A Mouse-Specific Model to Detect Genes under Selection in Tumors

Simple Summary We introduce GUST-mouse (Genes Under Selection in Tumors for mouse), a novel computational method designed to identify cancer driver genes within mouse tumor exomes. As the first method of its kind, GUST-mouse transcends conventional frequency-based rules. It incorporates molecular evolutionary theories and leverages transfer learning techniques to effectively differentiate between oncogenes, tumor suppressor genes, and passenger genes. When applied to mouse models of breast cancer, leukemia, and lung cancer, GUST-mouse unveiled that the emergence of somatic driver mutations is profoundly influenced by the genetically engineered background of the mouse models. A comparative analysis with human cancer drivers illuminated both shared and distinct patterns, casting new light on the intricate process of tumorigenesis. The pioneering framework of the GUST-mouse method opens a new avenue for identifying driver genes in non-human cancers.Abstract The mouse is a widely used model organism in cancer research. However, no computational methods exist to identify cancer driver genes in mice due to a lack of labeled training data. To address this knowledge gap, we adapted the GUST (Genes Under Selection in Tumors) model, originally trained on human exomes, to mouse exomes via transfer learning. The resulting tool, called GUST-mouse, can estimate long-term and short-term evolutionary selection in mouse tumors, and distinguish between oncogenes, tumor suppressor genes, and passenger genes using high-throughput sequencing data. We applied GUST-mouse to analyze 65 exomes of mouse primary breast cancer models and 17 exomes of mouse leukemia models. Comparing the predictions between cancer types and between human and mouse tumors revealed common and unique driver genes. The GUST-mouse method is available as an open-source R package on github.

Automated summary

GUST-mouse is a computational method designed to identify cancer driver genes within mouse tumor exomes. It incorporates molecular evolutionary theories and transfer learning techniques to differentiate between oncogenes, tumor suppressor genes, and passenger genes. Applied to mouse models of breast cancer, leukemia, and lung cancer, GUST-mouse revealed the influence of genetically engineered background on somatic driver mutations. Comparative analysis with human cancer drivers showed both common and unique patterns, shedding new light on tumorigenesis.