Cancer of unknown primary (CUP) refers to cancer with primary lesion unidentifiable by regular pathological and clinical diagnostic methods. This kind of cancer is extremely difficult to treat, and patients with CUP usually have a very short survival time. Recent studies have suggested that cancer treatment targeting primary lesion will significantly improve the survival of CUP patients. Thus, it is critical to develop accurate yet fast methods to infer the tissue-of-origin (TOO) of CUP. In the past years, there are a few computational methods to infer TOO based on single omics data like gene expression, methylation, somatic mutation, and so on. However, the metastasis of tumor involves the interaction of multiple levels of biological molecules. In this study, we developed a novel computational method to predict TOO of CUP patients by explicitly integrating expression quantitative trait loci (eQTL) into an XGBoost classification model. We trained our model with The Cancer Genome Atlas (TCGA) data involving over 7,000 samples across 20 types of solid tumors. In the 10-fold cross-validation, the prediction accuracy of the model with eQTL was over 0.96, better than that without eQTL. In addition, we also tested our model in an independent data downloaded from Gene Expression Omnibus (GEO) consisting of 87 samples across 4 cancer types. The model also achieved an f1-score of 0.7–1 depending on different cancer types. In summary, eQTL was an important information in inferring cancer TOO and the model might be applied in clinical routine test for CUP patients in the future.
Professional sentiment runs through the whole career of English teachers, imperceptibly changes the teaching methods, teaching attitudes, and teaching values of English teachers, and presents the characteristics of essence, dispersion, compatibility, and synchronization in its unique way. To cultivate English teachers' professional feelings, on the one hand, it is necessary for English teachers to strengthen the study of professional knowledge, develop professional ability, and maintain the feelings of English teachers forever. On the other hand, schools should create a harmonious development environment and establish a benign incentive mechanism, and at the same time, the society should also improve the status of English teachers, and increase the investment in English education resources.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.