MHCpLogics: an interactive machine learning-based tool for unsupervised data visualization and cluster analysis of immunopeptidomes

被引:0
作者
Shahbazy, Mohammad [1 ,2 ]
Ramarathinam, Sri H.
Li, Chen [1 ,2 ]
Illing, Patricia T. [1 ,2 ]
Faridi, Pouya [3 ]
Croft, Nathan P. [1 ,4 ]
Purcell, Anthony W. [1 ]
机构
[1] Monash Univ, Dept Biochem & Mol Biol, Melbourne, Vic 3800, Australia
[2] Monash Univ, Biomed Discovery Inst, Melbourne, Australia
[3] Monash Univ, Hudson Inst Med Res, Translat Antigen Discovery Lab, Melbourne, Australia
[4] Monash Univ, Melbourne, Australia
基金
澳大利亚国家健康与医学研究理事会;
关键词
Major histocompatibility complex; Human leukocyte antigens; Immunopeptidomics; Unsupervised machine learning; Data visualization; HLA peptide ligands; DATA-INDEPENDENT-ACQUISITION; MHC CLASS-I; PEPTIDOME DECONVOLUTION; PLATFORM; IDENTIFICATION; ALIGNMENT; NNALIGN;
D O I
暂无
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
The major histocompatibility complex (MHC) encodes a range of immune response genes, including the human leukocyte antigens (HLAs) in humans. These molecules bind peptide antigens and present them on the cell surface for T cell recognition. The repertoires of peptides presented by HLA molecules are termed immunopeptidomes. The highly polymorphic nature of the genres that encode the HLA molecules confers allotype-specific differences in the sequences of bound ligands. Allotype-specific ligand preferences are often defined by peptide-binding motifs. Individuals express up to six classical class I HLA allotypes, which likely present peptides displaying different binding motifs. Such complex datasets make the deconvolution of immunopeptidomic data into allotype-specific contributions and further dissection of binding-specificities challenging. Herein, we developed MHCpLogics as an interactive machine learning-based tool for mining peptide-binding sequence motifs and visualization of immunopeptidome data across complex datasets. We showcase the functionalities of MHCpLogics by analyzing both in-house and published mono- and multi-allelic immunopeptidomics data. The visualization modalities of MHCpLogics allow users to inspect clustered sequences down to individual peptide components and to examine broader sequence patterns within multiple immunopeptidome datasets. MHCpLogics can deconvolute large immunopeptidome datasets enabling the interrogation of clusters for the segregation of allotype-specific peptide sequence motifs, identification of sub-peptidome motifs, and the exportation of clustered peptide sequence lists. The tool facilitates rapid inspection of immunopeptidomes as a resource for the immunology and vaccine communities. MHCpLogics is a standalone application available via an executable installation at: https://github.com/PurcellLab/MHCpLogics.
引用
收藏
页数:17
相关论文
共 73 条
[1]   Principal component analysis [J].
Abdi, Herve ;
Williams, Lynne J. .
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS, 2010, 2 (04) :433-459
[2]   NNAlign_MA; MHC Peptidome Deconvolution for Accurate MHC Binding Motif Characterization and Improved T-cell Epitope Predictions [J].
Alvarez, Bruno ;
Reynisson, Birkir ;
Barra, Carolina ;
Buus, Soren ;
Ternette, Nicola ;
Connelley, Tim ;
Andreatta, Massimo ;
Nielsen, Morten .
MOLECULAR & CELLULAR PROTEOMICS, 2019, 18 (12) :2459-2477
[3]   GibbsCluster: unsupervised clustering and alignment of peptide sequences [J].
Andreatta, Massimo ;
Alvarez, Bruno ;
Nielsen, Morten .
NUCLEIC ACIDS RESEARCH, 2017, 45 (W1) :W458-W463
[4]   Simultaneous alignment and clustering of peptide data using a Gibbs sampling approach [J].
Andreatta, Massimo ;
Lund, Ole ;
Nielsen, Morten .
BIOINFORMATICS, 2013, 29 (01) :8-14
[5]  
[Anonymous], 2020, Nucleic Acids Res, V48, pW449, DOI [DOI 10.1093/NAR/GKAA379, 10.1093/nar/gkaa379]
[6]   Unsupervised HLA Peptidome Deconvolution Improves Ligand Prediction Accuracy and Predicts Cooperative Effects in Peptide-HLA Interactions [J].
Bassani-Sternberet, Michal ;
Gfellert, David .
JOURNAL OF IMMUNOLOGY, 2016, 197 (06) :2492-2499
[7]   Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificity [J].
Bassani-Sternberg, Michal ;
Chong, Chloe ;
Guillaume, Philippe ;
Solleder, Marthe ;
Pak, HuiSong ;
Gannon, Philippe O. ;
Kandalaft, Lana E. ;
Coukos, George ;
Gfeller, David .
PLOS COMPUTATIONAL BIOLOGY, 2017, 13 (08) :e1005725
[8]   The Importance of Being Presented: Target Validation by Immunopeptidomics for Epitope-Specific Immunotherapies [J].
Becker, Jonas P. ;
Riemer, Angelika B. .
FRONTIERS IN IMMUNOLOGY, 2022, 13
[9]   The Ludwig Institute for Cancer Research Melbourne Melanoma Cell Line Panel [J].
Behren, Andreas ;
Anaka, Matthew ;
Lo, Pu-Han ;
Vella, Laura J. ;
Davis, Ian D. ;
Catimel, Jenny ;
Cardwell, Tracy ;
Gedye, Craig ;
Hudson, Christopher ;
Stan, Rodica ;
Cebon, Jonathan .
PIGMENT CELL & MELANOMA RESEARCH, 2013, 26 (04) :597-600
[10]   Statistical properties of kernel principal component analysis [J].
Blanchard, Gilles ;
Bousquet, Olivier ;
Zwald, Laurent .
MACHINE LEARNING, 2007, 66 (2-3) :259-294