DepositLicenceAgreementv2.1.pdf
Size:
150.9 KB
Format:
Adobe Portable Document Format