An Annotation-Based Classifier for Drug-Discovery

The BORG database and classifier toolchain is a set of shell scripts and C application code to perform assimilation of protein annotation data from multiple sources and classify a set of proteins with respect to its possible relevance to a disease state based on the assimilated annotations.

The BORG database is available in three parts: the assimilator code, the classifier code, and the MySQL database of assimilated protein annotations.

• Assimilator source code
• Classifier source code
• MySQL database contents