Multi-omics discovery of exome-derived neoantigens in hepatocellular carcinoma

Abstract

Background: Although mutated HLA ligands are considered ideal cancer-specific immunotherapy targets, evidence for their presentation is lacking in hepatocellular carcinomas (HCCs). Employing a unique multi-omics approach comprising a neoepitope identification pipeline, we assessed exome-derived mutations naturally presented as HLA class I ligands in HCCs.

Methods: In-depth multi-omics analyses included whole exome and transcriptome sequencing to define individual patient-specific search spaces of neoepitope candidates. Evidence for the natural presentation of mutated HLA ligands was investigated through an in silico pipeline integrating proteome and HLA ligandome profiling data.

Results: The approach was successfully validated in a state-of-the-art dataset from malignant melanoma, and despite multi-omics evidence for somatic mutations, mutated naturally presented HLA ligands remained elusive in HCCs. An analysis of extensive cancer datasets confirmed fundamental differences of tumor mutational burden in HCC and malignant melanoma, challenging the notion that exome-derived mutations contribute relevantly to the expectable neoepitope pool in malignancies with only few mutations.

Conclusions: This study suggests that exome-derived mutated HLA ligands appear to be rarely presented in HCCs, inter alia resulting from a low mutational burden as compared to other malignancies such as malignant melanoma. Our results therefore demand widening the target scope for personalized immunotherapy beyond this limited range of mutated neoepitopes, particularly for malignancies with similar or lower mutational burden.

Keywords: HLA; HLA ligandomics; Hepatocellular carcinoma; Immunoinformatics; Immunotherapy; Liver cancer; Mass spectrometry; Multi-omics; Neoantigen; Next-generation sequencing; Peptide prediction; Personalized medicine.

Fig. 1

Characterization of somatic variants and their potential for HLA presentation in HCC. a Numbers of somatic variants across HCC patients (n = 16). Numbers are shown for all variants passing initial filtering (Var), coding non-synonymous variants (Var^ns), and coding non-synonymous variants with RNA level evidence (Var^exp). Boxplots show means ± SD. b Var^exp shared among HCC patients. Var^exp affecting identical genes in ≥ 3 patients are displayed in gray. Var^exp observed at identical genomic positions are displayed in red (the shown HLA-DR variants should be cautiously interpreted as potential artifacts). c Correlation between Var^ns and predicted HLA-binding neoepitopes (PNE) (left; blue). Correlation between Var^exp and expressed PNE (PNE^exp) (right; orange). d Scatter plot of numbers of Var^ns and PNE in HCC patients (blue) and a benchmarking dataset of melanoma (Mel) patients (red) as previously described by Bassani-Sternberg et al. [24]

Fig. 2

Numbers of predicted neoepitopes with evidence on different omics levels. a Numbers of somatic variants and non-synonymous somatic variants (Var and Var^ns), respectively; peptide search space (PSS), predicted HLA-binding neoepitopes (PNE), and PNE on the different available omics levels: expressed PNE (PNE^exp), PNE with evidence on shotgun proteome level (PNE^prot), and neoepitopes observed as natural HLA ligands (NE^lig) are shown for the HCC dataset (left; n = 16) and the Mel dataset (right; n = 5) published previously by Bassani-Sternberg et al. [24]. Numbers are given as mean ± SD. b Numbers of peptides after processing with our neoepitope identification pipeline are shown on a per patient basis according to the different omics levels as observed in the HCC dataset (left) as well as the Mel dataset (right). For each patient, total counts of predicted peptides (PSS) are annotated in black, numbers of NE^lig for Mel patients are shown in red (median = 1.0)

Fig. 3

Comparison of the mutational burden in Mel and HCC. a Number of mutations (# Var^ns) of TCGA cases in Mel (n = 476). b Number of mutations (# Var^ns) of TCGA cases in HCC (n = 363). The data were retrieved from Genomics Data Commons Data Portal (https://portal.gdc.cancer.gov/, access date: 2018-09-16). Variants were filtered for missense variants, frameshift variants, inframe deletions, inframe insertions, and coding sequence variants. Variants that were called by Mutect2 are considered. The number of mutations was assessed with respect to high tumor mutational burden (> 400 Var^ns, red) and the fraction of tumors with > 100 Var^ns (blue)

Fig. 4

Evidence for mutated proteins in the shotgun proteome and database matching. a Annotated spectra of albumin (ALB) showing sequences of wild-type (LAKTYETTLEK; top) and mutated (LAETYETTLEK; bottom) protein measured by LC-MS/MS. b Annotated spectra of RecQ like helicase (RECQL) showing sequences of the peptide AVEIQIQELTER resulting from an additional tryptic cleavage side added directly in front of this sequence through a mutation from histidine to arginine, evidenced in HCC tissue only. c Database matching of natural HLA ligands with wild-type peptide sequence (with diverse HLA restrictions) covering the exact position evidenced as mutated in ALB. d Database matching of natural HLA ligands with wild-type peptide sequence (with diverse HLA restrictions) covering the exact position evidenced as mutated in RECQL

Fig. 5

Number of database matches of wild-type ligands (WT^lig) corresponding to predicted mutated neoepitopes (PNE). PNE with additional evidence in HCC and Mel [24] are highlighted: (1) black: wild-type sequence of PNE contained in database; (2) yellow: wild-type sequence peptide corresponding to PNE confirmed in autologous tissue as natural HLA ligand by mass spectrometry; (3) blue: mutated protein confirmed by shotgun proteomics - PNE^prot; (4) red: PNE confirmed as natural HLA ligand by mass spectrometry - NE^lig