Evidence-Based Complementary and Alternative Medicine / 2013 / Article / Tab 3

Research Article

Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection

Table 3

Pearson correlation coefficient matrixes of rank lists by t-test, PLS, SVM, and RF in 2 cases based on all variables (A-B) and identified metabolites (C-D).

MethodtRankaPLSRankbRFRankcSVMRankdLDARanke

Pearson correlation coefficient matrix based on all variables

(A) Normal versus CRC
tRank1.0000.794f0.5750.3270.342
PLSRank0.7941.0000.5740.3280.342
RFRank0.5750.5741.0000.2100.256
SVMRank0.3270.3280.2101.0000.167
LDARank0.3420.3420.2560.1671.000
(B) Pre versus post
tRank1.000 0.232 0.217 0.021 0.032
PLSRank0.232 1.000 0.652 0.066 0.066
RFRank0.217 0.652 1.000 0.086 0.057
SVMRank0.021 0.066 0.086 1.000 0.007
LDARank0.032 0.066 0.057 0.007 1.000

Pearson correlation coefficient matrix based on identified metabolites

(C) Normal versus CRC
tRank1.000 0.7530.754 0.364 0.340
PLSRank0.7531.000 0.756 0.267 0.340
RFRank0.754 0.756 1.000 0.495 0.308
SVMRank0.364 0.267 0.495 1.000 0.190
LDARank0.340 0.340 0.308 0.190 1.000
(D) Pre versus post
tRank1.000 0.272 0.258 0.194 0.187
PLSRank0.272 1.000 0.733 0.048 0.044
RFRank0.258 0.733 1.000 0.034 0.041
SVMRank0.194 0.048 0.034 1.000 0.187
LDARank0.187 0.044 0.041 0.187 1.000

variable rank by the value of -test.
bvariable rank by the VIP value of PLS.
cvariable rank by the Gini value of RF.
dvariable rank by the SVM-REF.
evariable rank by the LDA coefficient.
fPearson correlation coefficient of PLS and -test variable rank lists for differentiating Normal and CRC.

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.