Skip to main content

Table 4 Parameters for OPLS-DA models derived from 1H-NMR spectra of plasma samples from controls and micro and SD patients

From: Blood metabolomic fingerprint is distinct in healthy coronary and in stenosing or microvascular ischemic heart disease

 

OPLS-DA models

Permutation*

Componentsa

R2Xcumb

R2Ycumc

Q2cumd

R2 intercept

Q2 intercept

Controls vs Micro vs SD

2P + 1O

0.305

0.800

0.511

0.460

−0.188

Controls vs Micro

1P + 1O

0.317

0.947

0.697

0.513

−0.161

Controls vs SD

1P + 1O

0.247

0.871

0.512

0.507

−0.147

Micro vs SD

1P + 1O

0.301

0.895

0.673

0.425

−0.144

  1. * R2 and Q2 intercept values are indicative of a valid model. The permutation test was evaluated on the corresponding partial least square discriminant analysis (PLS-DA) model
  2. a Number of predictive and orthogonal components used to create the statistical models
  3. b,c R2X and R2Y indicate the cumulative explained fraction of the variation of the X block and Y block for the extracted components
  4. d Q2cum values indicate the cumulative predicted fraction of the variation of the Y block for the extracted components