New capability assists researchers and pharmaceutical firms in biomarker discovery and validation, discovering drug targets, and personalised medicine
Health Discovery has executed a non-exclusive worldwide license agreement with Bruker Daltonics covering Bruker Daltonics's use of HDC's Support Vector Machine (SVM) technology in the ClinProTools clinical proteomics product line.
ClinProTools is Bruker Daltonics's state-of-the-art bioinformatics solution for biomarker panel analysis, biofluid profiling, multivariate data analysis of large sample cohorts, classical statistics and sample classification.
The agreement provides for an up-front fee and royalties based on sales.
Herbert Fritsche, professor of laboratory medicine at the University of Texas's MD Anderson Cancer Center and chairman of HDC's Science Board, commented: "The combination of HDC's SVM pattern recognition technology with Bruker Daltonics's top-performing mass spectrometry systems - in particular its ClinProt product line - provides a significant advance in the field of biomarker discovery.
"This new capability will greatly assist diagnostic researchers and pharmaceutical companies in their efforts to discover new drug targets, early diagnostic tests, and companion diagnostics for monitoring drug therapy for personalized medicine".
"HDC is very excited about this new partnership with Bruker Daltonics," said Stephen Barnhill, HDC's chairman and chief executive officer.
"Bruker Daltonics is recognized as a leading innovator and developer of systems for clinical research based on mass spectrometry.
"Bruker's recognition of HDC's powerful SVM technology enhances its ability to meet the needs of its diverse customer base that includes the world's leading pharmaceutical and biotechnology companies".
Michael Schubert, executive vice president of Bruker Daltonics, stated: "We are pleased to enter into this agreement with HDC, the leader in SVM technology in bioinformatics applications.
"SVMs are high-performance supervised classification algorithms that can analyze high-dimensional mass spectrometric data from a plurality of sample cohorts.
"In essence, SVMs allow the mass spectrometer to become a more powerful system, thus complementing the use of other classification algorithms such as our Supervised Neural Network, our QuickClassifier, modified genetic algorithms, and others".
