scholarly journals Improved methods for predicting peptide binding affinity to MHC class II molecules

Immunology ◽  
2018 ◽  
Vol 154 (3) ◽  
pp. 394-406 ◽  
Author(s):  
Kamilla Kjaergaard Jensen ◽  
Massimo Andreatta ◽  
Paolo Marcatili ◽  
Søren Buus ◽  
Jason A. Greenbaum ◽  
...  
2021 ◽  
Author(s):  
Ronghui You ◽  
Wei Qu ◽  
Hiroshi Mamitsuka ◽  
Shanfeng Zhu

Computationally predicting MHC-peptide binding affinity is an important problem in immunological bioinformatics. Recent cutting-edge deep learning-based methods for this problem are unable to achieve satisfactory performance for MHC class II molecules. This is because such methods generate the input by simply concatenating the two given sequences: (the estimated binding core of) a peptide and (the pseudo sequence of) an MHC class II molecule, ignoring the biological knowledge behind the interactions of the two molecules. We thus propose a binding core-aware deep learning-based model, DeepMHCII, with binding interaction convolution layer (BICL), which allows integrating all potential binding cores (in a given peptide) and the MHC pseudo (binding) sequence, through modeling the interaction with multiple convolutional kernels. Extensive empirical experiments with four large-scale datasets demonstrate that DeepMHCII significantly outperformed four state-of-the-art methods under numerous settings, such as five-fold cross-validation, leave one molecule out, validation with independent testing sets, and binding core prediction. All these results with visualization of the predicted binding cores indicate the effectiveness and importance of properly modeling biological facts in deep learning for high performance and knowledge discovery. DeepMHCII is publicly available at https://weilab.sjtu.edu.cn/DeepMHCII/.


2009 ◽  
Vol 36 (5) ◽  
pp. 289-296 ◽  
Author(s):  
Lian Wang ◽  
Danling Pan ◽  
Xihao Hu ◽  
Jinyu Xiao ◽  
Yangyang Gao ◽  
...  

Immunology ◽  
2017 ◽  
Vol 152 (2) ◽  
pp. 255-264 ◽  
Author(s):  
Massimo Andreatta ◽  
Vanessa I. Jurtz ◽  
Thomas Kaever ◽  
Alessandro Sette ◽  
Bjoern Peters ◽  
...  

1989 ◽  
pp. 1137-1143 ◽  
Author(s):  
F. Sinigaglia ◽  
J. Kilgus ◽  
P. Romagnoli ◽  
M. Guttinger ◽  
J. R. L. Pink

1992 ◽  
Vol 175 (4) ◽  
pp. 925-932 ◽  
Author(s):  
D A Vignali ◽  
J Moreno ◽  
D Schiller ◽  
G J Hämmerling

Exon-shuffled constructs between mouse (IA beta b) and human (DR3 beta) class II beta chains were made to study the interaction sites between CD4 and major histocompatibility complex (MHC) class II molecules, and to determine whether a species barrier is involved. The overall structure and the peptide binding groove appeared to be unaffected by the exon shuffling procedure as determined by monoclonal antibody and peptide binding assays, respectively. While purified CD4+ BALB/c T cells responded strongly in a mixed leukocyte reaction to transfectants expressing the whole IA molecule, the response to IA molecules containing a DR beta 2 domain was substantially reduced. In addition, the presence of an IA beta 2 domain in DR failed to restore the weak xenoreactivity to the whole DR molecule. Similar observations were made with murine HEL-specific, IA alpha k beta b-restricted T cell hybridomas which responded significantly stronger to the whole compared with the exon-shuffled IA molecules. The involvement of CD4 in these differential responses was confirmed by the observation that CD4 loss variants responded to both molecules comparably, and transfection of CD4 into these cells restored the parental phenotype. In contrast, CD4 loss variants transfected with human CD4 responded equally to both the whole and the exon-shuffled molecules. Taken together, these data imply the existence of a partial species barrier, and suggest that CD4 interacts with the beta 2 domain of MHC class II molecules, probably in addition to other contact sites. Models for the interaction of CD4 with MHC class II molecules are presented.


PLoS ONE ◽  
2010 ◽  
Vol 5 (2) ◽  
pp. e9272 ◽  
Author(s):  
Hao Zhang ◽  
Peng Wang ◽  
Nikitas Papangelopoulos ◽  
Ying Xu ◽  
Alessandro Sette ◽  
...  

Apmis ◽  
1994 ◽  
Vol 102 (1-6) ◽  
pp. 241-248 ◽  
Author(s):  
FRANCESCO Sinigaglia ◽  
JUERGEN Hammer

Sign in / Sign up

Export Citation Format

Share Document