Figure 3 from Human Papillomavirus 42 Drives Digital Papillary Adenocarcinoma and Elicits a Germ Cell–like Program Conserved in HPV-Positive Cancers

Abstract

<p>Oncogenic HPVs induce a germ cell–like transcriptional program conserved throughout HPV-driven cancers. <b>A,</b> Overview of the random forest (RF) feature selection and machine learning procedure to identify a transcriptional fingerprint of HPV-driven oncogenesis. CESC and HNSCC expression data were annotated with HPV status (data acquisition), commonly differentially expressed genes between HPV<sup>+</sup> and HPV<sup>−</sup> were identified (data preparation), and 12 protein-coding signature genes (RF12) were identified (feature selection). Four different machine learning models were trained with RF12 on a subset of DPA, CESC, and HNSCC samples (model training); the model with the best hyperparameters was evaluated using the withheld sample subset and used to classify Genotype-Tissue Expression (GTEx), skin warts, or normal skin expression data (deployment). <b>B,</b> Contribution of RF12 signature genes to cumulative feature importance (%) to discriminate between HPV<sup>+</sup> and HPV<sup>−</sup> tumor samples. <b>C,</b> Uniform manifold approximation and projection (UMAP) dimensionality reduction of RF12 expression in DPA, CESC, HNSCC, and skin warts. <b>D,</b> HPV<sup>+</sup> probability scores were calculated by RF12 for CESC, HNSCC, DPA, skin warts, and normal skin. For CESC, HNSCC, and DPA, the test set samples are displayed. <b>E,</b> HPV<sup>+</sup> probability scores for HNSCC calculated for <i>CDKN2A</i> and <i>SYCP2</i> alone, the combination of <i>CDKN2A</i> and <i>SYCP2</i> (RF2), and RF12. <b>F,</b> HPV<sup>+</sup> probability scores were calculated by RF12 for 31 normal tissues obtained from the GTEx database. <b>G,</b> Expression levels of RF12 genes in 15 cell types obtained from Human Protein Atlas. <b>H,</b> Schematic model of the germ cell–like program in HPV-driven cancer.</p>

Related Publications