C04758: An Algorithm for the Discovery of Robust Protein Biomarkers with Application to the Design of Classification Protein Arrays
Novelty:
The current invention is a general, quantitative method for the selection of protein biomarkers supporting accurate, sensitive and specific classification of protein profiles.
Value Proposition:
Biomarker discovery and validation is a complex process that can give false results because of the possible artifacts introduced when interpreting the results from 2D gel or mass spectroscopy experiments. The inventors use a robust analytical method, TSP (Top Scoring Pair) that was originally developed for nucleic acid microarray experiments to give more reliable biomarkers with smaller sample sizes. This approach to the design of diagnostic arrays will apply to a range of human disease states, including but not limited to cardiovascular disease (heart failure, coronary artery disease, etc), pulmonary disease (asthma, COPD) and a range of cancers). Advantages include:
- Can be used with a variety of proteomic methods including mass spectrometry, 2D gel electrophoresis, and DIGE (Difference Gel Electrophoresis) to identify possible biomarker proteins .
- For a broad range of diseases in which the disease manifests itself through changes in protein expression in a tissue (such as a tumor, blood, etc) that could be procured through patient biopsy .
- Uses multiple protein biomarkers to perform diagnostic classification .
Technical Details:
Johns Hopkins researchers have developed a method for the discovery of protein pairs whose relative expression levels may be used to assign protein profiles to two or more diagnostic classes. This machine learning method may be used to select protein probe pairs whose relative expression levels typically invert between control and disease states. The “optimal” decision rule constructed by this machine learning method may then be used to classify data obtained from each protein array for the purposes of clinical diagnosis. The strategy for designing protein arrays is novel because it minimizes sources of within-assay and between-assay experimental variation on selection of biomarkers and describes an approach to synthesizing a diagnostic protein array.
Looking for Partners:
To develop and commercialize the technology as a method for the selection of protein biomarkers.
Stage of Development:
Pre-Clinical
Data Availability:
Under CDA/NDA
Publications/Associated Cases:
An Algorithm for the Discovery of Robust Protein Biomarkers With Application to the Design of Classification Protein Arrays. Proteomics 2007.
