Ensemble outlier detection and gene selection in triple-negative breast cancer data
Abstract Background Learning accurate models from ‘omics data is bringing many challenges due to their inherent high-dimensionality, e.g. the number of gene expression variables, and comparatively lower sample sizes, which leads to ill-posed inverse problems. Furthermore, the presence of outliers, e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-018-2149-7 |
| _version_ | 1818539280914448384 |
|---|---|
| author | Marta B. Lopes André Veríssimo Eunice Carrasquinha Sandra Casimiro Niko Beerenwinkel Susana Vinga |
| author_facet | Marta B. Lopes André Veríssimo Eunice Carrasquinha Sandra Casimiro Niko Beerenwinkel Susana Vinga |
| author_sort | Marta B. Lopes |
| collection | DOAJ |
| description | Abstract Background Learning accurate models from ‘omics data is bringing many challenges due to their inherent high-dimensionality, e.g. the number of gene expression variables, and comparatively lower sample sizes, which leads to ill-posed inverse problems. Furthermore, the presence of outliers, either experimental errors or interesting abnormal clinical cases, may severely hamper a correct classification of patients and the identification of reliable biomarkers for a particular disease. We propose to address this problem through an ensemble classification setting based on distinct feature selection and modeling strategies, including logistic regression with elastic net regularization, Sparse Partial Least Squares - Discriminant Analysis (SPLS-DA) and Sparse Generalized PLS (SGPLS), coupled with an evaluation of the individuals’ outlierness based on the Cook’s distance. The consensus is achieved with the Rank Product statistics corrected for multiple testing, which gives a final list of sorted observations by their outlierness level. Results We applied this strategy for the classification of Triple-Negative Breast Cancer (TNBC) RNA-Seq and clinical data from the Cancer Genome Atlas (TCGA). The detected 24 outliers were identified as putative mislabeled samples, corresponding to individuals with discrepant clinical labels for the HER2 receptor, but also individuals with abnormal expression values of ER, PR and HER2, contradictory with the corresponding clinical labels, which may invalidate the initial TNBC label. Moreover, the model consensus approach leads to the selection of a set of genes that may be linked to the disease. These results are robust to a resampling approach, either by selecting a subset of patients or a subset of genes, with a significant overlap of the outlier patients identified. Conclusions The proposed ensemble outlier detection approach constitutes a robust procedure to identify abnormal cases and consensus covariates, which may improve biomarker selection for precision medicine applications. The method can also be easily extended to other regression models and datasets. |
| first_indexed | 2024-12-11T21:39:57Z |
| format | Article |
| id | doaj.art-2e73e1be010c4d1f9ef4b704c68dcddb |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-11T21:39:57Z |
| publishDate | 2018-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-2e73e1be010c4d1f9ef4b704c68dcddb2022-12-22T00:49:51ZengBMCBMC Bioinformatics1471-21052018-05-0119111510.1186/s12859-018-2149-7Ensemble outlier detection and gene selection in triple-negative breast cancer dataMarta B. Lopes0André Veríssimo1Eunice Carrasquinha2Sandra Casimiro3Niko Beerenwinkel4Susana Vinga5IDMEC, Instituto Superior Técnico, Universidade de LisboaIDMEC, Instituto Superior Técnico, Universidade de LisboaIDMEC, Instituto Superior Técnico, Universidade de LisboaLuis Costa Lab, Instituto de Medicina Molecular, Faculdade de Medicina da Universidade de LisboaDepartment of Biosystems Science and Engineering, ETH ZurichIDMEC, Instituto Superior Técnico, Universidade de LisboaAbstract Background Learning accurate models from ‘omics data is bringing many challenges due to their inherent high-dimensionality, e.g. the number of gene expression variables, and comparatively lower sample sizes, which leads to ill-posed inverse problems. Furthermore, the presence of outliers, either experimental errors or interesting abnormal clinical cases, may severely hamper a correct classification of patients and the identification of reliable biomarkers for a particular disease. We propose to address this problem through an ensemble classification setting based on distinct feature selection and modeling strategies, including logistic regression with elastic net regularization, Sparse Partial Least Squares - Discriminant Analysis (SPLS-DA) and Sparse Generalized PLS (SGPLS), coupled with an evaluation of the individuals’ outlierness based on the Cook’s distance. The consensus is achieved with the Rank Product statistics corrected for multiple testing, which gives a final list of sorted observations by their outlierness level. Results We applied this strategy for the classification of Triple-Negative Breast Cancer (TNBC) RNA-Seq and clinical data from the Cancer Genome Atlas (TCGA). The detected 24 outliers were identified as putative mislabeled samples, corresponding to individuals with discrepant clinical labels for the HER2 receptor, but also individuals with abnormal expression values of ER, PR and HER2, contradictory with the corresponding clinical labels, which may invalidate the initial TNBC label. Moreover, the model consensus approach leads to the selection of a set of genes that may be linked to the disease. These results are robust to a resampling approach, either by selecting a subset of patients or a subset of genes, with a significant overlap of the outlier patients identified. Conclusions The proposed ensemble outlier detection approach constitutes a robust procedure to identify abnormal cases and consensus covariates, which may improve biomarker selection for precision medicine applications. The method can also be easily extended to other regression models and datasets.http://link.springer.com/article/10.1186/s12859-018-2149-7Ensemble modelingHigh-dimensionalityOutlier detectionRank Product testTriple-negative breast cancer |
| spellingShingle | Marta B. Lopes André Veríssimo Eunice Carrasquinha Sandra Casimiro Niko Beerenwinkel Susana Vinga Ensemble outlier detection and gene selection in triple-negative breast cancer data BMC Bioinformatics Ensemble modeling High-dimensionality Outlier detection Rank Product test Triple-negative breast cancer |
| title | Ensemble outlier detection and gene selection in triple-negative breast cancer data |
| title_full | Ensemble outlier detection and gene selection in triple-negative breast cancer data |
| title_fullStr | Ensemble outlier detection and gene selection in triple-negative breast cancer data |
| title_full_unstemmed | Ensemble outlier detection and gene selection in triple-negative breast cancer data |
| title_short | Ensemble outlier detection and gene selection in triple-negative breast cancer data |
| title_sort | ensemble outlier detection and gene selection in triple negative breast cancer data |
| topic | Ensemble modeling High-dimensionality Outlier detection Rank Product test Triple-negative breast cancer |
| url | http://link.springer.com/article/10.1186/s12859-018-2149-7 |
| work_keys_str_mv | AT martablopes ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata AT andreverissimo ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata AT eunicecarrasquinha ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata AT sandracasimiro ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata AT nikobeerenwinkel ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata AT susanavinga ensembleoutlierdetectionandgeneselectionintriplenegativebreastcancerdata |