Figure 1.
Algorithm framework for biomarker extraction.
Figure 2.
Algorithm framework for diagnostic class prediction.
Figure 3.
Sparse canonical correlation between proteomics and clinical profiles in the TB dataset.
The x-axis gives the score in the proteomics profile while the y-axis gives the score in the clinical profile. Data points labeled based on the three diagnostic classes Active TB (red), Symptomatic Control (green) and Asymptomatic Control (blue). Ellipses denote the mean and covariance of the class clusters.
Figure 4.
TB clinical variables (a.) and plasma proteome m/z clusters (b.) with non-negligible coefficients in the SCCA model.
Figure 5.
Sparse canonical correlation between proteomics and clinical profiles in the childhood severe malaria dataset.
The x-axis gives the score in the proteomics profile while the y-axis gives the score in the clinical profile. Data points labeled based on the four diagnostic classes Community Controls (black), Uncomplicated Malaria (purple), Severe Malaria Anaemia (blue) and Cerebral Malaria (red). Ellipses denote the mean and covariance of the class clusters.
Figure 6.
Malaria clinical variables (a.) and plasma proteome m/z clusters (b.) with non-negligible coefficients in the SCCA model.
Table 1.
Diagnostic class prediction in the TB dataset.
Table 2.
Diagnostic class prediction in the Malaria dataset.