Copy number variation in plasma as a tool for lung cancer prediction using Extreme Gradient Boosting (XGBoost) classifier

被引:58
作者
Yu, Daping [1 ,2 ]
Liu, Zhidong [1 ,2 ]
Su, Chongyu [1 ,2 ]
Han, Yi [1 ,2 ]
Duan, XinChun [1 ,2 ]
Zhang, Rui [1 ,2 ]
Liu, Xiaoshuang [3 ]
Yang, Yang [4 ]
Xu, Shaofa [1 ,2 ]
机构
[1] Capital Med Univ, Beijing Chest Hosp, Thorac Surg Dept, Area 1st,9 Compound,Beiguan St, Beijing, Peoples R China
[2] Beijing TB & Thorac Tumor Res Inst, Area 1st,9 Compound,Beiguan St, Beijing, Peoples R China
[3] Ping An Hlth Technol, Beijing, Peoples R China
[4] Beijing Gencode Diagnost Lab, Beijing, Peoples R China
关键词
cfDNA; CNV; early diagnosis; lung cancer; XGBoost; CIRCULATING-TUMOR DNA; HEPATOCELLULAR-CARCINOMA; RISK-FACTORS;
D O I
10.1111/1759-7714.13204
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Background The main cause of cancer death is lung cancer (LC) which usually presents at an advanced stage, but its early detection would increase the benefits of treatment. Blood is particularly favored in clinical research given the possibility of using it for relatively noninvasive analyses. Copy number variation (CNV) is a common genetic change in tumor genomes, and many studies have indicated that CNV-derived cell-free DNA (cfDNA) from plasma could be feasible as a biomarker for cancer diagnosis. Methods In this study, we determined the possibility of using chromosomal arm-level CNV from cfDNA as a biomarker for lung cancer diagnosis in a small cohort of 40 patients and 41 healthy controls. Arm-level CNV distributions were analyzed based on z score, and the machine-learning algorithm Extreme Gradient Boosting (XGBoost) was applied for cancer prediction. Results The results showed that amplifications tended to emerge on chromosomes 3q, 8q, 12p, and 7q. Deletions were frequently detected on chromosomes 22q, 3p, 5q, 16q, 10q, and 15q. Upon applying a trained XGBoost classifier, specificity and sensitivity of 100% were finally achieved in the test group (12 patients and 13 healthy controls). In addition, five-fold cross-validation proved the stability of the model. Finally, our results suggested that the integration of four arm-level CNVs and the concentration of cfDNA into the trained XGBoost classifier provides a potential method for detecting lung cancer. Conclusion Our results suggested that the integration of four arm-level CNVs and the concentration from of cfDNA integrated withinto the trained XGBoost classifier could become provides a potentially method for detecting lung cancer detection. Key points Significant findings of the study: Healthy individuals have different arm-level CNV profiles from cancer patients. Amplifications tend to emerge on chromosome 3q, 8q, 12p, 7q and deletions tend to emerge on chromosome 22q, 3p, 5q, 16q, 10q, 15q. What this study adds: CfDNA concentration, arm 10q, 3q, 8q, 3p, and 22q are key features for prediction. Trained XGBoost classifier is a potential method for lung cancer detection.
引用
收藏
页码:95 / 102
页数:8
相关论文
共 39 条
[1]   Risk factors of Lung Cancer in nonsmoker [J].
Akhtar, Nahid ;
Bansal, Jeena Gupta .
CURRENT PROBLEMS IN CANCER, 2017, 41 (05) :328-339
[2]  
[Anonymous], 2017, Consistent feature attribution for tree ensembles
[3]  
[Anonymous], 31 C NEUR INF PROC S
[4]   Using Machine Learning Algorithms for Breast Cancer Risk Prediction and Diagnosis [J].
Asri, Hiba ;
Mousannif, Hajar ;
Al Moatassime, Hassan ;
Noel, Thomas .
7TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT 2016) / THE 6TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2016) / AFFILIATED WORKSHOPS, 2016, 83 :1064-1069
[5]   Chromosomal imbalances in human lung cancer [J].
Balsara, BR ;
Testa, JR .
ONCOGENE, 2002, 21 (45) :6877-6883
[6]   Circulating tumor markers: harmonizing the yin and yang of CTCs and ctDNA for precision medicine [J].
Batth, I. S. ;
Mitra, A. ;
Manier, S. ;
Ghobrial, I. M. ;
Menter, D. ;
Kopetz, S. ;
Li, S. .
ANNALS OF ONCOLOGY, 2017, 28 (03) :468-477
[7]   The landscape of somatic copy-number alteration across human cancers [J].
Beroukhim, Rameen ;
Mermel, Craig H. ;
Porter, Dale ;
Wei, Guo ;
Raychaudhuri, Soumya ;
Donovan, Jerry ;
Barretina, Jordi ;
Boehm, Jesse S. ;
Dobson, Jennifer ;
Urashima, Mitsuyoshi ;
Mc Henry, Kevin T. ;
Pinchback, Reid M. ;
Ligon, Azra H. ;
Cho, Yoon-Jae ;
Haery, Leila ;
Greulich, Heidi ;
Reich, Michael ;
Winckler, Wendy ;
Lawrence, Michael S. ;
Weir, Barbara A. ;
Tanaka, Kumiko E. ;
Chiang, Derek Y. ;
Bass, Adam J. ;
Loo, Alice ;
Hoffman, Carter ;
Prensner, John ;
Liefeld, Ted ;
Gao, Qing ;
Yecies, Derek ;
Signoretti, Sabina ;
Maher, Elizabeth ;
Kaye, Frederic J. ;
Sasaki, Hidefumi ;
Tepper, Joel E. ;
Fletcher, Jonathan A. ;
Tabernero, Josep ;
Baselga, Jose ;
Tsao, Ming-Sound ;
Demichelis, Francesca ;
Rubin, Mark A. ;
Janne, Pasi A. ;
Daly, Mark J. ;
Nucera, Carmelo ;
Levine, Ross L. ;
Ebert, Benjamin L. ;
Gabriel, Stacey ;
Rustgi, Anil K. ;
Antonescu, Cristina R. ;
Ladanyi, Marc ;
Letai, Anthony .
NATURE, 2010, 463 (7283) :899-905
[8]   Invited review DNA copy number changes as diagnostic tools for lung cancer [J].
Bowcock, Anne M. .
THORAX, 2014, 69 (05) :495-496
[9]   Circulating-tumor DNA as an early detection and diagnostic tool [J].
Butler, Timothy M. ;
Spellman, Paul T. ;
Gray, Joe .
CURRENT OPINION IN GENETICS & DEVELOPMENT, 2017, 42 :14-21
[10]  
Chen T., 2016, KDD16 P 22 ACM, P785, DOI [DOI 10.1145/2939672.2939785, 10.1145/2939672.2939785]