Blood-based tumor mutational burden as a biomarker for atezolizumab in non-small cell lung cancer: the phase 2 B-F1RST trial

Abstract

Tumor mutational burden (TMB) in circulating tumor DNA (ctDNA) has shown promise in predicting benefit from PD-L1/PD-1 inhibitors in retrospective studies. Aiming to assess blood TMB (bTMB) prospectively, we conducted B-F1RST ( NCT02848651 ), an open-label, phase 2 trial that evaluated bTMB as a predictive biomarker for first-line atezolizumab monotherapy in locally advanced or metastatic stage IIIB-IVB non-small cell lung cancer (n = 152). The co-primary endpoints were investigator-assessed objective response rate (ORR) per RECIST version 1.1 and investigator-assessed progression-free survival (PFS) between high and low bTMB subgroups at the pre-defined bTMB ≥ 16 (14.5 mutations per megabase) cutoff. Secondary endpoints included investigator-assessed PFS, overall survival (OS) and duration of response at various bTMB cutoffs, as well as safety. Investigator-assessed PFS in the bTMB ≥ 16 versus bTMB < 16 groups was not statistically significant. However, bTMB ≥ 16 was associated with higher ORR, and ORR improved as bTMB cutoffs increased. No new safety signals were seen. In exploratory analyses, patients with maximum somatic allele frequency (MSAF) < 1% had higher ORR than patients with MSAF ≥ 1%. However, further analysis showed that this effect was driven by better baseline prognostics rather than by MSAF itself. At 36.5-month follow-up, an exploratory analysis of OS found that bTMB ≥ 16 was associated with longer OS than bTMB < 16. Further study and assay optimization will be required to develop bTMB as a predictive, standalone biomarker of immunotherapy or for use in conjunction with other biomarkers.

Fig. 1. Confirmed responses with atezolizumab.

ORRs are shown for bTMB-high (dark blue) and bTMB-low (light blue) subgroups at three different cutoffs, all of which showed significant differences between the subgroups. Data cut: 26 July 2019. Statistical tests (Cochran–Mantel–Haenszel) were unadjusted for multiple comparisons and two-sided at the 0.10 significance level. Rate difference (90% CI): bTMB ≥ 10, 13.3% (2.5, 24.0); bTMB ≥ 16, 30.2% (14.8, 45.6); and bTMB ≥ 20, 41.4% (22.1, 60.6). CR, complete response; PR, partial response.

Fig. 2. Final analysis outcomes at the bTMB16 cutoff.

a. Kaplan–Meier survival curves of PFS for bTMB < 16 (light blue) versus bTMB ≥ 16 (dark blue). b. Kaplan–Meier survival curves of OS for bTMB < 16 (light blue) versus bTMB ≥ 16 (dark blue). Data cut: 26 July 2019. Statistical tests (log-rank) were unadjusted for multiple comparisons and two-sided at the 0.10 significance level. m, median; mo, months; NE, not estimable.

Fig. 3. Depth of response according to PD-L1 and bTMB categories.

This waterfall plot shows the maximum change in SLD from baseline by response category. PD-L1^a and bTMB status by category are displayed below the graph. Patients without a post-baseline SLD assessment were not included. Data cut: 26 July 2019. N/A, not available; PD, progressive disease; PR, partial response; SD, stable disease. ^a PD-L1 status was determined by any standard-of-care assay.

Fig. 4. PFS and OS HRs at different bTMB cutoffs.

a, PFS by bTMB cutoff. b, OS by bTMB cutoff. n refers to the number of patients in the respective subgroup. The blue diamonds indicate the HR. Statistical tests (log-rank) were unadjusted for multiple comparisons and two-sided at the 0.10 significance level. The error bars show the 90% CI. mo, months.

Fig. 5. Long-term follow-up OS. Kaplan–Meier plots of OS at the bTMB ≥ 16 cutoff.

Statistical tests (log-rank) were unadjusted for multiple comparisons and two-sided at the 0.10 significance level. m, median; mo, months; NE, not estimable.

Fig. 6. Atezolizumab AEs observed in ≥ 10% of the ITT population.

The incidence of AEs by grade ≥ 3 (dark blue) and grade 1–2 (light blue).

Extended Data Fig. 1. B-F1RST study design.

B-F1RST prospectively evaluated atezolizumab monotherapy in the first-line treatment of patients with NSCLC. bTMB, blood-based tumor mutational burden; DOR, duration of response; ECOG PS, Eastern Cooperative Oncology Group performance status; INV, investigator; NSCLC, non-small cell lung cancer; OS, overall survival; PD, progressive disease; PD-L1, programmed death-ligand 1; PFS, progression-free survival; RECIST v1.1, Response Evaluation Criteria in Solid Tumors version 1.1. ^a Staging based on International Association for the Study of Lung Cancer Lung Cancer Staging Project 8th Edition of the TNM Classification for Lung Cancer. ^b Total enrolled, N = 153; however, 1 patient was never treated and was not included in the intention-to-treat population. ^c Tissue biopsy was optional.

Extended Data Fig. 2. Patient flow.

153 patients were allocated to receive atezolizumab. One patient was not treated and was excluded from the primary analysis. The biomarker-evaluable population excluded patients with MSAF < 1% and assay quality control failures. bTMB, blood-based tumor mutational burden; MSAF, maximum somatic allele frequency; NSCLC, non-small cell lung cancer; QC, quality control. ^a Staging based on International Association for the Study of Lung Cancer Lung Cancer Staging Project 8th Edition of the TNM Classification for Lung Cancer.

Extended Data Fig. 3. Unadjusted and adjusted MSAF-associated PFS.

a. Kaplan–Meier plots of unadjusted PFS. b. Kaplan–Meier plot of PFS adjusted for baseline imbalances. After the PFS curves were adjusted, the difference between arms was not significant. Statistical tests (log-rank) were unadjusted for multiple comparisons and 2-sided at the 0.05 significance level. HR, hazard ratio; m, median; MSAF, maximum somatic allele frequency; PFS, progression-free survival.

Extended Data Fig. 4. Mutant genes in bTMB subgroups with > 2% frequency.

a. The prevalence of genes in the MEP, MSAF ≥ 1%, bTMB ≥ 16 and bTMB < 16 populations. The bTMB-high population was enriched in TP53 mutations compared with the other groups. Differences for all other genes were not significant. bTMB, blood-based tumor mutational burden; MEP, molecularly evaluable population; MSAF, maximum somatic allele frequency. ^aDoes not include FANCD2.