Cinelli, Mattia;
(2019)
Analysis of murine CDR3β repertoires using machine learning techniques.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Mattia Cinelli - Thesis.pdf - Accepted Version Download (4MB) | Preview |
Abstract
This thesis presents my research on the development and application of state-of- the-art machine learning methods for the classification and analysis of murine complementarity-determining regions 3 (CDR3) repertoires. Using classification methods, I investigated the role and mechanisms of the CDR3 protein sequence. These are short protein regions present on the T-cell receptor (TCR), and I have aimed to identify the amino acids and positions that play a major role in the TCR, allowing it to recognise specific antigens and to activate the adaptive immune response . The analyses performed are based on three different methods of machine learning: (i) The Support Vector Machine, used to carry out the classification analysis; (ii) An application of Bayesian theory, to isolate the most relevant CDR3 features; (iii) Markov chain and Hidden Markov Models, to study the variability of the repertoires and to identify specific regions of interest within the CDR3. All of these methods have proved useful and have helped me to identify different features of the CDR3 repertoires. Indeed, specific position and combination of amino acid have been identified and considered relevant for repertoires classification. It has been detected the presence of three different levels of emerging conserved-areas in the CDR3, and investigated the role of the glycine and other amino acids within motifs and putative interaction site. Although the biological mechanisms of CDR3 are still not fully understood, my contribution to the field has been to increase our understanding of CDR3, including the identification of relevant position for the CDR3 interaction; motifs and patterns for the different groups of mice repertoires; and an improved overall classification of such repertoires.
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Analysis of murine CDR3β repertoires using machine learning techniques |
| Event: | UCL (University College London) |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2019. Original content in this thesis is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Infection and Immunity |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10069442 |
Archive Staff Only
 |
View Item |
