The feature selection bias problem in relation to high-dimensional gene data

Krawczuk, Jerzy; Łukaszuk, Tomasz

doi:10.1016/j.artmed.2015.11.001

Cited by 60 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selection bias has been reported when a given dataset is used for both variable selection and assessment of model performance, in turn leading to biased estimates and an increasing risk of false-positive discoveries due to overfitting (Ambroise and McLachlan, 2002; Castaldi et al , 2011; Cawley and Talbot, 2010; Krawczuk and Łukaszuk, 2016). Benefitting from the rdCV scheme, MUVR minimizes selection bias by performing variable selection and tuning of model parameters in the inner segments, followed by assessment of modelling performance using outer loop data held out of model construction and variable reduction.…”

Section: Resultsmentioning

confidence: 99%

“…It is also noteworthy that many existing variable selection techniques may suffer from selection bias, consequently inducing underestimation of error rates and leading to general model overfitting (Krawczuk and Łukaszuk, 2016). Such selection bias occurs when variable selection is carried out based on some or all of the samples used to estimate the prediction error in cross-validation scheme, which is frequently applied to optimize model parameters and to evaluate model performance (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Variable selection and validation in multivariate modelling

et al. 2018

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Variable selection and validation in multivariate modelling

et al. 2018

View full text Add to dashboard Cite

show abstract

“…It enables to propose simple biomarkers and to smoothly distinguish between them in terms of their performance. Second, we work with the independent RT-qPCR data set that serves to validate the selected biomarkers, remove the selection bias and get an unbiased estimate of their classification accuracy (expressed in terms of AUC to compensate for unbalanced classes) [27,28].…”

Section: Methodsmentioning

confidence: 99%

Early isolated V-lesion may not truly represent rejection of the kidney allograft

et al. 2018

View full text Add to dashboard Cite

Intimal arteritis is known to be a negative prognostic factor for kidney allograft survival. Isolated v-lesion (IV) is defined as intimal arteritis with minimal tubulointerstitial inflammation (TI). Although the Banff classification assesses IV as T cell-mediated rejection (TCMR), clinical, and prognostic significance of early IV (early IV, eIV) with negative C4d and donor-specific antibodies (DSA) remains unclear. To help resolve if such eIV truly represents acute rejection, a molecular study was performed. The transcriptome of eIV (n=6), T cell-mediated vascular rejection with rich TI (T cell-mediated vascular rejection, TCMRV, n=4) and non-rejection histologic findings (n=8) was compared using microarrays. A total of 310 genes were identified to be deregulated in TCMRV compared with eIV. Gene enrichment analysis categorized deregulated genes to be associated primarily with T-cells associated biological processes involved in an innate and adaptive immune and inflammatory response. Comparison of deregulated gene lists between the study groups and controls showed only a 1.7% gene overlap. Unsupervised hierarchical cluster analysis revealed clear distinction of eIV from TCMRV and showed similarity with a control group. Up-regulation of immune response genes in TCMRV was validated using RT-qPCR in a different set of eIV (n=12) and TCMRV (n=8) samples. The transcriptome of early IV (< 1 month) with negative C4d and DSA is associated with a weak immune signature compared with TCMRV and shows similarity with normal findings. Such eIV may feature non-rejection origin and reflect an injury distinct from an alloimmune response. The present study supports use of molecular methods when interpreting kidney allograft biopsy findings.

show abstract

“…By using a trainable multilayer artificial neural network (ANN) to replace hand-engineered features, deep learning takes the advantage of functional spectra, which are more robust and informative. In contrast, feature selection for high-dimensional data is a challenging task for conventional machine learning algorithms, which could lead to bias especially for high-throughput gene expression profiles 29 . To train a DeepCC classifier, we highly recommend employing a widely adopted molecular subtyping system, so that the deep features trained by the ANN can capture most relevant biological properties associated with each molecular subtype.…”

Section: Resultsmentioning

confidence: 99%

DeepCC: a novel deep learning-based framework for cancer molecular subtype classification

et al. 2019

View full text Add to dashboard Cite

Molecular subtyping of cancer is a critical step towards more individualized therapy and provides important biological insights into cancer heterogeneity. Although gene expression signature-based classification has been widely demonstrated to be an effective approach in the last decade, the widespread implementation has long been limited by platform differences, batch effects, and the difficulty to classify individual patient samples. Here, we describe a novel supervised cancer classification framework, deep cancer subtype classification (DeepCC), based on deep learning of functional spectra quantifying activities of biological pathways. In two case studies about colorectal and breast cancer classification, DeepCC classifiers and DeepCC single sample predictors both achieved overall higher sensitivity, specificity, and accuracy compared with other widely used classification methods such as random forests (RF), support vector machine (SVM), gradient boosting machine (GBM), and multinomial logistic regression algorithms. Simulation analysis based on random subsampling of genes demonstrated the robustness of DeepCC to missing data. Moreover, deep features learned by DeepCC captured biological characteristics associated with distinct molecular subtypes, enabling more compact within-subtype distribution and between-subtype separation of patient samples, and therefore greatly reduce the number of unclassifiable samples previously. In summary, DeepCC provides a novel cancer classification framework that is platform independent, robust to missing data, and can be used for single sample prediction facilitating clinical implementation of cancer molecular subtyping.

show abstract

The feature selection bias problem in relation to high-dimensional gene data

Cited by 60 publications

References 21 publications

Variable selection and validation in multivariate modelling

Variable selection and validation in multivariate modelling

Early isolated V-lesion may not truly represent rejection of the kidney allograft

DeepCC: a novel deep learning-based framework for cancer molecular subtype classification

Contact Info

Product

Resources

About