NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data

Research output: Contribution to journalJournal articlepeer-review

Standard

NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data. / Montemurro, Alessandro; Schuster, Viktoria; Povlsen, Helle Rus; Bentzen, Amalie Kai; Jurtz, Vanessa; Chronister, William D.; Crinklaw, Austin; Hadrup, Sine R.; Winther, Ole; Peters, Bjoern; Jessen, Leon Eyrich; Nielsen, Morten.

In: Communications Biology , Vol. 4, 1060, 2021.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Montemurro, A, Schuster, V, Povlsen, HR, Bentzen, AK, Jurtz, V, Chronister, WD, Crinklaw, A, Hadrup, SR, Winther, O, Peters, B, Jessen, LE & Nielsen, M 2021, 'NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data', Communications Biology , vol. 4, 1060. https://doi.org/10.1038/s42003-021-02610-3

APA

Montemurro, A., Schuster, V., Povlsen, H. R., Bentzen, A. K., Jurtz, V., Chronister, W. D., Crinklaw, A., Hadrup, S. R., Winther, O., Peters, B., Jessen, L. E., & Nielsen, M. (2021). NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data. Communications Biology , 4, [1060]. https://doi.org/10.1038/s42003-021-02610-3

Vancouver

Montemurro A, Schuster V, Povlsen HR, Bentzen AK, Jurtz V, Chronister WD et al. NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data. Communications Biology . 2021;4. 1060. https://doi.org/10.1038/s42003-021-02610-3

Author

Montemurro, Alessandro ; Schuster, Viktoria ; Povlsen, Helle Rus ; Bentzen, Amalie Kai ; Jurtz, Vanessa ; Chronister, William D. ; Crinklaw, Austin ; Hadrup, Sine R. ; Winther, Ole ; Peters, Bjoern ; Jessen, Leon Eyrich ; Nielsen, Morten. / NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data. In: Communications Biology . 2021 ; Vol. 4.

Bibtex

@article{fdc9a2ed9aae45d8a499a91297743c12,
title = "NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data",
abstract = "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..",
author = "Alessandro Montemurro and Viktoria Schuster and Povlsen, {Helle Rus} and Bentzen, {Amalie Kai} and Vanessa Jurtz and Chronister, {William D.} and Austin Crinklaw and Hadrup, {Sine R.} and Ole Winther and Bjoern Peters and Jessen, {Leon Eyrich} and Morten Nielsen",
year = "2021",
doi = "10.1038/s42003-021-02610-3",
language = "English",
volume = "4",
journal = "Communications Biology",
issn = "2399-3642",
publisher = "nature publishing group",

}

RIS

TY - JOUR

T1 - NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data

AU - Montemurro, Alessandro

AU - Schuster, Viktoria

AU - Povlsen, Helle Rus

AU - Bentzen, Amalie Kai

AU - Jurtz, Vanessa

AU - Chronister, William D.

AU - Crinklaw, Austin

AU - Hadrup, Sine R.

AU - Winther, Ole

AU - Peters, Bjoern

AU - Jessen, Leon Eyrich

AU - Nielsen, Morten

PY - 2021

Y1 - 2021

N2 - 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..

AB - 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..

U2 - 10.1038/s42003-021-02610-3

DO - 10.1038/s42003-021-02610-3

M3 - Journal article

C2 - 34508155

VL - 4

JO - Communications Biology

JF - Communications Biology

SN - 2399-3642

M1 - 1060

ER -

ID: 280236370