Dataset Information

Using recursive feature elimination in random forest to account for correlated variables in high dimensional data.

ABSTRACT: BACKGROUND:Random forest (RF) is a machine-learning method that generally works well with high-dimensional problems and allows for nonlinear relationships between predictors; however, the presence of correlated predictors has been shown to impact its ability to identify strong predictors. The Random Forest-Recursive Feature Elimination algorithm (RF-RFE) mitigates this problem in smaller data sets, but this approach has not been tested in high-dimensional omics data sets. RESULTS:We integrated 202,919 genotypes and 153,422 methylation sites in 680 individuals, and compared the abilities of RF and RF-RFE to detect simulated causal associations, which included simulated genotype-methylation interactions, between these variables and triglyceride levels. Results show that RF was able to identify strong causal variables with a few highly correlated variables, but it did not detect other causal variables. CONCLUSIONS:Although RF-RFE decreased the importance of correlated variables, in the presence of many correlated variables, it also decreased the importance of causal variables, making both hard to detect. These findings suggest that RF-RFE may not scale to high-dimensional data.

SUBMITTER: Darst BF

PROVIDER: S-EPMC6157185 | biostudies-literature | 2018 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using recursive feature elimination in random forest to account for correlated variables in high dimensional data.

Darst Burcu F BF Malecki Kristen C KC Engelman Corinne D CD

BMC genetics 20180917 Suppl 1

<h4>Background</h4>Random forest (RF) is a machine-learning method that generally works well with high-dimensional problems and allows for nonlinear relationships between predictors; however, the presence of correlated predictors has been shown to impact its ability to identify strong predictors. The Random Forest-Recursive Feature Elimination algorithm (RF-RFE) mitigates this problem in smaller data sets, but this approach has not been tested in high-dimensional omics data sets.<h4>Results</h4> ...[more]

PMID: 30255764

Similar Datasets

Project description:BackgroundClassification studies using gene expression datasets are usually based on small numbers of samples and tens of thousands of genes. The selection of those genes that are important for distinguishing the different sample classes being compared, poses a challenging problem in high dimensional data analysis. We describe a new procedure for selecting significant genes as recursive cluster elimination (RCE) rather than recursive feature elimination (RFE). We have tested this algorithm on six datasets and compared its performance with that of two related classification procedures with RFE.ResultsWe have developed a novel method for selecting significant genes in comparative gene expression studies. This method, which we refer to as SVM-RCE, combines K-means, a clustering method, to identify correlated gene clusters, and Support Vector Machines (SVMs), a supervised machine learning classification method, to identify and score (rank) those gene clusters for the purpose of classification. K-means is used initially to group genes into clusters. Recursive cluster elimination (RCE) is then applied to iteratively remove those clusters of genes that contribute the least to the classification performance. SVM-RCE identifies the clusters of correlated genes that are most significantly differentially expressed between the sample classes. Utilization of gene clusters, rather than individual genes, enhances the supervised classification accuracy of the same data as compared to the accuracy when either SVM or Penalized Discriminant Analysis (PDA) with recursive feature elimination (SVM-RFE and PDA-RFE) are used to remove genes based on their individual discriminant weights.ConclusionSVM-RCE provides improved classification accuracy with complex microarray data sets when it is compared to the classification accuracy of the same datasets using either SVM-RFE or PDA-RFE. SVM-RCE identifies clusters of correlated genes that when considered together provide greater insight into the structure of the microarray data. Clustering genes for classification appears to result in some concomitant clustering of samples into subgroups. Our present implementation of SVM-RCE groups genes using the correlation metric. The success of the SVM-RCE method in classification suggests that gene interaction networks or other biologically relevant metrics that group genes based on functional parameters might also be useful.

Project description:Background: Open spina bifida (myelomeningocele) is the result of the failure of spinal cord closing completely and is the second most common and severe birth defect. Open neural tube defects are multifactorial, and the exact molecular mechanism of the pathogenesis is not clear due to disease complexity for which prenatal treatment options remain limited worldwide. Artificial intelligence techniques like machine learning tools have been increasingly used in precision diagnosis. Objective: The primary objective of this study is to identify key genes for open neural tube defects using a machine learning approach that provides additional information about myelomeningocele in order to obtain a more accurate diagnosis. Materials and Methods: Our study reports differential gene expression analysis from multiple datasets (GSE4182 and GSE101141) of amniotic fluid samples with open neural tube defects. The sample outliers in the datasets were detected using principal component analysis (PCA). We report a combination of the differential gene expression analysis with recursive feature elimination (RFE), a machine learning approach to get 4 key genes for open neural tube defects. The features selected were validated using five binary classifiers for diseased and healthy samples: Logistic Regression (LR), Decision tree classifier (DT), Support Vector Machine (SVM), Random Forest classifier (RF), and K-nearest neighbour (KNN) with 5-fold cross-validation. Results: Growth Associated Protein 43 (GAP43), Glial fibrillary acidic protein (GFAP), Repetin (RPTN), and CD44 are the important genes identified in the study. These genes are known to be involved in axon growth, astrocyte differentiation in the central nervous system, post-traumatic brain repair, neuroinflammation, and inflammation-linked neuronal injuries. These key genes represent a promising tool for further studies in the diagnosis and early detection of open neural tube defects. Conclusion: These key biomarkers help in the diagnosis and early detection of open neural tube defects, thus evaluating the progress and seriousness in diseases condition. This study strengthens previous literature sources of confirming these biomarkers linked with open NTD's. Thus, among other prenatal treatment options present until now, these biomarkers help in the early detection of open neural tube defects, which provides success in both treatment and prevention of these defects in the advanced stage.

Project description:BackgroundPersistent liver inflammatory damage is the main risk factor for developing liver fibrosis, cirrhosis, and even hepatocellular carcinoma in chronic hepatitis B (CHB) patients. Thus, accurate prediction of the degree of liver inflammation is a high priority and a growing medical need.AimTo build an effective and robust non-invasive model for predicting hepatitis B-related hepatic inflammation.MethodsA total of 650 treatment-naïve CHB (402 HBeAg-positive and 248 HBeAg-negative) patients who underwent liver biopsy were enrolled in this study. Histological inflammation grading was assessed by the Ishak scoring system. Serum quantitative hepatitis B core antibody (qAnti-HBc) levels and 21 immune-related inflammatory factors were measured quantitatively using a chemiluminescent microparticle immunoassay. A backward feature elimination (BFE) algorithm utilizing random forest (RF) was used to select optional features and construct a combined model. The diagnostic abilities of the model or variables were evaluated based on the estimated area under the receiver operating characteristics curve (AUROC) and compared using the DeLong test.ResultsFour features were selected to predict moderate-to-severe inflammation in CHB patients using the RF-BFE method. These predictive features included qAnti-HBc, ALT, AST, and CXCL11. Spearman's correlation analysis indicated that serum qAnti-HBc, ALT, AST, and CXCL11 levels were positively correlated with the histology activity index (HAI) score. These selected features were incorporated into the model to establish a novel model named I-3A index. The AUROC [0.822; 95% confidence interval (CI): 0.790-0.851] of the I-3A index was significantly increased compared with qAnti-HBc alone (0.760, 95%CI: 0.724-0.792, P < 0.0001) in all CHB patients. The use of an I-3A index cutoff value of 0.41 produced a sensitivity of 69.17%, specificity of 81.44%, and accuracy of 73.8%. Additionally, the I-3A index showed significantly improved diagnostic performance for predicting moderate-to-severe inflammation in HBeAg-positive and HBeAg-negative CHB patients (0.829, 95%CI: 0.789-0.865 and 0.810, 95%CI: 0.755-0.857, respectively).ConclusionThe selected features of the I-3A index constructed using the RF-BFE algorithm can effectively predict moderate-to-severe liver inflammation in CHB patients.

Dataset Information

Using recursive feature elimination in random forest to account for correlated variables in high dimensional data.

Publications

Using recursive feature elimination in random forest to account for correlated variables in high dimensional data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets