In silico design of MHC class I high binding affinity peptides through motifs activation map
Abstract Background Finding peptides with high binding affinity to Class I major histocompatibility complex (MHC-I) attracts intensive research, and it serves a crucial part of developing a better vaccine for precision medicine. Traditional methods cost highly for designing such peptides. The advanc...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-12-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-018-2517-3 |
id |
doaj-ac7c26be1e5248a89226009bb99599f5 |
---|---|
record_format |
Article |
spelling |
doaj-ac7c26be1e5248a89226009bb99599f52020-11-25T02:53:06ZengBMCBMC Bioinformatics1471-21052018-12-0119S19132410.1186/s12859-018-2517-3In silico design of MHC class I high binding affinity peptides through motifs activation mapZhoujian Xiao0Yuwei Zhang1Runsheng Yu2Yin Chen3Xiaosen Jiang4Ziwei Wang5Shuaicheng Li6South China Normal UniversityCity University of Hong KongSouth China Normal UniversityHuazhong University of Science and TechnologyHuazhong University of Science and TechnologyHunan Agricultural UniversityCity University of Hong KongAbstract Background Finding peptides with high binding affinity to Class I major histocompatibility complex (MHC-I) attracts intensive research, and it serves a crucial part of developing a better vaccine for precision medicine. Traditional methods cost highly for designing such peptides. The advancement of computational approaches reduces the cost of new drug discovery dramatically. Compared with flourishing computational drug discovery area, the immunology area lacks tools focused on in silico design for the peptides with high binding affinity. Attributed to the ever-expanding amount of MHC-peptides binding data, it enables the tremendous influx of deep learning techniques for modeling MHC-peptides binding. To leverage the availability of these data, it is of great significance to find MHC-peptides binding specificities. The binding motifs are one of the key components to decide the MHC-peptides combination, which generally refer to a combination of some certain amino acids at certain sites which highly contribute to the binding affinity. Result In this work, we propose the Motif Activation Mapping (MAM) network for MHC-I and peptides binding to extract motifs from peptides. Then, we substitute amino acid randomly according to the motifs for generating peptides with high affinity. We demonstrated the MAM network could extract motifs which are the features of peptides of highly binding affinities, as well as generate peptides with high-affinities; that is, 0.859 for HLA-A*0201, 0.75 for HLA-A*0206, 0.92 for HLA-B*2702, 0.9 for HLA-A*6802 and 0.839 for Mamu-A1*001:01. Besides, its binding prediction result reaches the state of the art. The experiment also reveals the network is appropriate for most MHC-I with transfer learning. Conclusions We design the MAM network to extract the motifs from MHC-peptides binding through prediction, which are proved to generate the peptides with high binding affinity successfully. The new peptides preserve the motifs but vary in sequences.http://link.springer.com/article/10.1186/s12859-018-2517-3Design new peptides with high binding affinity to MHC-I moleculeConvolutional neural networkMotifs activation map |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhoujian Xiao Yuwei Zhang Runsheng Yu Yin Chen Xiaosen Jiang Ziwei Wang Shuaicheng Li |
spellingShingle |
Zhoujian Xiao Yuwei Zhang Runsheng Yu Yin Chen Xiaosen Jiang Ziwei Wang Shuaicheng Li In silico design of MHC class I high binding affinity peptides through motifs activation map BMC Bioinformatics Design new peptides with high binding affinity to MHC-I molecule Convolutional neural network Motifs activation map |
author_facet |
Zhoujian Xiao Yuwei Zhang Runsheng Yu Yin Chen Xiaosen Jiang Ziwei Wang Shuaicheng Li |
author_sort |
Zhoujian Xiao |
title |
In silico design of MHC class I high binding affinity peptides through motifs activation map |
title_short |
In silico design of MHC class I high binding affinity peptides through motifs activation map |
title_full |
In silico design of MHC class I high binding affinity peptides through motifs activation map |
title_fullStr |
In silico design of MHC class I high binding affinity peptides through motifs activation map |
title_full_unstemmed |
In silico design of MHC class I high binding affinity peptides through motifs activation map |
title_sort |
in silico design of mhc class i high binding affinity peptides through motifs activation map |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2018-12-01 |
description |
Abstract Background Finding peptides with high binding affinity to Class I major histocompatibility complex (MHC-I) attracts intensive research, and it serves a crucial part of developing a better vaccine for precision medicine. Traditional methods cost highly for designing such peptides. The advancement of computational approaches reduces the cost of new drug discovery dramatically. Compared with flourishing computational drug discovery area, the immunology area lacks tools focused on in silico design for the peptides with high binding affinity. Attributed to the ever-expanding amount of MHC-peptides binding data, it enables the tremendous influx of deep learning techniques for modeling MHC-peptides binding. To leverage the availability of these data, it is of great significance to find MHC-peptides binding specificities. The binding motifs are one of the key components to decide the MHC-peptides combination, which generally refer to a combination of some certain amino acids at certain sites which highly contribute to the binding affinity. Result In this work, we propose the Motif Activation Mapping (MAM) network for MHC-I and peptides binding to extract motifs from peptides. Then, we substitute amino acid randomly according to the motifs for generating peptides with high affinity. We demonstrated the MAM network could extract motifs which are the features of peptides of highly binding affinities, as well as generate peptides with high-affinities; that is, 0.859 for HLA-A*0201, 0.75 for HLA-A*0206, 0.92 for HLA-B*2702, 0.9 for HLA-A*6802 and 0.839 for Mamu-A1*001:01. Besides, its binding prediction result reaches the state of the art. The experiment also reveals the network is appropriate for most MHC-I with transfer learning. Conclusions We design the MAM network to extract the motifs from MHC-peptides binding through prediction, which are proved to generate the peptides with high binding affinity successfully. The new peptides preserve the motifs but vary in sequences. |
topic |
Design new peptides with high binding affinity to MHC-I molecule Convolutional neural network Motifs activation map |
url |
http://link.springer.com/article/10.1186/s12859-018-2517-3 |
work_keys_str_mv |
AT zhoujianxiao insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT yuweizhang insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT runshengyu insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT yinchen insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT xiaosenjiang insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT ziweiwang insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap AT shuaichengli insilicodesignofmhcclassihighbindingaffinitypeptidesthroughmotifsactivationmap |
_version_ |
1724726693400150016 |