PMID- 36740003
OWN - NLM
STAT- MEDLINE
DCOM- 20230307
LR  - 20230314
IS  - 1096-0309 (Electronic)
IS  - 0003-2697 (Linking)
VI  - 666
DP  - 2023 Apr 1
TI  - DapNet-HLA: Adaptive dual-attention mechanism network based on deep learning to 
      predict non-classical HLA binding sites.
PG  - 115075
LID - S0003-2697(23)00040-4 [pii]
LID - 10.1016/j.ab.2023.115075 [doi]
AB  - Human leukocyte antigen (HLA) plays a vital role in immunomodulatory function. 
      Studies have shown that immunotherapy based on non-classical HLA has essential 
      applications in cancer, COVID-19, and allergic diseases. However, there are few 
      deep learning methods to predict non-classical HLA alleles. In this work, an 
      adaptive dual-attention network named DapNet-HLA is established based on existing 
      datasets. Firstly, amino acid sequences are transformed into digital vectors by 
      looking up the table. To overcome the feature sparsity problem caused by unique 
      one-hot encoding, the fused word embedding method is used to map each amino acid 
      to a low-dimensional word vector optimized with the training of the classifier. 
      Then, we use the GCB (group convolution block), SENet attention 
      (squeeze-and-excitation networks), BiLSTM (bidirectional long short-term memory 
      network), and Bahdanau attention mechanism to construct the classifier. The use 
      of SENet can make the weight of the effective feature map high, so that the model 
      can be trained to achieve better results. Attention mechanism is an 
      Encoder-Decoder model used to improve the effectiveness of RNN, LSTM or GRU 
      (gated recurrent neural network). The ablation experiment shows that DapNet-HLA 
      has the best adaptability for five datasets. On the five test datasets, the ACC 
      index and MCC index of DapNet-HLA are 4.89% and 0.0933 higher than the comparison 
      method, respectively. According to the ROC curve and PR curve verified by the 
      5-fold cross-validation, the AUC value of each fold has a slight fluctuation, 
      which proves the robustness of the DapNet-HLA. The codes and datasets are 
      accessible at https://github.com/JYY625/DapNet-HLA.
CI  - Copyright (c) 2023 Elsevier Inc. All rights reserved.
FAU - Jing, Yuanyuan
AU  - Jing Y
AD  - School of Mathematics and Statistics, Xidian University, Xi'an, 710071, PR China.
FAU - Zhang, Shengli
AU  - Zhang S
AD  - School of Mathematics and Statistics, Xidian University, Xi'an, 710071, PR China. 
      Electronic address: shengli0201@163.com.
FAU - Wang, Houqiang
AU  - Wang H
AD  - School of Mathematics and Statistics, Xidian University, Xi'an, 710071, PR China.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20230203
PL  - United States
TA  - Anal Biochem
JT  - Analytical biochemistry
JID - 0370535
RN  - 0 (Histocompatibility Antigens Class I)
RN  - 0 (HLA Antigens)
SB  - IM
MH  - Humans
MH  - *Deep Learning
MH  - *COVID-19
MH  - Histocompatibility Antigens Class I/metabolism
MH  - HLA Antigens
MH  - Binding Sites
OTO - NOTNLM
OT  - Bahdanau attention mechanism
OT  - Non-classical HLA binding sites
OT  - SENet attention mechanism
OT  - Word embedding
COIS- Declaration of competing interest The authors declare that they have no conflict 
      of interest.
EDAT- 2023/02/06 06:00
MHDA- 2023/03/08 06:00
CRDT- 2023/02/05 19:25
PHST- 2022/11/14 00:00 [received]
PHST- 2023/01/30 00:00 [revised]
PHST- 2023/02/02 00:00 [accepted]
PHST- 2023/02/06 06:00 [pubmed]
PHST- 2023/03/08 06:00 [medline]
PHST- 2023/02/05 19:25 [entrez]
AID - S0003-2697(23)00040-4 [pii]
AID - 10.1016/j.ab.2023.115075 [doi]
PST - ppublish
SO  - Anal Biochem. 2023 Apr 1;666:115075. doi: 10.1016/j.ab.2023.115075. Epub 2023 Feb 
      3.