Master Thesis - meTCRs: Learning a distance metric for T cell receptor sequences

Technische Universität München
January 01, 2023
Contact:N/A
Offerd Salary:Negotiation
Location:N/A
Working address:N/A
Contract Type:Other
Working Time:Negotigation
Working type:N/A
Ref info:N/A
Master Thesis - meTCRs: Learning a distance metric for T cell receptor

sequences

29.11.2022, Studentische Hilfskräfte, Praktikantenstellen, Studienarbeiten

Antigen recognition by T cells plays a crucial role in the adaptive immune system of vertebrates. Pathogen-derived peptides - so-called epitopes - are bound by the Major Histocompatibility Complex (MHC). Upon recognition of this joint complex by the highly variable T cell receptors (TCRs), T cells are activated and initiate the adaptive immune response. Determining TCR- epitope specificity from experimentally measured sequences in silico can directly benefit the development of vaccines and personalized medicine 1. Multiple sequence-based distance metrics have been developed to compare repertoires of TCRs based on different methods such as string alignment 2,3, edit distances 4, and autoencoder embeddings 5. We recently developed meTCRs (NIPS, LMRL workshop 2022, 6), which incorporates a task-specific objective by training on TCRs-epitope pairs through Deep Metric Learning. In this project, you will further improve the existing model by experimenting with different representation learning approaches, incorporating additional TCR information, and deriving better evaluation strategies.

Goals:

Adapt and apply representation learning concepts and deep learning architectures Improve the performance of the existing models Define meaningful benchmarking scenarios and metrics Benchmark the developed approach against existing methods

Public databases:

  • IEDB (https: // www. iedb.org/)
  • VDJdb (https: // vdjdb.cdr3.net/)
  • McPAS (https:// friedmanlab.weizmann.ac.il/McPAS-TCR/)
  • ImmuneRace (https: // immunerace.adaptivebiotech.com/half-billion-tcr-beta- sequenced-released/)
  • Suggested Reading:

    1 Mösch, A., Raffegerst, S., Weis, M., Schendel, D., & Frishman, D. (2019). Machine Learning for Cancer Immunotherapies Based on Epitope Recognition by T Cell Receptors. Frontiers in Genetics, 10, 1141.

    2 Dash P, Fiore-Gartland AJ, Hertz T, Wang GC, Sharma S, Souquette A, et al. Quantifiable predictive features define epitope-specific T cell receptor repertoires. Nature. 2017;547(7661):89-93.

    3 Thakkar N, Bailey-Kellogg C. Balancing sensitivity and specificity in distinguishing TCR groups by CDR sequence similarity. BMC Bioinformatics. 2019.

    4 Chronister WD, Crinklaw A, Mahajan S, Vita R, Koşaloğlu-Yalçın Z, Yan Z, et al. TCRMatch: Predicting T-Cell Receptor Specificity Based on Sequence Similarity to Previously Characterized Receptors. 2021.

    5 Sidhom, JW., Larman, H.B., Pardoll, D.M., Baras A.S. (2021). DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires. Nat Commun, 12, 1605.

    6 Drost, F., Schiefelbein, L., Schubert, B. (2022). meTCRs - Learning a metric for T-cell receptor. bioRxiv.

    Kontakt: felix.drost@helmholtz-muenchen.de, benjamin.schubert@helmholtz- muenchen.de

    From this employer

    Recent blogs

    Recent news