Translating Immunopeptidomics to Immunotherapy-Decision-Making for Patient and Personalized Target Selection

Abstract

Immunotherapy is revolutionizing cancer treatment and has shown success in particular for tumors with a high mutational load. These effects have been linked to neoantigens derived from patient-specific mutations. To expand efficacious immunotherapy approaches to the vast majority of tumor types and patient populations carrying only a few mutations and maybe not a single presented neoepitope, it is necessary to expand the target space to non-mutated cancer-associated antigens. Mass spectrometry enables the direct and unbiased discovery and selection of tumor-specific human leukocyte antigen (HLA) peptides that can be used to define targets for immunotherapy. Combining these targets into a warehouse allows for multi-target therapy and accelerated clinical application. For precise personalization aimed at optimally ensuring treatment efficacy and safety, it is necessary to assess the presence of the target on each individual patient's tumor. Here we show how LC-MS paired with gene expression data was used to define mRNA biomarkers currently being used as diagnostic test IMADETECT™ for patient inclusion and personalized target selection within two clinical trials (NCT02876510, NCT03247309). Thus, we present a way how to translate HLA peptide presentation into gene expression thresholds for companion diagnostics in immunotherapy considering the peptide-specific correlation to its encoding mRNA.

Keywords: Human leukocyte antigen; Immunopeptidome; Immunotherapy; Label-free quantitation; Precision medicine.

Figure 1

Mass spectrometry guided target discovery with concomitant biomarker development and its translation into clinical application. A) For target discovery, HLA ligands are identified by LC‐MS/MS followed by restriction to HLA‐A*02 positive donors. Label‐free quantitation of HLA‐peptide abundance by mass spectrometry as well as gene expression by RNA‐Seq is inspected across tumor (red) and normal (blue) tissues to define tumor‐associated peptides (TUMAPs). As part of target validation, parallel reaction monitoring (PRM) mass spectrometry allows to determine absolute peptide copy numbers per cell. Multiple targets can be combined to a target warehouse to maximize treatment efficacy and safety. Based on the acquired data, for every peptide the correlation between peptide and mRNA levels needs to be investigated to ensure that development of mRNA companion diagnostics is feasible. For this, LC‐MS peptide presentation is mapped to predictive RNA‐Seq thresholds in FPKM (red) and calibrated to qPCR thresholds expressed in ∆Ct (blue). Target genes expression above the determined threshold will be used as selection criterium within the diagnostic test. B) Personalization workflow based on mass spectrometry guided qPCR thresholds. Biopsies from cancer patients are used to measure mRNA expression of warehouse targets using qPCR. Target peptides are considered to be presented by the tumor if expression of corresponding mRNA is above the threshold. The screened cancer patient receives a personalized target‐specific product (e.g., engineered T cells for adoptive cellular transfer).

Figure 2

Peptide presentation and gene expression profiling of glioblastoma target PTPRZ1p195 derived from protein tyrosine phosphatase Z polypeptide 1 (PTPRZ1) isolated from tumor (red) and normal (blue) tissues. A) Each dot represents a sample for which the peptide was identified and quantified by mass spectrometry. B) Shows the mRNA expression for exon 6 of PTPRZ1 (ENSE00001288392) measured by RNA‐Seq in FPKM. The peptide shows tenfold higher peptide presentation levels and fourfold higher gene expression in glioblastoma samples (GBM) compared to healthy brain and on average 100‐fold and 50‐fold higher levels compared to other healthy tissues for presentation and expression, respectively.

Figure 3

Correlation between gene expression and peptide presentation. A) Peptide PDCD4p294 from programmed cell death protein 4 shows good correlation between gene expression and peptide presentation (R = 0.49, p < 0.001). B) Peptide TSC2p526 from tuberin shows no correlation between gene expression as measured by RNA‐Seq compared to peptide presentation measured by label‐free LC‐MS (R = 0.07, p = 0.303). C) Peptide SYNMp426 from synemin shows a correlation between gene expression and peptide presentation when filtered for samples with pairwise complete measurements (R = 0.68, p < 0.001). D) Dot‐box‐plot of gene expression for SYNMp426 for samples with and without peptide detection.

Figure 4

Two‐factor binary classification of KCNJ10p371 (ALSVRISNV, P78508_371‐379) derived from potassium inwardly rectifying channel protein, subfamily J, member 10 (KCNJ10). Peptide detection is predicted using (A) logistic regression and (B) decision tree based on gene expression by RNA‐Seq and A*02 PMD (HLA‐A*02 peptidome measurement depth). The decision line (dotted line) in (A) separates all samples that are more likely to have the peptide detected from all samples that are more likely to not have the peptide detected. The quadrants defined in (B) are defined by optimizing the A*02 PMD (black line) and RNA‐Seq threshold (red line) using the F score.

Figure 5

Threshold optimization and confidence estimates for binary classification of peptide detection by gene expression corrected for A*02 PMD (HLA‐A*02 peptidome measurement depth). The FPKM score predicting peptide detection with optimal F‐score is shown as red line while the 95% confidence interval is depicted as dashed line. A) Detection of PIGCp89 cannot be predicted by gene expression and PMD (F = 0.338). B) Detection of SYNMp426 can be predicted by gene expression (F = 0.810) but equally well by PMD alone (∆F = 0.009). C) Detection of ETNPPLp355 is well predictable by gene expression (F = 0.909) compared to PMD alone (∆F = 0.370). D) For detection of GFAPp96 the improvement of prediction performance is even more pronounced with ∆F = 0.640.