Molecular Determinants of Response to Anti-Programmed Cell Death (PD)-1 and Anti-Programmed Death-Ligand 1 (PD-L1) Blockade in Patients With Non-Small-Cell Lung Cancer Profiled With Targeted Next-Generation Sequencing

Abstract

Purpose Treatment of advanced non-small-cell lung cancer with immune checkpoint inhibitors (ICIs) is characterized by durable responses and improved survival in a subset of patients. Clinically available tools to optimize use of ICIs and understand the molecular determinants of response are needed. Targeted next-generation sequencing (NGS) is increasingly routine, but its role in identifying predictors of response to ICIs is not known. Methods Detailed clinical annotation and response data were collected for patients with advanced non-small-cell lung cancer treated with anti-programmed death-1 or anti-programmed death-ligand 1 [anti-programmed cell death (PD)-1] therapy and profiled by targeted NGS (MSK-IMPACT; n = 240). Efficacy was assessed by Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1, and durable clinical benefit (DCB) was defined as partial response/stable disease that lasted > 6 months. Tumor mutation burden (TMB), fraction of copy number-altered genome, and gene alterations were compared among patients with DCB and no durable benefit (NDB). Whole-exome sequencing (WES) was performed for 49 patients to compare quantification of TMB by targeted NGS versus WES. Results Estimates of TMB by targeted NGS correlated well with WES (ρ = 0.86; P < .001). TMB was greater in patients with DCB than with NDB ( P = .006). DCB was more common, and progression-free survival was longer in patients at increasing thresholds above versus below the 50th percentile of TMB (38.6% v 25.1%; P < .001; hazard ratio, 1.38; P = .024). The fraction of copy number-altered genome was highest in those with NDB. Variants in EGFR and STK11 associated with a lack of benefit. TMB and PD-L1 expression were independent variables, and a composite of TMB plus PD-L1 further enriched for benefit to ICIs. Conclusion Targeted NGS accurately estimates TMB and elevated TMB further improved likelihood of benefit to ICIs. TMB did not correlate with PD-L1 expression; both variables had similar predictive capacity. The incorporation of both TMB and PD-L1 expression into multivariable predictive models should result in greater predictive power.

Fig 1.

Somatic molecular features associated with response to immunotherapy. (A) Tumor mutation burden (TMB) assessed by targeted next-generation sequencing (NGS) correlates with TMB assessed by whole-exome sequencing (WES; n = 49, Spearman ρ = 0.86; P, .001). Individual tumors are shown as dots. The line depicts the best fit. (B) Somatic nonsynonymous TMB is greater in durable clinical benefit (DCB) versus no durable benefit (NDB; median, 8.5 v 6.6 single-nucleotide variants/megabase [Mb]; P = .006) and is significantly different in those with complete response (CR)/partial response (PR) versus stable disease (SD) versus progressive disease (PD; median, 8.5 v 6.6 v 6.6 single-nucleotide variants/Mb; P = .049). The distribution of TMB in patients with non–immune checkpoint inhibitor (ICI)–treated non–small-cell lung cancer (NSCLC) are shown for reference. TMB in patients with DCB was similar to those with CR/PR (P = .85) and greater in those with non-ICI NSCLC (P, .001). Box plots represent medians, interquartile ranges, and vertical lines extend to the 95th percentiles. TMB of individual patients are represented with light dots. (C) Odds ratio (OR) of DCB with increasing cut points of TMB.25th (OR, 1.75), 50th (OR, 2.02), 75th (OR, 2.06), and 90th (OR, 3.24) percentiles. The 0 percentile (white bar) is shown for reference of all patients (default OR, 1). The odds of DCB increase significantly above the 50th percentile of TMB. (D) Individual Kaplan-Meier curves of progressionfree survival (PFS) above each percentile at increasing thresholds of TMB. PFS in patients with NSCLC treated with anti–programmed cell death-1– or anti–programmed deathligand 1–based therapy increaseswith increases inTMB. (E) Fraction of copy number–altered genome (FGA) inDCBversusNDB(median, 0.08 v 0.15;P = .129) and PR/CR versus SD versus PD (median, 0.09 v 0.11 v 0.16; P = .479). FGA is enriched among those with PD or NDB compared with non-ICI NSCLC (P = .004 and .002, respectively).

Fig 2.

Genes associated with response and resistance to immunotherapy. OncoPrint that depicts alterations in preselected genes of interest in durable clinical benefit (DCB) and no durable benefit (NDB) groups. Reported frequencies include a composite of all alterations for each gene across all groups (single-nucleotide variants, indels, fusions, amplifications, deletions). Predicted functional impact of genetic alterations are described as known in OncoKB or variants of unknown significance (VUSs). Summary rows of each case at top include annotation for whether samples were obtained before or after initiation of immune checkpoint inhibitor (ICI) therapy, mutations/megabase (Mb; histogram), indels/Mb (histogram), frequencies of fraction of copy number–altered genome (FGA; lowest to highest FGA, white to dark red), smoking, and mutation spectrum. Events where information is unknown (eg, gene not covered in panel tested) are depicted in light gray on the OncoPrint.

Fig 3.

Comparison of programmed death-ligand 1 (PD-L1) expression with tumor mutation burden (TMB) and fraction of copy number–alteration genome (FGA). (A) Scatter plot of TMB and PD-L1 expression. TMB does not correlate with percent PD-L1 expression (n = 84; Spearman ρ = 0.192; P = .081). Dots represent individual tumors, and the line represents the best fit. (B) Scatter plot of FGA versus percent PD-L1 expression. No correlation exists between FGA and PD-L1 expression (n = 84; Spearman ρ = 0.127; P = .25). Dots represent individual tumors. (C) Receiver operating characteristic curve of sensitivity versus 1-specificity of durable clinical benefit (DCB) at varying levels of TMB (area under the curve [AUC], 0.601; P = .078) and PD-L1 expression (AUC, 0.646; P = .014). Results depict only those patients with available data for both TMB and PD-L1 (n = 84). (D) A histogram depicts the proportion of DCB among patients in groups defined by a composite variable of TMB (stratified above and below the median as low v high) and PD-L1 expression (stratified into 0% or ≥ 1% groups as low v high). Rate of DCB is lowest in patients low for both variables (18%), intermediate in patients high for one variable (29% to 35%), and highest in patients high for both variables (50%). Error bars show the SE of the percentage. Mb, megabase.

Fig A1.

Flow of patients with non–small-cell lung cancer (NSCLC). These patients were treated with anti–programmed cell death-1 or anti–programmed death-ligand 1 [PD-(L)1] therapy from April 2011 through January 2017 and profiled with Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets (MSK-IMPACT) panels are shown on the left. Patients with NSCLC profiled with MSK-IMPACT who have not been treated with immunotherapy (non–immune checkpoint inhibitors [ICIs]) are shown on the right. BOR, best overall response; RECIST, Response Evaluation Criteria in Solid Tumors; WES, whole-exome sequencing.

Fig A2.

Durable clinical benefit (DCB)/no durable benefit (NDB) compared with Response Evaluation Criteria in Solid Tumors (RECIST)–defined benefit. DCB and NDB are clinically useful, simple, binary outcomes to categorize those who benefit or not from immunotherapy. These groups have survival outcomes similar to RECIST-defined complete response (CR)/partial response (PR) or progressive disease (PD) while also incorporating meaningful distinction of those with stable disease (SD) who are benefiters or not. (A) Overall survival of patients with DCB/NDB or CR/PR, SD, or PD. Survival of DCB closely mirrors that of CR/PR, and NDB mirrors patients with PD. (B) A focus just on patients with SD shows a significant difference in overall survival stratified by DCB and NDB (P < .001). RECIST-defined SD, therefore, is an intermediate group that is comprised by a “true” benefit (progression-free survival [PFS] > 6 months) and not a “true” benefit (PFS < 6 months). Therefore, dichotomizing outcomes by duration of benefit more explicitly captures the major contribution of benefit from immunotherapy (durability), removes patients with uncommon short-lived responses, and improves adjudication of those with RECIST-defined SD, a heterogeneous group that comprises true benefit or not of immunotherapy.

Fig A3.

Range of mutation burden across varying sizes of targeted next-generation sequencing panels. (A) Absolute nonsynonymous missense mutation count reported for tumors assessed by using the Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets (MSK-IMPACT) 341-, 410-, and 486-gene panels. Increasing absolute mutation burden is seen with increasing numbers of genes tested (median of six, eight, and nine and a half mutations in the 341-, 410-, and 486-gene panels, respectively; P = .192). (B) The mutation rate normalized by the size of the coding region covered. This correction results in similar mutation rates across each panel (median, 6.1, 7.5, and 7.8 per megabase [Mb] in the 341-, 410-, and 486-gene panels, respectively; P = .673).

Fig A4.

Proportion of durable clinical benefit (DCB) above or below the (A) 25th, (B) 50th, (C) 75th, and (D) 90th percentiles of tumor mutation burden. Percentages of DCB in each group are reported above each bar. Error bars show the SE of the percentage. NDB, no durable response.

Fig A5.

Progression-free survival (PFS) of patients with tumor mutation burden above or below the (A) 25th, (B) 50th, (C) 75th, and (D) 90th percentiles. The hazard ratios for PFS at each cut point were as follows: 25th percentile, 1.19 (P = .279); 50th percentile, 1.38 (P = .024); 75th percentile, 1.74 (P = .001); 90th percentile, 2.05 (P = .004).

Fig A6.

Overall survival (OS) of patients with advanced-stage lung adenocarcinoma not treated with immunotherapy. Survival is shown on the basis of tumor mutation burden above or below the (A) 25th, (B) 50th, (C) 75th, and (D) 90th percentiles within the non–immune checkpoint inhibitor non–small-cell lung cancer advanced-stage cohort (n = 609). The hazard ratios for OS at each cut point were as follows: 25th percentile, 0.49 (P < .001); 50th percentile, 0.58 (P < .001); 75th percentile, 0.81 (P = .118); and 90th percentile, 0.82 (P = .338).

Fig A7.

Scatter plot of tumor mutational burden versus fraction of copy number–altered genome in individual tumors (n = 240; Spearman ρ = 0.31; P < .001). Mb, megabase.

Fig A8.

Log₂(odds ratio [OR]) and –log₂(P value) for enrichment of individual altered genes deemed oncogenic or likely oncogenic by OncoKB in group comparisons of (A) durable clinical benefit (DCB) versus no durable benefit (NDB), (B) DCB versus non–immune checkpoint inhibitor (ICI) non–small-cell lung cancer (NSCLC), and (C) NDB versus non-ICI NSCLC. The top 50 genes in each comparison are depicted, with adjusted P values used. Genes labeled in red were significantly enriched after correcting for the false discovery rate.

Fig A9.

OncoPrint that depicts durable clinical benefit (DCB), no durable benefit (NDB), and non–immune checkpoint inhibitor (ICI) non–small-cell lung cancer (NSCLC) with an expanded list of preselected genes of interest, including oncogenic drivers in NSCLC, genes involved in antigen presentation, genes involved in modulating immune responses to cancer, genes previously reported to associate with response/resistance to programmed death-1 blockade, and genes involved in DNA repair. Genes shown in light gray were not sequenced as part of the MSK-IMPACT (Memorial Sloan Kettering-Integrated Mutation Profiling of Actionable Cancer Targets) panel. VUS, variant of unknown significance.

Fig A10.

β2 microglobulin (B2M) mutation found in one patient that occurred in trans with one mutation on each allele. (A) The top plot shows overall copy number segmentations across the chromosome (Chr), with the vertical line highlighting the B2M gene position. The bottom plot shows the integer copy number, with the black line depicting the total integer copy number and the red line depicting minor copy number. (B) The hematoxylin and eosin (HE) stain (magnification, ×40) shows large tumor cells circumferentially around a central vessel. (C) B2M immunohistochemistry (magnification, ×40) shows selective loss of expression in tumor cells with retention of expression in normal endothelium and within scattered lymphocytes and histiocytes.

Fig A11.

JAK2 mutations were found in two patients. (A) A heterozygous mutation in JAK2 with the wild-type allele retained. (B) A homozygous loss-of-function mutation in JAK2 with loss of the wild-type allele occurring in a patient with primary progression to programmed death-1 blockade. Chr, chromosome.

Fig A12.

Amplifications in MDM2 or MDM4 were found in eight patients. Each plot shows the copy number (CN) log ratio of the overall CN segmentations across chromosomes (Chr). Estimated integer CNs are reported for each patient and calculated by FACETS. One patient had durable clinical benefit and five of eight patients had > 2 months progression-free survival. The patient with the greatest amplification had rapid progression. The progression-free survival curve of patients with MDM2 or MDM4 amplifications are compared with those with MDM2/MDM4 wild type (hazard ratio, 1.4; P = .44).

Fig A13.

Progression-free survival (PFS) curve of patients with a programmed death-ligand 1 (PD-L1) expression of 0% compared with a PD-L1 expression ≥ 1% (hazard ratio, 0.53; P = .01).

Fig A14.

Log₂(odds ratio [OR]) and –log₂(P value) for enrichment of individual altered genes deemed oncogenic or likely oncogenic by OncoKb in the programmed death-ligand 1 (PD-L1)–positive versus PD-L1–negative subgroup. The top 50 genes in each comparison are depicted, with the false discovery rate–adjusted P values used.