Show simple item record

dc.contributor.authorSeal, Srijiten
dc.contributor.authorYang, Hongbinen
dc.contributor.authorVollmers, Luisen
dc.contributor.authorBender, Andreasen
dc.date.accessioned2021-01-26T00:30:42Z
dc.date.available2021-01-26T00:30:42Z
dc.date.issued2021-02en
dc.identifier.issn0893-228X
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/316673
dc.description.abstractCell morphology features, such as from the Cell Painting assay, can be generated at relatively low cost and represent versatile biological descriptors of a system, and thereby compound response. In this study, we explored cell morphology descriptors and molecular fingerprints, separately and in combination, for the prediction of cytotoxicity- and proliferation-related in vitro assay endpoints. We selected 135 compounds from the MoleculeNet ToxCast benchmark dataset which were annotated with Cell Painting readouts, where the relatively small size of the dataset is due to the overlap of required annotations. We trained Random Forest classification models using nested cross-validation and Cell Painting descriptors, Morgan and ErG fingerprints, and their combinations. When using leave-one-cluster-out cross validation (with clusters based on physicochemical descriptors), models using Cell Painting descriptors achieved higher average performance over all assays (Balanced Accuracy of 0.65, Matthews Correlation Coefficient of 0.28 and AUC-ROC of 0.71) compared to models using ErG fingerprints (BA 0.55, MCC 0.09 and AUC-ROC 0.60) and Morgan fingerprints alone (BA 0.54, MCC 0.06 and AUC-ROC: 0.56). When using random shuffle splits, the combination of Cell Painting descriptors with ErG and Morgan fingerprints further improved balanced accuracy on average by 8.9% (in 9 out of 12 assays) and 23.4% (in 8 out of 12 assays) compared to using only ErG and Morgan fingerprints, respectively. Regarding feature importance, Cell Painting descriptors related to nuclei texture, granularity of cells and cytoplasm, as well as cell neighbours and radial distributions were identified to be most contributing, which is plausible given the endpoint considered. We conclude that cell morphological descriptors contain complementary information to molecular fingerprints which can be used to improve the performance of predictive cytotoxicity models, in particular in areas of novel structural space.
dc.format.mediumPrint-Electronicen
dc.languageengen
dc.publisherAmerican Chemical Society
dc.rightsAll rights reserved
dc.subjectCell Lineen
dc.subjectHumansen
dc.subjectPhosphate-Binding Proteinsen
dc.subjectCell Proliferationen
dc.subjectAlgorithmsen
dc.subjectTranscriptional Regulator ERGen
dc.titleComparison of Cellular Morphological Descriptors and Molecular Fingerprints for the Prediction of Cytotoxicity- and Proliferation-Related Assays.en
dc.typeArticle
prism.endingPage437
prism.issueIdentifier2en
prism.publicationDate2021en
prism.publicationNameChemical research in toxicologyen
prism.startingPage422
prism.volume34en
dc.identifier.doi10.17863/CAM.63786
dcterms.dateAccepted2021-01-18en
rioxxterms.versionofrecord10.1021/acs.chemrestox.0c00303en
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2021-02en
dc.contributor.orcidSeal, Srijit [0000-0003-2790-8679]
dc.contributor.orcidYang, Hongbin [0000-0001-6740-1632]
dc.contributor.orcidBender, Andreas [0000-0002-6683-7546]
dc.identifier.eissn1520-5010
rioxxterms.typeJournal Article/Reviewen
cam.orpheus.successMon Feb 08 07:30:35 GMT 2021 - Embargo updated*
cam.orpheus.counter1*
rioxxterms.freetoread.startdate2022-02-28


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record