SEPACS

SEPACS classifies seroreactivity profiles to differentiate disease and normal sera using immunogenic antigen sets identified in blood sera for minimally invasive disease detection and monitoring.

Key Features:

• Classification algorithms: Four variations of the Naïve Bayes classifier, Support Vector Machines (SVM) with a radial basis function kernel, Linear Discriminant Analysis (LDA), and Diagonal Discriminant Analysis (DDA).
• Training and prediction: Performs classification on labeled training sets and predicts unclassified seroreactivity profiles.
• Antigen-based profiling: Leverages immunogenic antigen sets identified in blood sera from patients with various diseases, including cancer.

Scientific Applications:

• Meningioma: Classification of seroreactivity profiles associated with meningioma to distinguish tumor and normal sera.
• Glioma: Classification of seroreactivity profiles associated with glioma to distinguish tumor and normal sera.
• Biomarker identification and disease monitoring: Identification of antigen sets that can serve as biomarkers for disease detection and monitoring using serum reactivity patterns.

Methodology:

Screening sera from diseased and unaffected individuals for specific antigens, then processing the resulting data set with the stated classification methods to differentiate tumor and normal sera and identify antigen sets as potential biomarkers.