Abstract
The discovery of cancer of unknown primary (CUP) is of great significance in designing more effective treatments and improving the diagnostic efficiency in cancer patients. In the study, we develop an appropriate machine learning model for tracing the tissue of origin of CUP with high accuracy after feature engineering and model evaluation. Based on a copy number variation data consisting of 4,566 training cases and 1,262 independent validation cases, an XGBoost classifier is applied to 10 types of cancer. Extremely randomized tree (Extra tree) is used for dimension reduction so that fewer variables replace the original high-dimensional variables. Features with top 300 weights are selected and principal component analysis is applied to eliminate noise. We find that XGBoost classifier achieves the highest overall accuracy of 0.8913 in the 10-fold cross-validation for training samples and 0.7421 on independent validation datasets for predicting tumor tissue of origin. Furthermore, by contrasting various performance indices, such as precision and recall rate, the experimental results show that XGBoost classifier significantly improves the classification performance of various tumors with less prediction error, as compared to other classifiers, such as K-nearest neighbors (KNN), Bayes, support vector machine (SVM), and Adaboost. Our method can infer tissue of origin for the 10 cancer types with acceptable accuracy in both cross-validation and independent validation data. It may be used as an auxiliary diagnostic method to determine the actual clinicopathological status of specific cancer.
Highlights
Recent advances in molecular biology, e.g., genomics, proteomics, and metabolics, have resulted in a more accurate and specific prediction of tumor response to treatment, as well as trends in metastasis recurrence and prognosis
It is found that XGBoost classifier achieves the best result compared with four other classifiers
We propose a cancer type classifier that exploited the copy number variations data of the tumor samples
Summary
Recent advances in molecular biology, e.g., genomics, proteomics, and metabolics, have resulted in a more accurate and specific prediction of tumor response to treatment, as well as trends in metastasis recurrence and prognosis. Traditional detection methods, e.g., clinical, impact, and pathological examination, can only determine 50–80% of patients of metastasis cancer, while the remaining 20–50% of patients still cannot be determined (Chen et al, 2017) as more effective methods of diagnosis are required. In the metastasis of cancer, tumor cells are carried from the primary site to lymphatics, blood vessels, or other sites to continue to grow and form. XGBoost-Based Cancer Tissue-of-Origin Identification the same type of tumor. Identifying the type and origin of cancer is important to determine the most appropriate treatment for cancer patients. The molecular expression profile of tumor cells in the metastatic focus is more similar to that in the primary site but different from that in the metastatic site, suggesting that we can trace the tumor origin according to the molecular expression profile of tumor cells in the metastatic site
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
