PMID- 33407098
OWN - NLM
STAT- MEDLINE
DCOM- 20210115
LR  - 20210115
IS  - 1471-2105 (Electronic)
IS  - 1471-2105 (Linking)
VI  - 22
IP  - 1
DP  - 2021 Jan 6
TI  - MATHLA: a robust framework for HLA-peptide binding prediction integrating 
      bidirectional LSTM and multiple head attention mechanism.
PG  - 7
LID - 10.1186/s12859-020-03946-z [doi]
LID - 7
AB  - BACKGROUND: Accurate prediction of binding between class I human leukocyte 
      antigen (HLA) and neoepitope is critical for target identification within 
      personalized T-cell based immunotherapy. Many recent prediction tools developed 
      upon the deep learning algorithms and mass spectrometry data have indeed showed 
      improvement on the average predicting power for class I HLA-peptide interaction. 
      However, their prediction performances show great variability over individual HLA 
      alleles and peptides with different lengths, which is particularly the case for 
      HLA-C alleles due to the limited amount of experimental data. To meet the 
      increasing demand for attaining the most accurate HLA-peptide binding prediction 
      for individual patient in the real-world clinical studies, more advanced deep 
      learning framework with higher prediction accuracy for HLA-C alleles and longer 
      peptides is highly desirable. RESULTS: We present a pan-allele HLA-peptide 
      binding prediction framework-MATHLA which integrates bi-directional long 
      short-term memory network and multiple head attention mechanism. This model 
      achieves better prediction accuracy in both fivefold cross-validation test and 
      independent test dataset. In addition, this model is superior over existing tools 
      regarding to the prediction accuracy for longer ligand ranging from 11 to 15 
      amino acids. Moreover, our model also shows a significant improvement for 
      HLA-C-peptide-binding prediction. By investigating multiple-head attention weight 
      scores, we depicted possible interaction patterns between three HLA I supergroups 
      and their cognate peptides. CONCLUSION: Our method demonstrates the necessity of 
      further development of deep learning algorithm in improving and interpreting 
      HLA-peptide binding prediction in parallel to increasing the amount of 
      high-quality HLA ligandome data.
FAU - Ye, Yilin
AU  - Ye Y
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
AD  - School of Computer Science and Technology, Heilongjiang University, Harbin, 
      150080, China.
FAU - Wang, Jian
AU  - Wang J
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
FAU - Xu, Yunwan
AU  - Xu Y
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
FAU - Wang, Yi
AU  - Wang Y
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
FAU - Pan, Youdong
AU  - Pan Y
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
FAU - Song, Qi
AU  - Song Q
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China.
FAU - Liu, Xing
AU  - Liu X
AD  - The Center for Microbes, Development and Health, Key Laboratory of Molecular 
      Virology and Immunology, Institut Pasteur of Shanghai, Chinese Academy of 
      Sciences, Shanghai, 200031, China.
FAU - Wan, Ji
AU  - Wan J
AUID- ORCID: 0000-0002-5279-0345
AD  - Shenzhen Neocura Biotechnology Co. Ltd., Shenzhen, 518055, China. 
      jiw@neocura.net.
LA  - eng
PT  - Journal Article
DEP - 20210106
PL  - England
TA  - BMC Bioinformatics
JT  - BMC bioinformatics
JID - 100965194
RN  - 0 (Histocompatibility Antigens Class I)
RN  - 0 (Peptides)
SB  - IM
MH  - Algorithms
MH  - Computational Biology/*methods
MH  - *Histocompatibility Antigens Class I/chemistry/metabolism
MH  - Humans
MH  - Models, Statistical
MH  - *Neural Networks, Computer
MH  - *Peptides/chemistry/metabolism
MH  - *Protein Binding
PMC - PMC7787246
OTO - NOTNLM
OT  - Cancer immunotherapy
OT  - Deep learning
OT  - HLA-peptide binding prediction
COIS- The authors declared that they have no competing interests.
EDAT- 2021/01/08 06:00
MHDA- 2021/01/16 06:00
PMCR- 2021/01/06
CRDT- 2021/01/07 05:42
PHST- 2020/07/30 00:00 [received]
PHST- 2020/12/21 00:00 [accepted]
PHST- 2021/01/07 05:42 [entrez]
PHST- 2021/01/08 06:00 [pubmed]
PHST- 2021/01/16 06:00 [medline]
PHST- 2021/01/06 00:00 [pmc-release]
AID - 10.1186/s12859-020-03946-z [pii]
AID - 3946 [pii]
AID - 10.1186/s12859-020-03946-z [doi]
PST - epublish
SO  - BMC Bioinformatics. 2021 Jan 6;22(1):7. doi: 10.1186/s12859-020-03946-z.