Show simple item record

dc.contributor.authorOrhobor, Oghenejokpeme I
dc.contributor.authorRehim, Abbi Abdel
dc.contributor.authorLou, Hang
dc.contributor.authorNi, Hao
dc.contributor.authorKing, Ross
dc.date.accessioned2022-05-10T12:00:06Z
dc.date.available2022-05-10T12:00:06Z
dc.date.issued2022-05
dc.date.submitted2021-11-08
dc.identifier.issn2054-5703
dc.identifier.otherrsos211745
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/336970
dc.description.abstractThe representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes.
dc.languageen
dc.publisherThe Royal Society
dc.subjectBiochemistry, cellular and molecular biology
dc.subjectResearch articles
dc.subjectmachine learning
dc.subjectprotein binding affinity prediction
dc.subjectscoring functions
dc.titleA simple spatial extension to the extended connectivity interaction features for binding affinity prediction.
dc.typeArticle
dc.date.updated2022-05-10T12:00:06Z
prism.issueIdentifier5
prism.publicationNameR Soc Open Sci
prism.volume9
dc.identifier.doi10.17863/CAM.84394
dcterms.dateAccepted2022-04-13
rioxxterms.versionofrecord10.1098/rsos.211745
rioxxterms.versionAO
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidOrhobor, Oghenejokpeme I [0000-0003-1178-611X]
dc.contributor.orcidKing, Ross [0000-0001-7208-4387]
dc.identifier.eissn2054-5703
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/R022925/1)


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record