Statistical Approaches to Candidate Biomarker Panel Selection

Abstract

The statistical analysis of robust biomarker candidates is a complex process, and is involved in several key steps in the overall biomarker development pipeline (see Fig. 22.1, Chap. 19 ). Initially, data visualization (Sect. 22.1, below) is important to determine outliers and to get a feel for the nature of the data and whether there appear to be any differences among the groups being examined. From there, the data must be pre-processed (Sect. 22.2) so that outliers are handled, missing values are dealt with, and normality is assessed. Once the processed data has been cleaned and is ready for downstream analysis, hypothesis tests (Sect. 22.3) are performed, and proteins that are differentially expressed are identified. Since the number of differentially expressed proteins is usually larger than warrants further investigation (50+ proteins versus just a handful that will be considered for a biomarker panel), some sort of feature reduction (Sect. 22.4) should be performed to narrow the list of candidate biomarkers down to a more reasonable number. Once the list of proteins has been reduced to those that are likely most useful for downstream classification purposes, unsupervised or supervised learning is performed (Sects. 22.5 and 22.6, respectively).

Keywords: Candidate biomarker selection; Data clustering; Data consistency; Data inspection; Data normalization; Data transformations; Machine learning; Outlier detection.

Fig. 22.1

Histograms for IP_10 Cytokine data. Dengue Fever is on the top; Dengue Hemorrhagic Fever is on the bottom

Fig. 22.2

Boxplots for IP_10 Cytokine data. Dengue Fever is on the left; Dengue Hemorrhagic Fever is on the right

Fig. 22.3

(a) Q-Q plot of IP-10 cytokine data for Dengue Hemorrhagic Fever, (b) Q-Q plot of IP-10 cytokine data for Dengue Fever

Fig. 22.4

SAM result for Aspergillosis dataset

Fig. 22.5

Hierarchical clustering of Dengue Fever study. Subjects labeled 1–30 are subjects with Dengue Fever; Subjects labeled 31–52 are subjects with Dengue Hemorrhagic Fever

Fig. 22.6

(a) CART tree for DF vs DHF comparison, (b) Variable importance for the CART model

Fig. 22.7

ROC Curves for both the training and testing datasets. The blue curve represents the training data, and the red curve represents the testing data. The AUC for the training data is 0.90 and the AUC for the testing data is 0.47

Fig. 22.8

Random forests variable importance for the top 20 most important spots

Fig. 22.9

ROC curve for the data. The AUC for the ROC is 0.77

Fig. 22.10

MARS variable importance

Fig. 22.11

ROC curves for the training and testing data. The blue curve represents the training data and the red curve represents the testing data. The AUC for the training data is 1.0 and theAUC for the testing data is 0.63

Fig. 22.12

GPS variable importance for the top 20 most important spots

Fig. 22.13

ROC curve for the data. The blue curve represents the training data; the red curve represents the testing data. The AUC for the training ROC is 1.0; the AUC for the testing data is 0.92

Fig. 22.14

Partial residual plot