Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Dec:2017:416-421.
doi: 10.1109/ISSPIT.2017.8388679. Epub 2018 Jun 21.

An Ensemble Feature Selection Method for Biomarker Discovery

Aliasghar Shahrjooihaghighi  1 , Hichem Frigui  1 , Xiang Zhang  2 , Xiaoli Wei  2 , Biyun Shi  2 , Ameni Trabelsi  1
Affiliations

An Ensemble Feature Selection Method for Biomarker Discovery

Aliasghar Shahrjooihaghighi et al. Proc IEEE Int Symp Signal Proc Inf Tech. 2017 Dec.

Abstract

Feature selection in Liquid Chromatography-Mass Spectrometry (LC-MS)-based metabolomics data (biomarker discovery) have become an important topic for machine learning researchers. High dimensionality and small sample size of LC-MS data make feature selection a challenging task. The goal of biomarker discovery is to select the few most discriminative features among a large number of irreverent ones. To improve the reliability of the discovered biomarkers, we use an ensemble-based approach. Ensemble learning can improve the accuracy of feature selection by combining multiple algorithms that have complementary information. In this paper, we propose an ensemble approach to combine the results of filter-based feature selection methods. To evaluate the proposed approach, we compared it to two commonly used methods, t-test and PLS-DA, using a real data set.

Keywords: biomarker discovery; ensemble feature selection; ensemble learning; filter methods; scoring functions.

PubMed Disclaimer

Figures

Fig. 1:
Fig. 1:
performance of the 5 individual feature selection algorithms when samples from groups 0 and 5 are considered.
Fig. 2:
Fig. 2:
performance of the 5 individual feature selection algorithms when samples from groups 0 and 1 are considered.
Fig. 3:
Fig. 3:
performance of the proposed ensemble approach when groups 0 and 5 are considered.
Fig. 4:
Fig. 4:
performance of the proposed ensemble approach when groups 0 and 1 are considered.
See this image and copyright information in PMC

References

    1. Colburn W, DeGruttola VG, DeMets DL, Downing GJ, Hoth DF, Oates JA, Peck CC, Schooley RT, Spilker BA, Woodcock J, et al., “Biomarkers and surrogate endpoints: Preferred definitions and conceptual framework. biomarkers definitions working group,” Clinical Pharmacol & Therapeutics, vol. 69, pp. 89–95, 2001. - PubMed
    1. Christin C, Hoefsloot HC, Smilde AK, Hoekman B, Suits F, Bischoff R, and Horvatovich P, “A critical assessment of feature selection methods for biomarker discovery in clinical proteomics,” Molecular & Cellular Proteomics, vol. 12, no. 1, pp. 263–276, 2013. - PMC - PubMed
    1. Saeys Y, Inza I, and Larrañaga P, “A review of feature selection techniques in bioinformatics,” bioinformatics, vol. 23, no. 19, pp. 2507–2517, 2007. - PubMed
    1. Awada W, Khoshgoftaar TM, Dittman D, Wald R, and Napolitano A, “A review of the stability of feature selection techniques for bioinformatics data,” in Information Reuse and Integration (IRI), 2012 IEEE 13th International Conference on, pp. 356–363, IEEE, 2012.
    1. Lazar C, Taminau J, Meganck S, Steenhoff D, Coletta A, Molter C, de Schaetzen V, Duque R, Bersini H, and Nowe A, “A survey on filter techniques for feature selection in gene expression microarray analysis,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 9, no. 4, pp. 1106–1119, 2012. - PubMed

LinkOut - more resources