Forskning
Udskriv Udskriv
Switch language
Rigshospitalet - en del af Københavns Universitetshospital
Udgivet

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

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Evaluation of commercially available glucagon receptor antibodies and glucagon receptor expression

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Copy number variants as modifiers of breast cancer risk for BRCA1/BRCA2 pathogenic variant carriers

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. ANGPTL7, a therapeutic target for increased intraocular pressure and glaucoma

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Neutrophils dominate in opsonic phagocytosis of P. falciparum blood-stage merozoites and protect against febrile malaria

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. DeepLoc 2.0: Multi-label subcellular localization prediction using protein language models

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. NetSurfP-3.0: accurate and fast prediction of protein structural features by protein language models and deep learning

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. SignalP 6.0 predicts all five types of signal peptides using protein language models

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Calibrated uncertainty for molecular property prediction using ensembles of message passing neural networks

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • Alessandro Montemurro
  • Viktoria Schuster
  • Helle Rus Povlsen
  • Amalie Kai Bentzen
  • Vanessa Jurtz
  • William D Chronister
  • Austin Crinklaw
  • Sine R Hadrup
  • Ole Winther
  • Bjoern Peters
  • Leon Eyrich Jessen
  • Morten Nielsen
Vis graf over relationer

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 CDR3β-pMHC binding data overall is of low quality and that the development of accurate prediction models is contingent on paired α/β TCR sequence data corresponding to at least 150 distinct pairs for each investigated pMHC. In comparison, models trained on CDR3α or CDR3β 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 .

OriginalsprogEngelsk
Artikelnummer1060
TidsskriftCommunications biology
Vol/bind4
Udgave nummer1
Sider (fra-til)1060
ISSN2399-3642
DOI
StatusUdgivet - 10 sep. 2021

Bibliografisk note

© 2021. The Author(s).

ID: 74851237