Research Article

A Semiautomated Framework for Integrating Expert Knowledge into Disease Marker Identification

Table 1

Optimal integrated CAs derived from (A) the distance-based hierarchical clustering and (B) the disease-model-related functional selection approaches.

Clustering based on
Optimal Integrated CA
Distance matrix Data expression profiles Functional relationshipsA combination of the two
No. of clusters1612612612

(A) Different distance matricesBALFFull0.830.860.790.930.800.810.81
Partial0.930.960.961.001.000.99
PlasmaFull0.660.680.540.62
Partial0.770.790.83

Number of proteins1AllTop 3
No. of clusters112112

(B) Disease model-related functional selectionBALFFull0.810.900.880.82
Partial0.930.99
PlasmaFull0.570.560.590.65
Partial0.730.87

This refers to the different number of significantly changed proteins (all proteins or top 3 proteins) used in each cluster.