Reliability of panel-based mutational signatures for immune-checkpoint-inhibition efficacy prediction in non-small cell lung cancer

•A previously built efficacy predictor did poorly when tested on panel sequencing mutations.•Corresponding mutational signature attributions (MSA) had a large false negative rate.•All tested panels had large reconstruction errors and misattributions in the MSA.•The panel size of the sequencing assay appears as the primary bottleneck. Mutational signatures (MS) are gaining traction for deriving therapeutic insights for immune checkpoint inhibition (ICI). We asked if MS attributions from comprehensive targeted sequencing assays are reliable enough for predicting ICI efficacy in non-small cell lung cancer (NSCLC). Somatic mutations of m = 126 patients were assayed using panel-based sequencing of 523 cancer-related genes. In silico simulations of MS attributions for various panels were performed on a separate dataset of m = 101 whole genome sequenced patients. Non-synonymous mutations were deconvoluted using COSMIC v3.3 signatures and used to test a previously published machine learning classifier. The ICI efficacy predictor performed poorly with an accuracy of 0.51-0.09+0.09, average precision of 0.52-0.11+0.11, and an area under the receiver operating characteristic curve of 0.50-0.09+0.10. Theoretical arguments, experimental data, and in silico simulations pointed to false negative rates (FNR) related to panel size. A secondary effect was observed, where deconvolution of small ensembles of point mutations lead to reconstruction errors and misattributions. MS attributions from current targeted panel sequencing are not reliable enough to predict ICI efficacy. We suggest that, for downstream classification tasks in NSCLC, signature attributions be based on whole exome or genome sequencing instead.