An improved clear cell renal cell carcinoma stage prediction model based on gene sets
Abstract Background Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma and accounts for cancer-related deaths. Survival rates are very low when the tumor is discovered in the late-stage. Thus, developing an efficient strategy to stratify patients by the stage...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-06-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-020-03543-0 |
id |
doaj-b936896bfe6a4391b81ed4226cd87d91 |
---|---|
record_format |
Article |
spelling |
doaj-b936896bfe6a4391b81ed4226cd87d912020-11-25T03:18:24ZengBMCBMC Bioinformatics1471-21052020-06-0121111510.1186/s12859-020-03543-0An improved clear cell renal cell carcinoma stage prediction model based on gene setsFangjun Li0Mu Yang1Yunhe Li2Mingqiang Zhang3Wenjuan Wang4Dongfeng Yuan5Dongqi Tang6School of Information Science and Engineering, Shandong University, supported by Shandong Provincial Key Laboratory of Wireless Communication TechnologiesCenter for Gene and Immunothererapy, The Second Hospital of Shandong UniversitySchool of Information Science and Engineering, Shandong University, supported by Shandong Provincial Key Laboratory of Wireless Communication TechnologiesSchool of Information Science and Engineering, Shandong University, supported by Shandong Provincial Key Laboratory of Wireless Communication TechnologiesCenter for Gene and Immunothererapy, The Second Hospital of Shandong UniversitySchool of Information Science and Engineering, Shandong University, supported by Shandong Provincial Key Laboratory of Wireless Communication TechnologiesCenter for Gene and Immunothererapy, The Second Hospital of Shandong UniversityAbstract Background Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma and accounts for cancer-related deaths. Survival rates are very low when the tumor is discovered in the late-stage. Thus, developing an efficient strategy to stratify patients by the stage of the cancer and inner mechanisms that drive the development and progression of cancers is critical in early prevention and treatment. Results In this study, we developed new strategies to extract important gene features and trained machine learning-based classifiers to predict stages of ccRCC samples. The novelty of our approach is that (i) We improved the feature preprocessing procedure by binning and coding, and increased the stability of data and robustness of the classification model. (ii) We proposed a joint gene selection algorithm by combining the Fast-Correlation-Based Filter (FCBF) search with the information value, the linear correlation coefficient, and variance inflation factor, and removed irrelevant/redundant features. Then the logistic regression-based feature selection method was used to determine influencing factors. (iii) Classification models were developed using machine learning algorithms. This method is evaluated on RNA expression value of clear cell renal cell carcinoma derived from The Cancer Genome Atlas (TCGA). The results showed that the result on the testing set (accuracy of 81.15% and AUC 0.86) outperformed state-of-the-art models (accuracy of 72.64% and AUC 0.81) and a gene set FJL-set was developed, which contained 23 genes, far less than 64. Furthermore, a gene function analysis was used to explore molecular mechanisms that might affect cancer development. Conclusions The results suggested that our model can extract more prognostic information, and is worthy of further investigation and validation in order to understand the progression mechanism.http://link.springer.com/article/10.1186/s12859-020-03543-0Feature selectionMachine learningClear cell renal cell carcinomaCancer stage |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fangjun Li Mu Yang Yunhe Li Mingqiang Zhang Wenjuan Wang Dongfeng Yuan Dongqi Tang |
spellingShingle |
Fangjun Li Mu Yang Yunhe Li Mingqiang Zhang Wenjuan Wang Dongfeng Yuan Dongqi Tang An improved clear cell renal cell carcinoma stage prediction model based on gene sets BMC Bioinformatics Feature selection Machine learning Clear cell renal cell carcinoma Cancer stage |
author_facet |
Fangjun Li Mu Yang Yunhe Li Mingqiang Zhang Wenjuan Wang Dongfeng Yuan Dongqi Tang |
author_sort |
Fangjun Li |
title |
An improved clear cell renal cell carcinoma stage prediction model based on gene sets |
title_short |
An improved clear cell renal cell carcinoma stage prediction model based on gene sets |
title_full |
An improved clear cell renal cell carcinoma stage prediction model based on gene sets |
title_fullStr |
An improved clear cell renal cell carcinoma stage prediction model based on gene sets |
title_full_unstemmed |
An improved clear cell renal cell carcinoma stage prediction model based on gene sets |
title_sort |
improved clear cell renal cell carcinoma stage prediction model based on gene sets |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2020-06-01 |
description |
Abstract Background Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma and accounts for cancer-related deaths. Survival rates are very low when the tumor is discovered in the late-stage. Thus, developing an efficient strategy to stratify patients by the stage of the cancer and inner mechanisms that drive the development and progression of cancers is critical in early prevention and treatment. Results In this study, we developed new strategies to extract important gene features and trained machine learning-based classifiers to predict stages of ccRCC samples. The novelty of our approach is that (i) We improved the feature preprocessing procedure by binning and coding, and increased the stability of data and robustness of the classification model. (ii) We proposed a joint gene selection algorithm by combining the Fast-Correlation-Based Filter (FCBF) search with the information value, the linear correlation coefficient, and variance inflation factor, and removed irrelevant/redundant features. Then the logistic regression-based feature selection method was used to determine influencing factors. (iii) Classification models were developed using machine learning algorithms. This method is evaluated on RNA expression value of clear cell renal cell carcinoma derived from The Cancer Genome Atlas (TCGA). The results showed that the result on the testing set (accuracy of 81.15% and AUC 0.86) outperformed state-of-the-art models (accuracy of 72.64% and AUC 0.81) and a gene set FJL-set was developed, which contained 23 genes, far less than 64. Furthermore, a gene function analysis was used to explore molecular mechanisms that might affect cancer development. Conclusions The results suggested that our model can extract more prognostic information, and is worthy of further investigation and validation in order to understand the progression mechanism. |
topic |
Feature selection Machine learning Clear cell renal cell carcinoma Cancer stage |
url |
http://link.springer.com/article/10.1186/s12859-020-03543-0 |
work_keys_str_mv |
AT fangjunli animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT muyang animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT yunheli animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT mingqiangzhang animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT wenjuanwang animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT dongfengyuan animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT dongqitang animprovedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT fangjunli improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT muyang improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT yunheli improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT mingqiangzhang improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT wenjuanwang improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT dongfengyuan improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets AT dongqitang improvedclearcellrenalcellcarcinomastagepredictionmodelbasedongenesets |
_version_ |
1724626871782473728 |