PMID- 23994431
OWN - NLM
STAT- MEDLINE
DCOM- 20140714
LR  - 20131008
IS  - 1879-0542 (Electronic)
IS  - 0165-2478 (Linking)
VI  - 154
IP  - 1-2
DP  - 2013 Jul-Aug
TI  - The ever-growing peptide knowledge promotes the improvement of HLA class I 
      peptide-binding prediction.
PG  - 49-53
LID - S0165-2478(13)00110-7 [pii]
LID - 10.1016/j.imlet.2013.08.008 [doi]
AB  - Computational prediction methods for peptide binding to human leukocyte antigen 
      (HLA) molecules have played an instrumental role in the development of 
      epitope-based vaccines. These methods are based on experimentally verified 
      peptides. However, the available peptide data continue increasing and contain 
      significant biases. In this study, we report the feedback effect of peptide data 
      on a frequently used matrix-based prediction method. We implemented the weighted 
      and unweighted models of this method and evaluated the relative performance of 
      the two models on several benchmark datasets. Improvements on both models were 
      obtained by optimizing the components of a training dataset based on the effect 
      of peptide data on the performance of prediction models. Moreover, the variation 
      of the relative performance of the weighted and unweighted models with the 
      evaluated data indicated that the increased number of binding peptides required 
      the modification of the predictive engine. Our results suggest that prediction 
      methods for HLA-binding peptides should be updated as HLA-peptide-binding 
      knowledge increases.
CI  - Copyright (c) 2013 Elsevier B.V. All rights reserved.
FAU - Wang, Shufeng
AU  - Wang S
AD  - Institute of Immunology, PLA, Third Military Medical University, Chongqing 
      400038, China.
FAU - Wu, Yuzhang
AU  - Wu Y
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20130828
PL  - Netherlands
TA  - Immunol Lett
JT  - Immunology letters
JID - 7910006
RN  - 0 (Epitopes)
RN  - 0 (HLA-A Antigens)
RN  - 0 (Peptides)
SB  - IM
MH  - Antigen Presentation
MH  - Computational Biology
MH  - Computer Simulation
MH  - Epitopes/*immunology
MH  - HLA-A Antigens/*immunology
MH  - Humans
MH  - Knowledge Bases
MH  - *Models, Theoretical
MH  - Peptides/*immunology
MH  - Predictive Value of Tests
MH  - Prognosis
MH  - Protein Binding
OTO - NOTNLM
OT  - AUC
OT  - HLA
OT  - HLA-binding peptides
OT  - Improvement
OT  - MHC
OT  - NMN
OT  - Prediction
OT  - ROC
OT  - human leukocyte antigen
OT  - major histocompatibility complex
OT  - non-motif-containing non-binder
OT  - receiver operating characteristic
OT  - the area under the ROC curve
EDAT- 2013/09/03 06:00
MHDA- 2014/07/16 06:00
CRDT- 2013/09/03 06:00
PHST- 2013/07/31 00:00 [received]
PHST- 2013/08/18 00:00 [accepted]
PHST- 2013/09/03 06:00 [entrez]
PHST- 2013/09/03 06:00 [pubmed]
PHST- 2014/07/16 06:00 [medline]
AID - S0165-2478(13)00110-7 [pii]
AID - 10.1016/j.imlet.2013.08.008 [doi]
PST - ppublish
SO  - Immunol Lett. 2013 Jul-Aug;154(1-2):49-53. doi: 10.1016/j.imlet.2013.08.008. Epub 
      2013 Aug 28.