Induced pluripotent stem cells display a distinct set of MHC I-associated peptides shared by human cancers

Apavaloaei, Anca; Hesnard, Leslie; Hardy, Marie-Pierre; Benabdallah, Basma; Ehx, Grégory; Thériault, Catherine; Laverdure, Jean‐Philippe; Durette, Chantal; Lanoix, Joël; Courcelles, Mathieu; Noronha, Nandita; Chauhan, Kapil Dev; Lemieux, Sébastien; Beauséjour, Christian; Bhatia, Mick; Thibault, Pierre; Perreault, Claude

doi:10.1016/j.celrep.2022.111241

Cited by 9 publications

(19 citation statements)

References 139 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…an immunogenicity prediction tool needs to prioritize 1 neoantigen out of every 100 negative peptides. We found that the ratio 1:100 was in line with the number of neoantigens and the number of candidates identified from genomics/proteogenomics pipelines in most existing neoantigen studies 2,6,16,[30][31][32][33][34][35][36] . Any common peptides shared between the evaluation set and the training data were excluded from the training data.…”

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...supporting

confidence: 59%

“…The key idea of DeepSelf is to use HLA self peptides obtained from MS-based immunopeptidomics as negative data to train immunogenicity prediction models. Four of the 18 patients, Mel-15, Mel-0D5P, Mel-51, and iSPC2_IFN, had MS-based immunopeptidomics data 6,[30][31][32] . For each of those four patients, their data was analyzed using DeepNovo Peptidome and their HLA self peptides were obtained as described in the previous section.…”

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...mentioning

confidence: 99%

“…The number of neoantigens varied from 2-6 per patient, while the total number of peptides that had been tested in T cell assays was 15-434 per patient (Table S3). However, it should be noted that, before T cell assay validation, those peptides had actually been selected from an even larger pool of candidates 2,6,16,[30][31][32][33][34][35][36] . Thus, we expanded the evaluation set of each patient by adding negative peptides randomly drawn from that patient's self peptides (or allelematched MHC eluted peptides from the IEDB if self peptides were not available).…”

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...mentioning

confidence: 99%

See 2 more Smart Citations

Discovering and Validating Neoantigens by Mass Spectrometry-based Immunopeptidomics and Deep Learning

Tran

2022

Preprint

View full text Add to dashboard Cite

SummaryHere we propose a personalized machine learning approach to predict the collective response of a patient’s CD8+ T cells by modeling the positive and negative selection processes, i.e. the central tolerance of T cells. In particular, for each individual patient, we collected his/her HLA-I self peptides derived from mass spectrometry-based immunopeptidomics as negative selection, and allele-matched immunogenic T cell epitopes from the Immune Epitope Database as positive selection. The negative and positive peptides were used to train a binary classification model, which was then applied to predict the immunogenicity of candidate neoantigens of that patient. Evaluation results on three cancer patients and one mouse cancer cell line and showed that our personalized models achieved an average accuracy of 79% and outperformed existing immunogenicity prediction tools. Furthermore, the models were able to rank neoantigens that elicited CD8+ T-cell responses within the top 15% of candidate peptides identified from the patients, thus reducing the time and costs of complicated in vitro validations.

show abstract

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...supporting

confidence: 59%

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...mentioning

confidence: 99%

Section: Evaluation Of Deepself and Other Immunogenicity Prediction T...mentioning

confidence: 99%

See 1 more Smart Citation

Discovering and Validating Neoantigens by Mass Spectrometry-based Immunopeptidomics and Deep Learning

Tran

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Our workflow identified 181,012 HLA-I and 208,255 HLA-II peptides, substantially expanding the HLA Ligand Atlas by 46-100%. We also extensively evaluated DeepSelf on the immunopeptidomes and neoantigens of 18 cancer patients from 10 previously published studies 1,5,[16][17][18][19][20][21][22][23] . Finally, we presented a new MS-based immunopeptidomics study of native tumor tissues from five patients with cervical cancer.…”

Section: Introductionmentioning

confidence: 99%

A complete mass spectrometry-based immunopeptidomics pipeline for neoantigen identification and validation

Li,

Tran,

Peng

et al. 2023

Preprint

View full text Add to dashboard Cite

Here we proposed DeepImmu, a complete pipeline for neoantigen identification and validation that was based solely on mass spectrometry (MS) immunopeptidomics. In particular, a new enrichment kit was developed for HLA peptide purification from a small amount of biopsied tissue as low as 18mg. To identify candidate neoantigens from such a small amount of sample, we built DeepNovo Peptidome, a highly sensitive de novo sequencing-based workflow for HLA peptide identification. Furthermore, we developed DeepSelf, a personalized model for immunogenicity prediction based on the central tolerance of T cells, which could be used to prioritize candidate neoantigens from de novo HLA peptides for in vitro validation. Finally, we presented a new MS-based immunopeptidomics study of native tumor tissues from five patients with cervical cancer. We applied DeepImmu pipeline to identify and prioritize candidate neoantigens from low amounts of tumor tissues, and then performed in vitro validation of autologous neoantigen-specific T cell responses to confirm our results. Our MS-based de novo sequencing approach provides an unbiased solution for neoantigen discovery, because it does not depend on prior knowledge of protein databases, RNA sequencing data, or the source of neoantigens. By reducing the amount of sample to biopsy size, our DeepImmu pipeline can be easily performed in routine clinical applications.

show abstract

“…Therefore, AltProts include proteins of less than and greater than 100 amino acids. Recently, AltProts have turned out to play essential roles in a variety of physiological processes or diseases ( 4 , 5 , 6 , 7 ), such as metabolism ( 8 ), cancer immunology ( 9 , 10 ), transcriptional ( 11 ), translational regulation ( 12 ), ion signaling ( 13 ), and development ( 12 , 14 ).…”

mentioning

confidence: 99%

An Optimized Proteomics Approach Reveals Novel Alternative Proteins in Mouse Liver Development

Yang

Wang²,

Zhang³

et al. 2023

Molecular & Cellular Proteomics

View full text Add to dashboard Cite

Induced pluripotent stem cells display a distinct set of MHC I-associated peptides shared by human cancers

Cited by 9 publications

References 139 publications

Discovering and Validating Neoantigens by Mass Spectrometry-based Immunopeptidomics and Deep Learning

Discovering and Validating Neoantigens by Mass Spectrometry-based Immunopeptidomics and Deep Learning

A complete mass spectrometry-based immunopeptidomics pipeline for neoantigen identification and validation

An Optimized Proteomics Approach Reveals Novel Alternative Proteins in Mouse Liver Development

Contact Info

Product

Resources

About