Unsupervised feature selection under perturbations: meeting the challenges of biological data

Varshavsky, Roy; Gottlieb, Assaf; Horn, D.; Linial, Michal

doi:10.1093/bioinformatics/btm528

Cited by 23 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As described by Varshavsky et al [29], differential singular value decomposition (SVD)-entropy , where is a singular value and is the total number of miRNAs, was attributed to each miRNA. After 100 independent cross-validations with 10% test samples and 90% training samples, the top miRNAs with larger were selected.…”

Section: Methodsmentioning

confidence: 99%

“…As in Abeel et al [14] and Varshavsky et al [29], we evaluated whether the selection of miRNAs for the discrimination between patients with diseases and healthy controls was stable [13]. The procedure was as follows:…”

Section: Methodsmentioning

confidence: 99%

“…These types of classification-independent and stability-problem-free approaches were invented only very recently (e.g., unsupervised feature filtering (UFF) [29]) and are still very rare.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Principal Component Analysis Based Feature Extraction Approach to Identify Circulating microRNA Biomarkers

Taguchi

Murakami

2013

PLoS ONE

View full text Add to dashboard Cite

The discovery and characterization of blood-based disease biomarkers are clinically important because blood collection is easy and involves relatively little stress for the patient. However, blood generally reflects not only targeted diseases, but also the whole body status of patients. Thus, the selection of biomarkers may be difficult. In this study, we considered miRNAs as biomarker candidates for several reasons. First, since miRNAs were discovered relatively recently, they have not yet been tested extensively. Second, since the number of miRNAs is relatively limited, selection is expected to be easy. Third, since they are known to play critical roles in a wide range of biological processes, their expression may be disease specific. We applied a newly proposed method to select combinations of miRNAs that discriminate between healthy controls and each of 14 diseases that include 5 cancers. A new feature selection method is based on principal component analysis. Namely this method does not require knowledge of whether each sample was derived from a disease patient or a healthy control. Using this method, we found that hsa-miR-425, hsa-miR-15b, hsa-miR-185, hsa-miR-92a, hsa-miR-140-3p, hsa-miR-320a, hsa-miR-486-5p, hsa-miR-16, hsa-miR-191, hsa-miR-106b, hsa-miR-19b, and hsa-miR-30d were potential biomarkers; combinations of 10 of these miRNAs allowed us to discriminate each disease included in this study from healthy controls. These 12 miRNAs are significantly up- or downregulated in most cancers and other diseases, albeit in a cancer- or disease-specific combinatory manner. Therefore, these 12 miRNAs were also previously reported to be cancer- and disease-related miRNAs. Many disease-specific KEGG pathways were also significantly enriched by target genes of up−/downregulated miRNAs within several combinations of 10 miRNAs among these 12 miRNAs. We also selected miRNAs that could discriminate one disease from another or from healthy controls. These miRNAs were found to be largely overlapped with miRNAs that discriminate each disease from healthy controls.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Principal Component Analysis Based Feature Extraction Approach to Identify Circulating microRNA Biomarkers

Taguchi

Murakami

2013

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…However, entropy can also be used to measure the amount of information or variance embedded in a cluster, and to quantify the deviation of the cluster's eigenvalue distribution from a uniform one (Alter et al, 2000). This idea has been used in the context of biological systems (Varshavsky et al, 2007;Varshavsky et al, 2006) and economic systems (Shapira et al, 2009). The eigenvalue entropy is defined as…”

Section: Quantifying Cluster Information: Cluster Entropymentioning

confidence: 99%

Functional Holography and Cliques in Brain Activation Patterns

Jacob¹,

Papo²,

Hendler³

et al. 2012

Advances in Brain Imaging

View full text Add to dashboard Cite

“…Entropy can be used to quantify the deviation of the cluster's eigenvalue distribution from a uniform one (Alter et al, 2000). This idea was used in the context of biological systems (Varshavsky et al, 2006(Varshavsky et al, , 2007 and economic systems (Shapira et al, 2009). We calculated the eigenvalue entropy defined by,…”

Section: Calculation Of Cluster Entropymentioning

confidence: 99%