ProteinChip Pattern Analysis Software

ProteinChip pattern analysis software allows simultaneous analysis of multiple biomarkers. Tracking multiple biomarkers increases statistical power, providing superior predictive value and greater utility in diagnosis, toxicology, patient stratification, and patient monitoring. The ability to detect patterns formed by multiple biomarkers greatly improves the sensitivity and specificity of an assay. With ProteinChip pattern analysis software, you can collect reproducible protein expression data on hundreds of proteins at once — opening the door to rapid, simplified pattern analysis.

Discover Predictive Protein Biomarker Patterns
Subtle variations found in SELDI data from clinical samples indicate that certain patterns of protein expression can predict phenotypes, such as the presence or absence of a certain disease, a particular stage of cancer progression, or a positive or adverse response to drug treatment. ProteinChip pattern analysis software supports both the discovery of multiple protein biomarkers and their translation to assays with high predictive accuracy. A particularly valuable feature of this software is that it provides a hierarchy of presumptive protein biomarkers that users can then proceed to identify, expediting the discovery of relevant functional information about the proteins.

Classify Samples Using the Decision Tree Model
Starting with SELDI peak intensity values from a "training set" of samples, ProteinChip pattern analysis software defines a single splitting rule that best segregates the training set by phenotype. The software repeats this process on each resulting subclassification of the data to produce a decision tree that describes the best set of rules for organizing the samples according to phenotype.

Incorporate Clinical Sample Information
Classification algorithms allow incorporation of non-SELDI data into the analysis. This can result in a better overall decision tree and help elucidate complex relationships between protein expression profiles and clinical data.