Show simple item record

dc.contributor.authorMervin, Lewis
dc.date.accessioned2018-10-02T14:53:30Z
dc.date.available2018-10-02T14:53:30Z
dc.date.issued2018-09-30
dc.date.submitted2017-10-06
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/283004
dc.description.abstractTarget-based screening projects for bioactive (orphan) compounds have been shown in many cases to be insufficiently predictive for in vivo efficacy, leading to attrition in clinical trials. Phenotypic screening has hence undergone a renaissance in both academia and in the pharmaceutical industry, partly due to this reason. One key shortcoming of this paradigm shift is that the protein targets modulated need to be elucidated subsequently, which is often a costly and time-consuming procedure. In this work, we have explored both improved methods and real-world case studies of how computational methods can help in target elucidation of phenotypic screens. One limitation of previous methods has been the ability to assess the applicability domain of the models, that is, when the assumptions made by a model are fulfilled and which input chemicals are reliably appropriate for the models. Hence, a major focus of this work was to explore methods for calibration of machine learning algorithms using Platt Scaling, Isotonic Regression Scaling and Venn-Abers Predictors, since the probabilities from well calibrated classifiers can be interpreted at a confidence level and predictions specified at an acceptable error rate. Additionally, many current protocols only offer probabilities for affinity, thus another key area for development was to expand the target prediction models with functional prediction (activation or inhibition). This extra level of annotation is important since the activation or inhibition of a target may positively or negatively impact the phenotypic response in a biological system. Furthermore, many existing methods do not utilize the wealth of bioactivity information held for orthologue species. We therefore also focused on an in-depth analysis of orthologue bioactivity data and its relevance and applicability towards expanding compound and target bioactivity space for predictive studies. The realized protocol was trained with 13,918,879 compound-target pairs and comprises 1,651 targets, which has been made available for public use at GitHub. Consequently, the methodology was applied to aid with the target deconvolution of AstraZeneca phenotypic readouts, in particular for the rationalization of cytotoxicity and cytostaticity in the High-Throughput Screening (HTS) collection. Results from this work highlighted which targets are frequently linked to the cytotoxicity and cytostaticity of chemical structures, and provided insight into which compounds to select or remove from the collection for future screening projects. Overall, this project has furthered the field of in silico target deconvolution, by improving the performance and applicability of current protocols and by rationalizing cytotoxicity, which has been shown to influence attrition in clinical trials.
dc.description.sponsorshipBBSRC AstraZeneca
dc.language.isoen
dc.rightsAttribution 4.0 International (CC BY 4.0)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCheminformatics
dc.subjectMode of action
dc.subjectIn silico
dc.subjectProtein Target Prediction
dc.subjectOrthologue
dc.subjectChemical space
dc.subjectAstraZeneca
dc.subjectChemistry Connect
dc.subjectBioactivity data
dc.subjectTarget deconvolution
dc.subjectTarget prediction
dc.subjectMoA
dc.subjectChEMBL
dc.subjectPubChem
dc.subjectFunctional prediction
dc.subjectSphere exclusion
dc.subjectRandom Forest
dc.subjectNaive Bayes
dc.subjectSVM
dc.subjectSupport Vector Machine
dc.subjectAD-AUC
dc.subjectActivation
dc.subjectInhibition
dc.subjectFunctional Effects
dc.subjectMechanism-of-action
dc.subjectMode-of-action
dc.subjectMechanism of action
dc.subjectPhenotypic screens
dc.subjectHigh throughput screens
dc.subjectHigh content screens
dc.subjectPR-AUC
dc.subjectApplicability domain
dc.subjectVenn Abers
dc.subjectPlatt scaling
dc.subjectIsotonic regression scaling
dc.subjectPython
dc.subjectScikit-learn
dc.subjectRDKit
dc.titleImproved In Silico Methods for Target Deconvolution in Phenotypic Screens
dc.typeThesis
dc.type.qualificationlevelDoctoral
dc.type.qualificationnameDoctor of Philosophy (PhD)
dc.publisher.institutionUniversity of Cambridge
dc.publisher.departmentChemistry
dc.date.updated2018-09-07T12:04:24Z
dc.identifier.doi10.17863/CAM.30369
dc.contributor.orcidMervin, Lewis [0000-0002-7271-0824]
dc.publisher.collegeKing's College
dc.type.qualificationtitlePhD in Chemistry
cam.supervisorBender, Andreas
cam.supervisorEngkvist, Ola
cam.supervisor.orcidBender, Andreas [0000-0002-6683-7546]
cam.supervisor.orcidEngkvist, Ola [0000-0003-4970-6461]
cam.thesis.fundingfalse


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY 4.0)