Construction of prediction model for early screening in male patients with gastric cancer based on cell －free DNA methylation and machine learning
10.19405/j.cnki.issn1000-1492.2022.12.024
- Author:
Jie Ji
1
,
2
,
3
;
Jian Qi
1
,
2
,
3
;
Bo Hong
1
,
3
;
Shujie Wang
1
,
3
;
Ruifang Sun
4
;
Xueling Cao
4
;
Xiaojun Sun
1
,
3
;
Jinfu Nie
1
,
3
Author Information
1. Anhui Province Key Laboratory of Medical Physics and Technology，Center of Medical Physics and Technology， Hefei Institutes of Physical Science，Chinese Academy of Sciences，Hefei 230031
2. University of Science and Technology of China，Hefei Institutes of Physical Science，Hefei 230026
3. Hefei Cancer Hospital，Chinese Academy of Sciences， Hefei 230031
4. Shanxi Provincial Cancer Hospital，Biobank of Tumor，Taiyuan 030013
- Publication Type:Journal Article
- Keywords:
gastric cancer;
liquid biopsy;
cfDNA methylation;
MeDIP-seq;
machine learning
- From:
Acta Universitatis Medicinalis Anhui
2022;57(12):1991-1996
- CountryChina
- Language:Chinese
-
Abstract:
Objective :To construct a cell-free DNA ( cfDNA) methylation model for early screening in male pa- tients with gastric cancer by using novel cfDNA methylation detection technology．
Methods :Methylation informa- tion of the whole genome of gastric cancer patients were detected by cell-free methylated DNA immunoprecipitation and highthroughput sequencing ( cfMeDIP-seq ) technology and locate gastrogenic cfDNA． Then bioinformation methods were used to extract specific methylation labels which could distinguish GC patients and establish diagnosis model by random forest algorithm. Related validation clinical researches were also conducted.
Results :63 most sig- nificant DMR were selected to construct the cfDNA methylation model based on GC samples and normal control samples，the goal sensitivity was above 85 percent while the goal specificity was above 95% ．The sensitivity and specificity of the validation set were 98. 7% and 99. 0% while the area under curve(AUC) was 0. 999．
Conclusion:The cfDNA methylation model constructed in this study has good performance in predicting GC.
- Full text:2024072222270704138基于cfDNA甲基化和机器...男性胃癌早筛预测模型的建立_季杰.pdf
