A Random Forest Genomic Classifier for Tumor Agnostic Prediction of Response to Anti-PD1 Immunotherapy. (November 2022)

• Record Type: Journal Article
• Authors: Bigelow, Emma; Saria, Suchi; Piening, Brian; Curti, Brendan; Dowdell, Alexa; Weerasinghe, Roshanthi; Bifulco, Carlo; Urba, Walter; Finkelstein, Noam; Fertig, Elana J; Baras, Alex; Zaidi, Neeha; Jaffee, Elizabeth; Yarchoan, Mark
• Is Part Of: Cancer informatics. Volume 21(2022)
• Publication Date: 2022-11
• Subjects: Checkpoint inhibitors -- therapeutic response -- algorithmic biomarker -- patient stratification -- anti-PD-1 immunotherapy; Bioinformatics -- Periodicals; Biology -- Data processing -- Periodicals; Cancer -- Periodicals; Cancer -- Research -- Periodicals; Computational biology -- Periodicals; 570.285
• DOI: 10.1177/11769351221136081
• Languages: English
• ISSNs: 1176-9351

Abstract

Tumor mutational burden (TMB), a surrogate for tumor neoepitope burden, is used as a pan-tumor biomarker to identify patients who may benefit from anti-program cell death 1 (PD1) immunotherapy, but it is an imperfect biomarker. Multiple additional genomic characteristics are associated with anti-PD1 responses, but the combined predictive value of these features and the added informativeness of each respective feature remains unknown. We evaluated whether machine learning (ML) approaches using proposed determinants of anti-PD1 response derived from whole exome sequencing (WES) could improve prediction of anti-PD1 responders over TMB alone. Random forest classifiers were trained on publicly available anti-PD1 data (n = 104), and subsequently tested on an independent anti-PD1 cohort (n = 69). Both the training and test datasets included a range of cancer types such as non-small cell lung cancer (NSCLC), head and neck squamous cell carcinoma (HNSCC), melanoma, and smaller numbers of patients from other tumor types. Features used include summaries such as TMB and number of frameshift mutations, as well as more gene-level features such as counts of mutations associated with immune checkpoint response and resistance. Both ML algorithms demonstrated area under the receiver-operator curves (AUC) that exceeded TMB alone (AUC 0.63 "human-guided, " 0.64 "cluster, " and 0.58 TMB alone). Mutations within oncogenes disproportionately modulate anti-PD1 responses relative to their overall contribution to tumor neoepitope burden. The use of a ML algorithm evaluating multiple proposed genomic determinants of anti-PD1 responses modestly improves performance over TMB alone, highlighting the need to integrate other biomarkers to further improve model performance.