A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations
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...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-11-01
|
Series: | Frontiers in Genetics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2020.585029/full |
id |
doaj-784d04f595404629ad6a4de441ec8bc9 |
---|---|
record_format |
Article |
spelling |
doaj-784d04f595404629ad6a4de441ec8bc92020-11-25T04:11:19ZengFrontiers Media S.A.Frontiers in Genetics1664-80212020-11-011110.3389/fgene.2020.585029585029A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number VariationsYulin Zhang0Tong Feng1Shudong Wang2Ruyi Dong3Jialiang Yang4Jionglong Su5Bo Wang6College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, ChinaCollege of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, ChinaCollege of Computer and Communication Engineering, China University of Petroleum (East China), Qingdao, ChinaGeneis (Beijing) Co., Ltd., Beijing, ChinaGeneis (Beijing) Co., Ltd., Beijing, ChinaSchool of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi’an Jiaotong-Liverpool University, Suzhou, ChinaGeneis (Beijing) Co., Ltd., Beijing, ChinaThe 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.https://www.frontiersin.org/articles/10.3389/fgene.2020.585029/fulltissue-of-origincopy number variationsmulticlassXGBoostextremely randomized treeprincipal component analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yulin Zhang Tong Feng Shudong Wang Ruyi Dong Jialiang Yang Jionglong Su Bo Wang |
spellingShingle |
Yulin Zhang Tong Feng Shudong Wang Ruyi Dong Jialiang Yang Jionglong Su Bo Wang A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations Frontiers in Genetics tissue-of-origin copy number variations multiclass XGBoost extremely randomized tree principal component analysis |
author_facet |
Yulin Zhang Tong Feng Shudong Wang Ruyi Dong Jialiang Yang Jionglong Su Bo Wang |
author_sort |
Yulin Zhang |
title |
A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations |
title_short |
A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations |
title_full |
A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations |
title_fullStr |
A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations |
title_full_unstemmed |
A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations |
title_sort |
novel xgboost method to identify cancer tissue-of-origin based on copy number variations |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Genetics |
issn |
1664-8021 |
publishDate |
2020-11-01 |
description |
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. |
topic |
tissue-of-origin copy number variations multiclass XGBoost extremely randomized tree principal component analysis |
url |
https://www.frontiersin.org/articles/10.3389/fgene.2020.585029/full |
work_keys_str_mv |
AT yulinzhang anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT tongfeng anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT shudongwang anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT ruyidong anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT jialiangyang anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT jionglongsu anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT bowang anovelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT yulinzhang novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT tongfeng novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT shudongwang novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT ruyidong novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT jialiangyang novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT jionglongsu novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations AT bowang novelxgboostmethodtoidentifycancertissueoforiginbasedoncopynumbervariations |
_version_ |
1724418116369252352 |