1. Pancreatic cancer biomarker detection by two support vector strategies for recursive feature elimination.
- Author
-
Wang Y, Liu K, Ma Q, Tan Y, Du W, Lv Y, Tian Y, and Wang H
- Subjects
- Biomarkers, Tumor urine, Case-Control Studies, Humans, Matrix Metalloproteinase 7 genetics, Matrix Metalloproteinase 7 urine, Pancreas metabolism, Pancreatic Neoplasms genetics, Pancreatic Neoplasms urine, Prognosis, Proto-Oncogene Proteins c-fos genetics, Proto-Oncogene Proteins c-fos urine, Survival Rate, alpha-Macroglobulins genetics, alpha-Macroglobulins urine, Algorithms, Biomarkers, Tumor genetics, Gene Expression Profiling, Pancreas pathology, Pancreatic Neoplasms diagnosis, Support Vector Machine
- Abstract
Aim: Pancreatic cancer is one of the worst malignant tumors in prognosis. Therefore, to reduce the mortality rate of pancreatic cancer, early diagnosis and prompt treatment are particularly important., Results: We put forward a new feature-selection method that was used to find clinical markers for pancreatic cancer by combination of Support Vector Machine Recursive Feature Elimination (SVM-RFE) and Large Margin Distribution Machine Recursive Feature Elimination (LDM-RFE) algorithms. As a result, seven differentially expressed genes were predicted as specific biomarkers for pancreatic cancer because of their highest accuracy of classification on cancer and normal samples., Conclusion: Three (MMP7, FOS and A2M) out of the seven predicted gene markers were found to encode proteins secreted into urine, providing potential diagnostic evidences for pancreatic cancer.
- Published
- 2019
- Full Text
- View/download PDF