GENE EXPRESSION PROFILES STUDY

Biopsy Samples

1 Sample Groups Biopsy

• Group 1: NORMAL POSTTRANSPLANT BIOPSIES (n=21)
• Group 2: ACUTE REJECTION (n=8)
• Group 3: CHRONIC ANTIBODY MEDIATED REJECTION (n=32)
• Group 4: TRANSPLANT GLOMERULOPATHY WITHOUT DSA (n=9)
• Group 5: IFTA (n=17)
• Group 6: IFTA with inflammation (n= 28)
• Group 7: GLOMERULAR DISEASE (n= 37)
• Group 8: ATN (n= 19)

1.1 Sample Summary

2 New Comparisons: kSORT

kSORT assay genes (table below) predicting acute rejection (Group 3), chronic antibody mediated rejection (Group 4), and CTMR viremia (Group 5) compared to Groups 1, 2 and 6.

2.1 Predicting Acute Rejection (G2 VS. G1+G5+G8)

2.1.1 kSORT Subset Gene Expression

2.1.2 kSORT Genes as predictors

A Support Vector Machine (SVM) algorithm was used to predict the classes based on the expression values of the kSORT genes. A 5-fold cross validation was used when generating the confusion matrices and the density plot correspond to the area under the receiver operating characteristic curve from the 5-fold cross-validation.

2.1.3 Feature selection: finding an optimal subset of kSORT Genes

A Recursive Feature Elimination (RFE) with 5-fold cross-validation with a Support Vector Machine algorithm was used to select the optimal subset of features that maximise the area under the receiver operating characteristic curve.

2.2 Predicting Chronic Antibody Mediated Rejection (G3 VS. G1+G5+G8)

2.2.1 kSORT Subset Gene Expression

2.2.2 kSORT Genes as predictors

A Support Vector Machine (SVM) algorithm was used to predict the classes based on the expression values of the kSORT genes. A 5-fold cross validation was used when generating the confusion matrices and the density plot correspond to the area under the receiver operating characteristic curve from the 5-fold cross-validation.

2.2.3 Feature selection: finding an optimal subset of kSORT Genes

A Recursive Feature Elimination (RFE) with 5-fold cross-validation with a Support Vector Machine algorithm was used to select the optimal subset of features that maximise the area under the receiver operating characteristic curve.

2.3 Predicting Rejection (G2+G3 VS. G1+G5+G8)

2.3.1 kSORT Subset Gene Expression

2.3.2 kSORT Genes as predictors

2.3.3 Feature selection: finding an optimal subset of kSORT Genes

A Recursive Feature Elimination (RFE) with 5-fold cross-validation with a Support Vector Machine algorithm was used to select the optimal subset of features that maximise the area under the receiver operating characteristic curve.

2.4 Predicting Chronic T-Cell Mediated Rejection (G4+G6+G7 VS. G1+G5+G8)

2.4.1 kSORT Subset Gene Expression

2.4.2 kSORT Genes as predictors

2.4.3 Feature selection: finding an optimal subset of kSORT Genes