NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data.
NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCRα and β sequence data.
复制标题
DOI：
10.1038/s42003-021-02610-3
复制
发表时间：
2021-09-10
影响因子：
5.9
通讯作者：
Nielsen M
中科院分区：
文献类型：
--
作者：
Montemurro A;Schuster V;Povlsen HR;Bentzen AK;Jurtz V;Chronister WD;Crinklaw A;Hadrup SR;Winther O;Peters B;Jessen LE;Nielsen M
预测T细胞受体（TCR）与MHC-肽复合物的相互作用仍然具有高度挑战性。这一挑战主要是由于三个主要因素：数据准确性、数据稀缺性和问题复杂性。在这里，我们展示了“浅”卷积神经网络（CNN）架构足以处理TCR长度变化带来的问题复杂性。我们证明，目前公开的大量CDR 3 β-pMHC结合数据总体质量较低，准确预测模型的开发取决于配对的α/β TCR序列数据，这些数据对应于每种研究的pMHC的至少150个不同对。相比之下，仅在CDR 3 α或CDR 3 β数据上训练的模型表现出可变的和pMHC特异性的相对性能下降。总之，这些发现支持T细胞特异性是可预测的，因为有准确和足够的配对TCR序列数据。NetTCR-2.0可在https://services.healthtech.dtu.dk/service.php?上公开获取NetTCR-2.0。Montemurro等人提出了NetTCR-2.0，这是一种基于卷积神经网络的工具，用于预测T细胞受体和MHC-肽复合物之间的相互作用。该工具表明，当结合使用CDR 3 α或CDR 3 β结合数据时，可进行最佳预测。
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. Montemurro et al. present NetTCR-2.0, a convolutional neural network-based tool for predicting the interactions between T cell receptors and MHC-peptide complexes. This tool demonstrates that the best predictions are made when CDR3 α or CDR3 β binding data are used in combination.
登录
查看更多内容
DOI：
10.1073/pnas.89.22.10915
发表时间：
1992-11-15
影响因子：
11.1
作者：
HENIKOFF, S;HENIKOFF, JG
通讯作者：
HENIKOFF, JG
影响因子：
7.3
作者：
Gielis, Sofie;Maris, Pieter;Meysman, Pieter
通讯作者：
Meysman, Pieter
影响因子：
14.8
作者：
Rodenko, Boris;Toebes, Mireille;Ovaa, Huib
通讯作者：
Ovaa, Huib
影响因子：
3.7
作者：
Klinger M;Pepin F;Wilkins J;Asbury T;Wittkop T;Zheng J;Moorhead M;Faham M
通讯作者：
Faham M
影响因子：
30.5
作者：
Feng, Dan;Bond, Christopher J.;Garcia, K. Christopher
通讯作者：
Garcia, K. Christopher