Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Figure 3 | BMC Bioinformatics

Figure 3

From: A comparison of feature selection and classification methods in DNA methylation studies using the Illumina Infinium platform

Figure 3

PPV performance comparisons of all three feature selection methods: without-filtering (WF, pink), variance-filtering (VF, brown), and supervised-PCA (SPCA, purple) on beta-value methylation profiles. A) diagnostic setting in UKOPS, ENDOM, CERVX, BC and LC with the top 200, 1500, 2500, 1500, and 3000 diagnosis-associated-CpGs as the evaluation sets respectively; and B) age setting in T1D, OVC, CERVX, UKOPS, ENDOM, and BC with the top 1000, 500, 200, 500, 200, and 1500 age-associated-CpGs as evaluation sets, respectively. A total of 50 training-test set partitions were used.

Back to article page