The Impact of peptide flanking residues on predicting peptide-MHC-II binding interactions using convolutional Neural Networks

Simple item page
dc.contributor.advisorBah, Bubacarren_ZA
dc.contributor.advisorDegoot, Abdoelnaser M.en_ZA
dc.contributor.advisorNdifon, Wilfreden_ZA
dc.contributor.authorDaumas, Tshenolo Thato Eustaciaen_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Mathematical Sciences (Applied Mathematics)en_ZA
dc.date.accessioned2022-03-11T14:39:59Z
dc.date.accessioned2022-04-29T09:44:19Z
dc.date.available2022-03-11T14:39:59Z
dc.date.available2022-04-29T09:44:19Z
dc.date.issued2022-04
dc.descriptionThesis (MSc)--Stellenbosch University, 2022.en_ZA
dc.description.abstractENGLISH ABSTRACT: Major histocompatibility complex class II (MHC-II) is one of three classes of MHC molecules and is located on the surface of professional antigen presenting cells. MHC-II molecules present antigenic peptides derived from pathogens that cause infection, for recognition by CD4+ T lymphocytes. MHC-II molecules are critical components of the chain of intercellular interactions required for the adaptive im- mune response to be launched successfully, as this chain is thought to begin with the binding of antigenic peptides by MHC-II molecules. While considerable progress in computational efforts have been made towards un- derstanding peptide-MHC interactions for classes I and II, the case for peptide- MHC-II remains challenging due to MHC-II molecules being highly polymorphic and having open-ended binding grooves. Consequently, MHC-II molecules interact with peptides of varying lengths; therefore, the role that peptide flanking residues (PFRs) play in peptide-MHC-II binding interactions must be considered. We pro- pose an allele-specific convolutional neural network model that simulates binding interactions between peptides and MHC-II molecules that also incorporates PFR information in the input. Deep learning models for peptide-MHC-II interactions that have been published, such as the allele-specific model, NetMHCII and the transallelic model NetMHCI- Ipan have demonstrated encouraging predictive performance. When compared, our proposed CNN model outperformed the latest version of the model, NetMHCII-2.3 across all MHC-II alleles considered with mean AUC value of 0.951 as compared with 0.822 for NetMHCII-3.2. Furthermore, we analysed the impact that PFRs have on modelling peptide-MHC-II binding interactions and laid the foundations of de- veloping a transallelic model based on the CNN model.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Groot histoversoenbaarheidskompleks klas II (MHC-II) is een van drie klasse van MHC molekules en is geleë op die oppervlak van professionele antigeen-presenterende selle. MHC-II molekules bied antigeniese peptiede aan wat afkomstig is van pato- gene wat infeksie veroorsaak, vir herkenning deur CD4+ T limfosiete. MHC-II molekules is kritieke komponente van die ketting van intersellulêre interaksies wat nodig is vir die aanpasbare immuunrespons om suksesvol van stapel te stuur, aan- gesien hierdie ketting vermoedelik begin met die binding van antigeniese peptiede deur MHC-II molekules. Terwyl aansienlike vordering in berekeningspogings gemaak is om peptied-MHC interaksies vir klasse I en II te verstaan, bly die saak vir peptied-MHC-II uitdagend as gevolg van MHC-II-molekules wat hoogs polimorf is en oop-einde bindings- groewe het. Gevolglik, MHC-II molekules interaksie met peptiede van verskil- lende lengtes; daarom, moet die rol wat peptied flankerende residue (PFRs) speel in peptied-MHC-II bindende interaksies oorweeg word. Ons stel ’n alleel-spesifieke konvolusionele neurale netwerk model voor wat bindingsinteraksies tussen peptiede en MHC-II molekules simuleer wat ook PFR-inligting in die inset inkorporeer. Diep leer modelle vir peptied-MHC-II interaksies wat gepubliseer is, soos die al- leelspesifieke model, NetMHCII en die transalleliese model, NetMHCIIpan het be- moedigende voorspellende prestasie getoon. As dit vergelyk word, het ons voorge-stelde CNN-model beter gevaar as die nuutste weergawe van die model, NetMHCII- 2.3 oor alle MHC-II allele wat oorweeg word met gemiddelde AUC waarde van 0,951 in vergelyking met 0,822 vir NetMHCII-3.2. Verder het ons die impak wat PFRe het op die modellering van peptied-MHC-II bindingsinteraksies ontleed en die grondslag gelê van die ontwikkeling van ’n transalleliese model gebaseer op die CNN-model.af_ZA
dc.description.versionMastersen_ZA
dc.format.extent80 pagesen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/124973
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectPeptide-MHC-IIen_ZA
dc.subjectUCTDen_ZA
dc.subjectPeptidesen_ZA
dc.subjectNeural networks (Computer science)en_ZA
dc.subjectMajor histocompatibility complexen_ZA
dc.subjectHistocompatibility antigens -- Bindingen_ZA
dc.titleThe Impact of peptide flanking residues on predicting peptide-MHC-II binding interactions using convolutional Neural Networksen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
daumas_impact_2022.pdf
Size:
3.43 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Applied Mathematics)