Identification, crystallization and epitope determination of public TCR shared and expanded in COVID-19 patients

Lu, Xiuyuan; Hosono, Yuki; Ishizuka, Shigenari; Nagae, Masamichi; Ishikawa, Eri; Motooka, Daisuke; Ozaki, Yuki; Sax, Nicolas; Shinnakasu, Ryo; Inoue, Takeshi; Onodera, Taishi; Matsumoto, Takayuki; Shinkai, Masaharu; Sato, Takashi; Nakamura, Shota; Mori, Shunsuke; Kanda, Teru; Nakayama, Emi E.; Shioda, Tatsuo; Kurosaki, Tomohiro; Arase, Hisashi; Yamashita, Kazuo; Takahashi, Yoshimasa; Yamasaki, Satoshi

doi:10.1101/2021.03.23.436573

Cited by 1 publication

(3 citation statements)

References 46 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We applied our predictive model to a recently published Covid-19 dataset [35], evaluating its efficacy in predicting TCR-peptide interactions in a real-life setting. As described in the Methods section, peptides from each Mean and standard deviation (for the 39 structures) of the proportion of residues that satisfy the property shown in the first column.…”

Section: Covid-19 Prediction Experiments Resultsmentioning

confidence: 99%

“…In the second experiment, we retrained the model using all available data and applied it to a dataset of TCR-peptide pairs of known 3D structures, performing statistical analyses of cross-attention values to detail the biochemical binding event. Finally, in the third experiment, the model was applied to a recently published Covid-19 dataset [35] to assess its generalizability in a real-world setting.…”

Section: Study Overview and Experiments Typesmentioning

confidence: 99%

“…To evaluate how accurately our model would perform in a realistic situation, we applied it to prediction tasks of a real-world Covid-19 dataset generated from the Covid-19 study [35]. A virtual dataset was created using the TCRs pairs and peptides taken from the S(Spike) protein.…”

Section: Covid-19 Datasets and Experimentsmentioning

confidence: 99%

See 2 more Smart Citations

Attention network for predicting T cell receptor-peptide binding can associate attention with interpretable protein structural properties

Koyama¹,

Hashimoto

Nagao

et al. 2023

Preprint

View full text Add to dashboard Cite

Motivation: Understanding how a T cell receptor (TCR) recognizes its specific ligand peptide is crucial for gaining insight into biological functions and disease mechanisms. Despite its importance, experimentally determining TCR-peptide interactions can be expensive and time-consuming. To address this challenge, several computational methods have been proposed, but none have incorporated an attention layer from language models in conjunction with TCR-peptide "structural" binding mechanisms. Results: In this study, we developed a machine learning model based on a modified version of the transformer, a cross-attention neural network, to predict TCR-peptide binding solely based on protein sequences. This model achieved state-of-the-art performance as measured by the ROCAUC score on a benchmark dataset of TCR-peptide binding. Furthermore, by analyzing the results of binding predictions, we associated the neural network weights with protein structural properties. By classifying the residues into large and small attention groups, we identified statistically significant properties associated with the largely attended residues, such as hydrogen-bond connections within the TCR. This ability to provide an interpretable prediction of TCR-peptide binding should increase our knowledge of molecular recognition and pave the way to designing new therapeutics.

show abstract

Section: Covid-19 Prediction Experiments Resultsmentioning

confidence: 99%

Section: Study Overview and Experiments Typesmentioning

confidence: 99%