Journal
COMMUNICATIONS BIOLOGY
Volume 4, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s42003-021-02610-3
Keywords
-
Categories
Funding
- Independent research fund Denmark [DFF-7014-00055]
- Federal funds from the National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services [HHSN272201200010CERC]
- StG NextDART [677268]
- Lundbeck Foundation Experiment [R324-2019-1671]
Ask authors/readers for more resources
Predicting T-cell receptor interactions with MHC-peptide complexes is challenging due to factors like data accuracy, scarcity, and problem complexity. Shallow CNN architectures show promise in handling the complexity caused by TCR length variations. Accurate and sufficient paired TCR sequence data can predict T-cell specificity effectively.
Prediction of T-cell receptor (TCR) interactions with MHC-peptide complexes remains highly challenging. This challenge is primarily due to three dominant factors: data accuracy, data scarceness, and problem complexity. Here, we showcase that shallow convolutional neural network (CNN) architectures are adequate to deal with the problem complexity imposed by the length variations of TCRs. We demonstrate that current public bulk CDR3 beta-pMHC binding data overall is of low quality and that the development of accurate prediction models is contingent on paired alpha/beta TCR sequence data corresponding to at least 150 distinct pairs for each investigated pMHC. In comparison, models trained on CDR3 alpha or CDR3 beta data alone demonstrated a variable and pMHC specific relative performance drop. Together these findings support that T-cell specificity is predictable given the availability of accurate and sufficient paired TCR sequence data. NetTCR-2.0 is publicly available at https://services.healthtech.dtu.dk/service.php?NetTCR-2.0..
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available