A review of feature selection techniques in bioinformatics

Saeys, Yvan; Inza, Iñaki; Larrañaga, Pedro

doi:10.1093/bioinformatics/btm344

Cited by 4,347 publications

(2,961 citation statements)

References 128 publications

Supporting

Mentioning

2,770

Contrasting

Unclassified

Order By: Relevance

“…With the increased proliferation of powerful computational facilities, these algorithms have also been coupled with feature selection techniques that allow the decomposition of an optimal set of variables (spectral features) from the spectral data which maximize the predictive capacity and speed of implementation of the modelling algorithms, together with simplifying them and rendering them more interpretable scientifically [74]. All of the algorithms seek to calibrate a model that relates the spectral dataset (X-matrix) to a target of interest (Y-matrix, eg.…”

Section: Quantitative Multivariate Analytical Methodsologiesmentioning

confidence: 99%

Spectroscopic and chemometric approaches to radiobiological analyses

Meade

Byrne²,

Lyng

2010

Mutation Research/Reviews in Mutation Research

View full text Add to dashboard Cite

Vibrational spectroscopy is an attractive modality for the analysis of biological samples, providing a complete non-invasive acquisition of the biochemical fingerprint of the sample. It has been demonstrated that this data provides the means to assay multiple functional responses of a biological system at a spatial resolution as low as a micron within the sample. As the interaction of ionizing radiation with biological systems involves chemical reactions between the products of radiation induced damage and various structural and functional units within the cell, the vibrational spectroscopic modalities have received attention as potential measurement platforms for the in-situ examination of the chemistry of biological species in radiobiology. This presents challenges in relation to sample preparation and the construction of suitable analytical methodologies. In this work protocols for sample preparation and approaches to multivariate analysis of vibrational spectra in radiobiological analysis are detailed and the utility of the methodology in analyzing the evolution of biochemical responses to radiobiological damage are highlighted.

show abstract

Section: Quantitative Multivariate Analytical Methodsologiesmentioning

confidence: 99%

Spectroscopic and chemometric approaches to radiobiological analyses

Meade

Byrne²,

Lyng

2010

Mutation Research/Reviews in Mutation Research

View full text Add to dashboard Cite

show abstract

“…The large gap between optimal and estimated correlation is at least in part due to the inaccuracy of the cross-validation type error estimators with small sample size; see, e.g., [9]. …”

Section: Resultsmentioning

confidence: 99%

Bioprocess data mining using regularized regression and random forests

et al. 2013

View full text Add to dashboard Cite

BackgroundIn bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments. In particular, the integration of multiple data sets causes that these needs cannot be properly addressed by regression models that assume linear input-output relationship or unimodality of the response function. Regularized regression and random forests, on the other hand, have several properties that may appear important in this context. They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way.ResultsIn this work, the applicability of regularized regression (Lasso) and random forests (RF) in bioprocess data mining was examined, and their performance was benchmarked against multiple linear regression. As an example, we used data from a culture media optimization study for microbial hydrogen production. All the three methods were capable in providing a significant model when the five variables of the culture media optimization were linearly included in modeling. However, multiple linear regression failed when also the multiplications and squares of the variables were included in modeling. In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91).ConclusionWe found that both regularized regression and random forests were able to produce feasible models, and the latter was efficient in capturing the non-linearity in the data. In this kind of a data mining task of bioprocess data, both methods outperform multiple linear regression.

show abstract

“…Significance was assessed by student t test. All statistical tests were done employing SPSS program version 16 (SPSS Software, SPSS Inc., Chicago, USA) and the differences were considered significant at p B 0.05 [19].…”

Section: Resultsmentioning

confidence: 99%

Role of Heme Oxygenase, Leptin, Coenzyme Q10 and Trace Elements in Pre-eclamptic Women

Abo-Elmatty

Badawy²,

Hussein³

et al. 2012

Ind J Clin Biochem

View full text Add to dashboard Cite

The objective of this study to evaluate heme oxygenase (COHb), leptin and coenzyme Q10 (CoQ10) in pre-eclamptic women. Also Zinc, copper, Iron, total iron binding capacity, Ferritin and uric acid were assessed. 120 female subjects were included in this study. They were divided into, 60 female with normal pregnancy attending the outpatient clinic, 60 pre-eclamptic patients were recruited from obstetrics and gynaecology department Elkasr El-Aini hospital. The results showed that in preeclampatic group, leptin level was significantly increased while COHb and CoQ10 was significantly decreased. It is concluded that hemeoxygenase, leptin and coenzyme CoQ10 can be considered as new markers for prediction of pre-eclampsia.

show abstract

A review of feature selection techniques in bioinformatics

Cited by 4,347 publications

References 128 publications

Spectroscopic and chemometric approaches to radiobiological analyses

Spectroscopic and chemometric approaches to radiobiological analyses

Bioprocess data mining using regularized regression and random forests

Role of Heme Oxygenase, Leptin, Coenzyme Q10 and Trace Elements in Pre-eclamptic Women

Contact Info

Product

Resources

About