Cross-platform methylation-based site of origin classification for squamous cell carcinomas

Squamous cell carcinomas (SCCs) are one of the most common cancer types and can arise at nearly any anatomic site. As SCCs are one of the most common metastases, do not have reliable site-specific morphologic or genomic features and have considerable morphologic and immunohistochemical overlap with urothelial carcinomas, distinguishing between primary and metastatic squamous appearing tumors can be challenging. This distinction can be critical to clinical management. We present SquaMOS (Squamous cell carcinoma Methylation for Origin Site), a methylation-based classifier to predict site-of-origin of squamous appearing carcinomas. Trained on publicly available array-based methylation data from 1062 primary SCCs (from lung, head & neck, cervix and esophagus) and urothelial carcinomas, SquaMOS predicted site-of-origin in primary tumors with 96.1% accuracy in an internal test set (n=458) and 97.4% accuracy in an external test set from three institutions (n=78). On metastatic tumors (n=51), SquaMOS predictions were 96.1% accurate. SquaMOS was directly applicable to shallow Nanopore sequencing data (CpG probe site coverage 0.25-2.88X) with an accuracy of 91.7% (n=36; 100% accurate for high-confidence predictions). When tested on SCCs outside the training set types (n=15, including 3 metastases to lung), no cases were misclassified as of lung origin, supporting accuracy of lung vs non-lung origin classification for diverse SCC types. Overall, we demonstrate highly accurate performance of the SquaMOS classifier on primary and metastatic tumors from multiple data sources, robust to suboptimal tumor purity. We illustrate transferability of our array-based classifier to low-depth Nanopore sequencing data, a potentially rapid means of site-of-origin determination in a clinical setting.